In this paper, we present a new compact vision sensor consisting of two fisheye event cameras mounted back-to-back, which offers a full 360-degree view of the surrounding environment. We describe the optical design, projection model and practical calibration using the incoming stream of events, of the novel stereo camera, called SFERA. The potential of SFERA for real-time target tracking is evaluated using a Bayesian estimator adapted to the geometry of the sphere. Real-world experiments with a prototype of SFERA, including two synchronized Prophesee EVK4 cameras and a DJI Mavic Air 2 quadrotor, show the effectiveness of the proposed system for aerial surveillance.

Autonomous driving systems require robust object detection in complex environments. Event cameras outperform RGB cameras under challenging lighting conditions, but face limitations due to the scarcity of available datasets and lack of specialized training. To narrow the gap between RGB- and event-based detection accuracy and avoid the high complexity of real-time RGB-event fusion, in this paper, we propose a knowledge distillation framework. Our approach uses both modalities during training but relies solely on sparse event data at inference and transfers knowledge from a robust RGB-based teacher model. We build on the success of DETR (DEtection TRansformer) and we leverage an event-aware masked knowledge distillation mechanism, to boost event-based detection accuracy. Experiments on the DSEC-DET dataset demonstrate that our method not only excels in challenging driving scenarios where RGB images are unreliable, but also surpasses the state-of-the-art in event-based object detection.

In rapidly-evolving domains such as autonomous driving, the use of multiple sensors with different modalities is crucial to ensure high operational precision and stability. To correctly exploit the provided information by each sensor in a single common frame, it is essential for these sensors to be accurately calibrated. In this paper, we leverage the ability of Neural Radiance Fields (NeRF) to represent different sensors modalities in a common volumetric representation to achieve robust and accurate spatio-temporal sensor calibration. By designing a partitioning approach based on the visible part of the scene for each sensor, we formulate the calibration problem using only the overlapping areas. This strategy results in a more robust and accurate calibration that is less prone to failure. We demonstrate that our approach works on outdoor urban scenes by validating it on multiple established driving datasets. Results show that our method is able to get better accuracy and robustness compared to existing methods.

On the one hand, cameras of conventional field-of-view usually considered in computer vision and robotics are very often modeled as a pinhole plus possibly a distortion model. On the other hand, there is a large variety of models for panoramic cameras. Many camera models have been proposed for fisheye cameras, catadioptric cameras, and super fisheye cameras. But in both cases, few models offer the possibility of converting them into another model.This paper contributes to filling this gap in, to allow an algorithm designed with a projection model to accept data of a camera calibrated with another model. So, a pre-existing data set can be used without having to recalibrate the camera. We provide the methodology and mathematical developments for three conversions considering three different types of cameras that are evaluated with respect to calibration and within a visual Simultaneous Localization And Mapping benchmark. The source code of the camera model conversions studied in this paper is shared within the libPeR library for Perception in Robotics: https://github.com/PerceptionRobotique/libPeRbase.

Reliable multimodal sensor fusion algorithms require accurate spatiotemporal calibration. Recently, targetless calibration techniques based on implicit neural representations have proven to provide precise and robust results. Nevertheless, such methods are inherently slow to train given the high computational overhead caused by the large number of sampled points required for volume rendering. With the recent introduction of 3D Gaussian Splatting as a faster alternative to implicit representation methods, we propose to leverage this new rendering approach to achieve faster multi-sensor calibration. We introduce 3DGS-Calib, a new calibration method that relies on the speed and rendering accuracy of 3D Gaussian Splatting to achieve multimodal spatiotemporal calibration that is accurate, robust, and with a substantial speed-up compared to methods relying on implicit neural representations. We demonstrate the superiority of our proposal with experimental results on sequences from KITTI-360, a widely used driving dataset.

Self-supervised monocular depth prediction is a widely researched field that aims to provide a better scene understanding. However, most existing methods prioritize prediction accuracy over computation cost, which can hinder the deployment of these methods in real-world applications. Our objective is to propose a solution that efficiently compresses the depth map while maintaining a high level of accuracy for navigation purpose. The proposed method is an expansion of the work presented in N-QGN, which utilizes a quadtree representation for compression. This approach has already shown promising results, but we aim to improve it further by making it more accurate, faster, and easier to train. Therefore, we introduce a new method that directly predicts the quadtree structure, resulting in a more consistent prediction, and we revise the network architecture to be lighter and produce state-of-the-art accuracy results, depending on the data compression rate. The new implementation is also faster, making it more suitable for real-time applications. Experiments have been conducted on various scene configuration highlighting the capability of the method to efficiently predicting a reliable quadtree depth representation of the scene at low computation cost and high accuracy.

With the recent advances in autonomous driving and the decreasing cost of LiDARs, the use of multimodal sensor systems is on the rise. However, in order to make use of the information provided by a variety of complimentary sensors, it is necessary to accurately calibrate them. We take advantage of recent advances in computer graphics and implicit volumetric scene representation to tackle the problem of multi-sensor spatial and temporal calibration. Thanks to a new formulation of the Neural Radiance Field (NeRF) optimization, we are able to jointly optimize calibration parameters along with scene representation based on radiometric and geometric measurements. Our method enables accurate and robust calibration from data captured in uncontrolled and unstructured urban environments, making our solution more scalable than existing calibration solutions. We demonstrate the accuracy and robustness of our method in urban scenes typically encountered in autonomous driving scenarios.

Monocular depth estimation has been a popu-lar area of research for several years, especially since self-supervised networks have shown increasingly good results in bridging the gap with supervised and stereo methods. However, these approaches focus their interest on dense 3D reconstruction and sometimes on tiny details that are superfluous for autonomous navigation. In this paper, we propose to address this issue by estimating the navigation map under a quad tree representation. The objective is to create an adaptive depth map prediction that only extract details that are essential for the obstacle avoidance. Other 3D space which leaves large room for navigation will be provided with approximate distance. Experiment on KITTI dataset shows that our method can significantly reduce the number of output information without major loss of accuracy.

In this paper, we present a relative pose estimation algorithm based on lines knowing the vertical direction associated to each image. We demonstrate that a closed-form solution requiring only eight lines between three views is possible. As a linear solution, it is shown that our approach outperforms the standard trifocal estimation based on 13 triplets of lines and can be efficiently inserted into an hypothesize-and-test framework such as RANSAC. We also study our approach on different singular configurations of lines. The method is evaluated on both synthetic data and real-world sequences from KITTI and the Zürich Urban Micro Aerial Vehicle datasets. Our method is compared to 13 lines algorithm as well to points based methods such as 7-points, 5-points and 3-points.

The idea of cooperation has been introduced to self-driving cars about a decade ago with the aim to reduce the occlusion caused by other users or the scene. More recently, the research efforts turned toward cooperative infrastructure bringing a new kind of the point of view as well as more processing power. This paper lies in this new field providing a survey that addresses the cooperative environment. We provide an overview of the architectures available to create such a system as well as the challenges introduced by the cooperation. Later, we review the main blocks involved in the perception: localization, object detection & tracking, map generation. Each block is reviewed under the prism of cooperation. We also provide a Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis of the cooperative perception as well as a list of related scenarios alongside experimentations. Finally, we list some related datasets before concluding our paper, underlining the perspectives for further works.

Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemented and still raise a lot of interest even though their theoretical expressive power is limited to the first order Weisfeiler-Lehman test (1-WL). In this paper, we show that if the graph convolution supports are designed in spectral-domain by a non-linear custom function of eigenvalues and masked with an arbitrary large receptive field, the MPNN is theoretically more powerful than the 1-WL test and experimentally as powerful as a 3-WL existing models, while remaining spatially localized. Moreover, by designing custom filter functions, outputs can have various frequency components that allow the convolution process to learn different relationships between a given input graph signal and its associated properties. So far, the best 3-WL equivalent graph neural networks have a computational complexity in $\mathcal{O}(n^3)$ with memory usage in $\mathcal{O}(n^2)$, consider non-local update mechanism and do not provide the spectral richness of output profile. The proposed method overcomes all these aforementioned problems and reaches state-of-the-art results in many downstream tasks.

Despite the utility and benefits of omnidirectional images in robotics and automotive applications, there are no datasets of omnidirectional images available with semantic segmentation, depth map, and dynamic properties. This is due to the time cost and human effort required to annotate ground truth images. This paper presents a framework for generating omnidirectional images using images that are acquired from a virtual environment. For this purpose, we demonstrate the relevance of the proposed framework on two well-known simulators: CARLA Simulator, which is an open-source simulator for autonomous driving research, and Grand Theft Auto V (GTA V), which is a very high quality video game. We explain in details the generated OmniScape dataset, which includes stereo fisheye and catadioptric images acquired from the two front sides of a motorcycle, including semantic segmentation, depth map, intrinsic parameters of the cameras and the dynamic parameters of the motorcycle. It is worth noting that the case of two-wheeled vehicles is more challenging than cars due to the specific dynamic of these vehicles.

In this paper we present minimal solutions for two-view relative motion estimation based on a homography formulation. By assuming a known vertical direction (e.g. from an IMU) and assuming a dominant ground plane we demonstrate that rotation and translation estimation can be decoupled. This result allows us to reduce the number of point matches needed to compute a motion hypothesis. We then derive different algorithms based on this decoupling that allow an efficient estimation. We also demonstrate how these algorithms can be used efficiently to compute an optimal inlier set using exhaustive search or histogram voting instead of a traditional RANSAC step. Our methods are evaluated on synthetic data and on the KITTI data set, demonstrating that our methods are well suited for visual odometry in road driving scenarios.

Recent progress in 3D sensor devices and in semantic mapping allows to build very rich HD 3D maps very useful for autonomous navigation and localization. However, these maps are particularly huge and require important memory capabilities as well computational resources. In this paper, we propose a new method for summarizing a 3D map (Mesh)as a set of compact spheres in order to facilitate its use by systems with limited resources (smartphones, robots, UAVs,...). This vision-based summarizing process is applied in a fully automatic way using jointly photometric, geometric and semantic information of the studied environment. The main contribution of this research is to provide a very compact map that maximizes the significance of its content while maintaining the full visibility of the environment. Experimental results in summarizing large-scale 3D map demonstrate the feasibility of our approach and evaluate the performance of the algorithm.

In this paper, we explore the different minimal solutions for egomotion estimation of a camera based on homography knowing the gravity vector between calibrated images. These solutions depend on the prior knowledge about the reference plane used by the homography. We then demonstrate that the number of matched points can vary from two to three and that a direct closed-form solution or a Gröbner basis based solution can be derived according to this plane. Many experimental results on synthetic and real sequences in indoor and outdoor environments show the efficiency and the robustness of our approach compared to standard methods.

Visual surveillance of dynamic objects, particularly vehicles on the road, has been, over the past decade, an active research topic in computer vision and intelligent transportation systems communities. In the context of traffic monitoring, important advances have been achieved in environment modeling, vehicle detection, tracking, and behavior analysis. This paper is a survey that addresses particularly the issues related to vehicle monitoring with cameras at road intersections. In fact, the latter has variable architectures and represents a critical area in traffic. Accidents at intersections are extremely dangerous, and most of them are caused by drivers' errors. Several projects have been carried out to enhance the safety of drivers in the special context of intersections. In this paper, we provide an overview of vehicle perception systems at road intersections and representative related data sets. The reader is then given an introductory overview of general vision-based vehicle monitoring approaches. Subsequently and above all, we present a review of studies related to vehicle detection and tracking in intersection-like scenarios. Regarding intersection monitoring, we distinguish and compare roadside (pole-mounted, stationary) and in-vehicle (mobile platforms) systems. Then, we focus on camera-based roadside monitoring systems, with special attention to omnidirectional setups. Finally, we present possible research directions that are likely to improve the performance of vehicle detection and tracking at intersections.

This paper investigates the problem of registering a scanned scene, represented by 3D Euclidean point coordinates, and two or more uncalibrated cameras. An unknown subset of the scanned points have their image projections detected and matched across images. The proposed approach assumes the cameras only known in some arbitrary projective frame and no calibration or autocalibration is required. The devised solution is based on a Linear Matrix Inequality (LMI) framework that allows simultaneously estimating the projective transformation relating the cameras to the scene and establishing 2D-3D correspondences without triangulating image points. The proposed LMI framework allows both deriving triangulation-free LMI cheirality conditions and establishing putative correspondences between 3D volumes (boxes) and 2D pixel coordinates. Two registration algorithms, one exploiting the scene's structure and the other concerned with robustness, are presented. Both algorithms employ the Branch-and-Prune paradigm and guarantee convergence to a global solution under mild initial bound conditions. The results of our experiments are presented and compared against other approaches.

This paper deals with the problem of registering a known structured 3D scene and its metric Structure-from-Motion (SfM) counterpart. The proposed work relies on a prior plane segmentation of the 3D scene and aligns the data obtained from both modalities by solving the point-to-plane assignment problem. An inliers-maximization approach within a Branch-and-Bound (BnB) search scheme is adopted. For the first time in this paper, a Sum-of-Squares optimization theory framework is employed for identifying point-to-plane mismatches (i.e. outliers) with certainty. This allows us to iteratively build potential inliers sets and converge to the solution satisfied by the largest number of point-to-plane assignments. Furthermore, our approach is boosted by new plane visibility conditions which are also introduced in this paper. Using this framework, we solve the registration problem in two cases: (i) a set of putative point-to-plane correspondences (with possibly overwhelmingly many outliers) is given as input and (ii) no initial correspondences are given. In both cases, our approach yields outstanding results in terms of robustness and optimality.

In this paper we present an unsynchronized camera network able to estimate the motion and the structure with accurate absolute scale. The proposed algorithm requires at least three frames: two frames from one camera and a frame from a neighbouring camera. The relative camera poses are estimated with classical Structure-from-Motion and the absolute scales between views are computed by assuming straight trajectories between consecutive views of one camera. We propose a final optimisation step to refine only the scale and the 3D points. Our method is evaluated in real conditions on the KITTI dataset. We show quantitative evaluation through comparisons against GPS/INS ground truth.

In this paper, we propose a car positioning approach that does not rely on GPS. We propose to use car wheel speeds and road maps in order to achieve robust positioning of the vehicle. The vehicle positioning is achieved by applying particle filtering on a graph-based representation of a road map. We show that the vehicle positioning is feasible and robust with these two inputs at a really low computational cost. We achieve car positioning with an averaged 5 m accuracy within a 100 km drivable road map on a 12 km sequence.

This paper introduces a new framework to improve the performance of Viola and Jones face detector on omnidirectional unwrapped images. First, an optimization scheme is used to improve the unwrapped image specifically for rectangular Haar-like features. Then, we compare our unwrapping approach to the performance obtained with spherical unwrapping. The impact of the decision boundary and candidate window density are also investigated. Our work suggests that our new unwrapping technique improves significantly the performance of Viola and Jones detector on omnidirectional unwrapped images.

In this paper we propose a robust and direct 2D-to-3D registration method for localizing 2D cameras in a known 3D environment. Although the 3D environment is known, localizing the cameras remains a challenging problem that is particularly undermined by the unknown 2D-3D correspondences, outliers, scale ambiguities and occlusions. Once the cameras are localized, the Structure-from-Motion reconstruction obtained from image correspondences is refined by means of a constrained nonlinear optimization that benefits from the knowledge of the scene. We also propose a common optimization framework for both localization and refinement steps in which projection errors in one view are minimized while preserving the existing relationships between images. The problem of occlusion and that of missing scene parts are handled by employing a scale histogram while the effect of data inaccuracies is minimized using an M-estimator-based technique.

In this paper are presented simple and practical solutions to extrinsic calibration between a camera and a 2D laser sensor, without overlap. Previous methods utilized a plane or an intersecting line of two planes as a geometric constraint with enough common field-of-view. These required additional sensors to calibrate non-overlapping systems. In this paper, we present two methods for solving the problem - one utilizes a plane; the other utilizes an intersecting line of two planes. For each method, an initial solution of the relative positions of a non-overlapping camera and a laser sensor, was computed by adopting a reasonable assumption about geometric structures. Then we refined it via non-linear optimization, even if the assumption was not perfectly satisfied. Both simulation results and experiments using real data showed that the proposed methods provided reliable results compared to ground-truth, and similar or better results than those provided by a conventional method.

In this paper, we tackle the problem of map estimation from small set of vehicular GPS traces collected from low cost devices. Contrary to the existing works, we rely only on GPS information. First, we propose a fast implementation of Kalman filtering of spline-based road modeling. Our approach demonstrates a significant boost of the computation speed while maintained a good estimation error. Secondly, we perform an evaluation of our algorithm on real world data. Our estimation is compared to a high grade Inertial Navigation System and vectorial data gathered from major map providers. Our results suggest that a good performance can be achieved from the fusion of multiple GPS traces collected from multiple vehicles and drivers.

This article studies the feasibility of an exteroceptive system for the contactless control of a motion-compensated gangway which can be used for maintenance operations on offshore wind farms. Our study shows that current systems based only on inertial systems are not accurate enough to ensure the gangway is held in place without being secured mechanically. Using measurements from a 2D LIDAR system, we propose a method for the real-time monitoring of the position of the gangway in relation to the offshore wind turbine. Our algorithm involves detecting and estimating the position of the wind turbine pile in a 2D scatter diagram using robust approaches. To evaluate our method, we have installed a real-time 3D simulation chain fed with data from actual measurements. We obtain a measurement accuracy of the order of a centimeter, in real time, in representative sea state scenarios.

Accurate estimation of camera motion is very important for many robotics applications involving SfM and visual SLAM. Such accuracy is attempted by refining the estimated motion through nonlinear optimization. As many modern robots are equipped with both 2D and 3D cameras, it is both highly desirable and challenging to exploit data acquired from both modalities to achieve a better localization. Existing refinement methods, such as Bundle adjustment and loop closing, may be employed only when precise 2D-to-3D correspondences across frames are available. In this paper, we propose a framework for robot localization that benefits from both 2D and 3D information without requiring such accurate correspondences to be established. This is carried out through a 2D-3D based initial motion estimation followed by a constrained nonlinear optimization for motion refinement. The initial motion estimation finds the best possible 2D-to-3D correspondences and localizes the cameras with respect the 3D scene. The refinement step minimizes the projection errors of 3D points while preserving the existing relationships between images. The problems of occlusion and that of missing scene parts are handled by comparing the image-based reconstruction and 3D sensor measurements. The effect of data inaccuracies is minimized using an M-estimator based technique. Our experiments have demonstrated that the proposed framework allows to obtain a good initial motion estimate and a significant improvement through refinement.

This paper presents a visual odometry with metric scale estimation of a multi-camera system in challenging un-synchronized setup. The intended application is in the field of intelligent vehicles. We propose a new algorithm named “triangle-based” method. The proposed algorithm employs the information from both extrinsic and intrinsic parameters of calibrated cameras. We assume that the trajectory between two consecutive frames of a camera is a linear segment (straight trajectory). The relative camera poses are estimated via classical Structure-from-Motion. Then, the scale factors are computed by imposing the known extrinsic parameters and the linearity assumption. We verify the validity of our method both in simulated and real conditions. For the real world, the motion trajectory estimated for image sequence of two cameras from KITTI dataset is compared against the GPS/INS ground truth.

Data correspondence/grouping under an unknown parametric model is a fundamental topic in computer vision. Finding feature correspondences between two images is probably the most popular application of this research field, and is the main motivation of our work. It is a key ingredient for a wide range of vision tasks, including three-dimensional reconstruction and object recognition. Existing feature correspondence methods are based on either local appearance similarity or global geometric consistency or a combination of both in some heuristic manner. None of these methods is fully satisfactory, especially in the presence of repetitive image textures or mismatches. In this paper, we present a new algorithm that combines the benefits of both appearance-based and geometry-based methods and mathematically guarantees a global optimization. Our algorithm accepts the two sets of features extracted from two images as input, and outputs the feature correspondences with the largest number of inliers, which verify both the appearance similarity and geometric constraints. Specifically, we formulate the problem as a mixed integer program and solve it efficiently by a series of linear programs via a branch-and-bound procedure. We subsequently generalize our framework in the context of data correspondence/grouping under an unknown parametric model and show it can be applied to certain classes of computer vision problems. Our algorithm has been validated successfully on synthesized data and challenging real images.

Bio-inspired and non-conventional vision systems are highly researched topics. Among them, omnidirectional vision systems have demonstrated their ability to significantly improve the geometrical interpretation of scenes. However, few researchers have investigated how to perform object detection with such systems. The existing approaches require a geometrical transformation prior to the interpretation of the picture. In this paper, we investigate what must be taken into account and how to process omnidirectional images provided by the sensor. We focus our research on face detection and highlight the fact that particular attention should be paid to the descriptors in order to successfully perform face detection on omnidirectional images. We demonstrate that this choice is critical to obtaining high detection rates. Our results imply that the adaptation of existing object-detection frameworks, designed for perspective images, should be focused on the choice of appropriate image descriptors in the design of the object-detection pipeline.

The projections of world parallel lines in an image intersect at a single point called the vanishing point (VP). VPs are a key ingredient for various vision tasks including rotation estimation and 3D reconstruction. Urban environments generally exhibit some dominant orthogonal VPs. Given a set of lines extracted from a calibrated image, this paper aims to (1) determine the line clustering, i.e. find which line belongs to which VP, and (2) estimate the associated orthogonal VPs. None of the existing methods is fully satisfactory because of the inherent difficulties of the problem, such as the local minima and the chicken-and-egg aspect. In this paper, we present a new algorithm that solves the problem in a mathematically guaranteed globally optimal manner and can inherently enforce the VP orthogonality. Specifically, we formulate the task as a consensus set maximization problem over the rotation search space, and further solve it efficiently by a branch-and-bound procedure based on the Interval Analysis theory. Our algorithm has been validated successfully on sets of challenging real images as well as synthetic data sets.

This paper presents a single camera and laser system dedicated to the realtime estimation of attitude and altitude for unmanned aerial vehicles (UAV) under low illumination conditions to dark environments. The fisheye camera allows to cover a large field of view (FOV). The approach, close to structured light systems, uses the geometrical information obtained by the projection of a laser circle onto the ground plane and perceived by the camera. We propose some experiments based on simulated data and real sequences. The results show good agreement with the ground truth values from the commercial sensors in terms of its accuracy and correctness. The results also prove its suitability for autonomous take-off and landing as well as for the case of low altitude manoeuvre in dark, GPS signal deficient unknown environments with no prebuilt map. It also provides room for additional payload to be used for different applications due to it being inexpensive and use of light weight micro-camera and laser system.

This paper presents a system dedicated to the real-time estimation of attitude and altitude for unmanned aerial vehicles (UAV) under low light and dark environment. This system consists in a fisheye camera, which allows to cover a large field of view (FOV), and a laser circle projector mounted on a fixed baseline. The approach, close to structured light systems, uses the geometrical information obtained by the projection of the laser circle onto the ground plane and perceived by the camera. We present a theoretical study of the system in which the camera is modelled as a sphere and show that the estimation of a conic on this sphere allows to obtain the attitude and the altitude of the robot. We propose some experiments based on simulated data and real sequences. The estimated attitude and altitude from our method are comparable with commercial sensors in terms of its accuracy and correctness. The results also prove its suitability for autonomous take-off and landing as well as for the case of low altitude manoeuvre in dark environments. It also provides room for additional payload to be used for different applications due to use of light weight micro-camera and laser system.

We present an algorithm for reconstruction of piece-wise planar scenes from only two views and based on minimum line correspondences. We first recover camera rotation by matching vanishing points based on the methods already exist in the literature and then recover the camera translation by searching among a family of hypothesized planes passing through one line. Unlike algorithms based on line segments, the presented algorithm does not require an overlap between two line segments or more that one line correspondence across more than two views to recover the translation and achieves the goal by exploiting photometric constraints of the surface around the line. Experimental results on real images prove the functionality of the algorithm.

We present a translation estimation method for single viewpoint (SVP) cameras using line features. Images captured by multiple central cameras such as perspective, central catadioptric and fisheye cameras are mapped to spherical images using the unified projection model. It is possible to recover the camera rotations using vanishing points of parallel line sets. We then estimate the translations from known rotations and line images on the spheres. The algorithm has been validated on simulated data and real images. This vision-based estimation approach can be applied in navigation of autonomous robots besides the conventional devices such as Global Positioning System (GPS) and Inertial Navigation System (INS). It helps vision-based localization of a single robot or recovery of relative positions among multiple robots equipped with different types of cameras.

This paper presents a method for catadioptric line matching across multiple images. While most of previous works deals with vertical lines and planar motion, our approach is able to match any kind of lines between two views separated by a rigid transformation without any prior knowledge of the epipolar geometry. Catadioptric lines are represented by their normals in sphere space and we use only these normals and their relative positions in order to perform the matching. A geometric hashing approach allows in the first image to construct hashing tables based on bases defined by every possible couples of normals. In the second image, a voting scheme permits to select the best corresponding bases and subsequently to match catadioptric lines.We show that the proposed representation is invariant in the case of a pure rotation and quasi-invariant for a combination of rotation and translation. We also propose different experimental results obtained in real time on real outdoor sequences.

Whereas some methods for plane extraction have been proposed, this problem still remains an open issue due to the complexity of the task. This paper especially focuses on the extraction of points lying on a plane (such as the ground and buildings walls) in sequences acquired by a central omnidirectional camera. Our approach is based on the epipolar constraint for planar scenes (i.e. homography) on a pair of omnidirectional images to detect some interest points belonging to a plane. Our main contribution is the introduction of a new method, called “2-point algorithm for homography”, that imposes some constraints on the homography using vanishing point (VP) information. Compared to the widely used DLT (4-point) algorithm, experiments on real data demonstrated that the proposed “2-point algorithm for homography” is more robust to noise and false matching, even when the plane to extract is not dominant in the image. Finally, we show that our system provides key clues for ground segmentation by GrabCut.

Altitude is one of the most important parameters to be known for an Unmanned Aerial Vehicle (UAV) especially during critical maneuvers such as landing or steady flight. In this paper, we present mixed stereoscopic vision system made of a fish-eye camera and a perspective camera for altitude estimation. Contrary to classical stereoscopic systems based on feature matching, we propose a plane sweeping approach in order to estimate the altitude and consequently to detect the ground plane. Since there exists a homography between the two views and the sensor being calibrated and the attitude estimated by the fish-eye camera, the algorithm consists then in searching the altitude which verifies this homography. We show that this approach is robust and accurate, and a CPU implementation allows a real time estimation. Experimental results on real sequences of a small UAV demonstrate the effectiveness of the approach.

International audience

Due to distorsions of catadioptric sensors, omnidirectional images can not be treated as classical images. If the equivalence between central catadioptric images and spherical images is now well known and used, spherical analysis often leads to complex methods particularly tricky to employ. In this paper, we propose to derive omnidirectional image treatments by using geodesic metric. We demonstrate that this approach allows to adapt efficiently classical image processing to omnidirectional images.

Unmanned Aerial Vehicles (UAV) are the subject of an increasing interest in many applications and a key requirement for autonomous navigation is the attitude/position stabilization of the vehicle. Some previous works have suggested using catadioptric vision, instead of traditional perspective cameras, in order to gather much more information from the environment and therefore improve the robustness of the UAV attitude/position estimation. This paper belongs to a series of recent publications of our research group concerning catadioptric vision for UAVs. Currently, we focus on the extraction of skyline in catadioptric images since it provides important information about the attitude/position of the UAV. For example, the DEM-based methods can match the extracted skyline with a Digital Elevation Map (DEM) by process of registration, which permits to estimate the attitude and the position of the camera. Like any standard cameras, catadioptric systems cannot work in low luminosity situations because they are based on visible light. To overcome this important limitation, in this paper, we propose using a catadioptric infrared camera and extending one of our methods of skyline detection towards catadioptric infrared images. The task of extracting the best skyline in images is usually converted in an energy minimization problem that can be solved by dynamic programming. The major contribution of this paper is the extension of dynamic programming for catadioptric images using an adapted neighborhood and an appropriate scanning direction. Finally, we present some experimental results to demonstrate the validity of our approach.

Most of vision-based algorithms for motion and localization estimation requires matching some interest points in a pair of images. After building feature correspondence, it is possible to estimate camera motion/localization using epipolar geometry. However feature matching is still a challenging problem because of time constraint or image variability for example. In several robotic applications, the camera rotation may be known thanks to a gyroscope or another orientation sensor. Therefore, in this paper, we aim to answer the following question: can the knowledge of rotation from a gyroscope be used to improve feature matching. To analyze this new approach of camera and gyroscope data fusion, we proceed in two steps. First, we rotationally align the images using rotation information of the gyroscope. And second, we compare the quality of feature matching in the original and rotationally aligned images. Experimental results on a real catadioptric sequence show that gyroscope data permits to sensibly improve the number of inliers according to epipolar geometry.

Unmanned aerial vehicles (UAV) are the subject of an increasing interest in many applications and a key requirement is the stabilization of the vehicle. Some previous works have suggested using catadioptric vision, instead of traditional perspective cameras, in order to gather much more information from the environment and therefore improve the robustness of the UAV attitude estimation. This paper belongs to a series of recent publications of our research group concerning catadioptric vision for UAVs. Currently, we focus on the estimation of the complete attitude of a UAV flying in urban environment. In order to avoid the limitations of horizon-based approaches, the difficulties of traditional epipolar methods (such as rotation-translation ambiguity, lack of features, retrieving motion parameters from matrix decomposition, etc..) and improve UAV dynamic control, we suggest computing infinite homography. We show how catadioptric vision plays a key role to: first, extract a large number of lines, second robustly estimate the associated vanishing points and third, track them even during long video sequences. Therefore it is not only possible to estimate the relative rotation between consecutive frames but also compute the absolute rotation between two distant frames without error accumulation. Finally, we present some experimental results with ground truth data to demonstrate the accuracy and the robustness of our method.

A key requirement for unmanned aerial vehicles (UAV) applications is the attitude stabilization of the aircraft, which requires the knowledge of its orientation. It is now well established that traditional navigation equipments, like GPS or INS, suffer from several disadvantages. That is why some works have suggested a vision-based approach of the problem. Especially, catadioptric vision is more and more used since it permits to gather much more information from the environment, compared to traditional perspective cameras, and therefore the robustness of the UAV attitude estimation is improved. Rotation estimation from conventional and catadioptric images has been extensively studied. Whereas interesting results can be obtained, the existing methods have non-negligible limitations such as difficult features matching (e.g. repeated texture, blurring or illumination changing) or a high computational cost (e.g. vanishing point extraction or analyze in frequency domain). In order to overcome these limitations, this paper presents a top-down approach for estimating the rotation and extracting the vanishing points in catadioptric images. This new framework is accurate and can run in real-time. To obtain the ground truth data, we also calibrate our catadioptric camera with a gyroscope. Finally, experimental results on a real video sequence are presented and compared to the ground truth data obtained by the gyroscope.

Camera calibration is an important step for vision-based stabilization of unmanned aerial vehicles (UAV). The goal of this paper is to develop a method for automatic calibration of a catadioptric camera so that it can be easily run before mounting the camera on the UAV or even during the flight to deal with vibrations or shocks. Whereas existing works can provide interesting results, they suffer from several practical limitations (manual line extraction, inaccurate conic fitting, calibration pattern, camera motion, execution time, etc...) and therefore cannot be applied in our application. The proposed algorithm aims to determine the most probable calibration that verifies some geometric constraints induced by catadioptric projection. In order to efficiently maximize this probability, we use a particle filtering approach. Experimental results have demonstrated the effectiveness of the proposed method.

Nowadays, robotic systems are more and more equipped with catadioptric cameras. However several problems associated to catadioptric vision have been studied only slightly. Especially algorithms for detecting rectangles in catadioptric images have not yet been developed whereas it is required in diverse applications such as building extraction in aerial images. We show that working in the equivalent sphere provides an appropriate framework to detect lines, parallelism, orthogonality and therefore rectangles. Finally, we present experimental results on synthesized and real data.

Attitude is one of the most important parameters for a UAV during a flight. Attitude computation methods based vision generally use the horizon line as reference. However, the horizon line becomes an inadequate feature in urban environment. We then propose in this paper an omnidirectional vision system based on straight lines (very frequent in urban environment) that is able to compute the roll and pitch angles. The method consists in finding bundles of horizontal and vertical parallel lines in order to obtain an absolute reference for the attitude computation. We also develop here a new and efficient method for line extraction and bundle of parallel line detection. An original method of horizontal and vertical plane detection is also provided. We show experimental results on different images extracted from video sequences.

Unmanned aerial vehicles (UAVs) are the subject of an increasing interest in many applications. Autonomy is one of the major advantages of these vehicles. It is then necessary to develop particular sensors in order to provide efficient navigation functions. In this paper, we propose a method for attitude computation catadioptric images. We first demonstrate the advantages of the catadioptric vision sensor for this application. In fact, the geometric properties of the sensor permit to compute easily the roll and pitch angles. The method consists in separating the sky from the earth in order to detect the horizon. We propose an adaptation of the Markov random fields for catadioptric images for this segmentation. The second step consists in estimating the parameters of the horizon line thanks to a robust estimation algorithm. We also present the angle estimation algorithm and finally, we show experimental results on synthetic and real images captured from an airplane

Attitude (roll and pitch) is an essential data for the navigation of a UAV. Rather than using inertial sensors, we propose a catadioptric vision system allowing a fast, robust and accurate estimation of these angles. We show that the optimization of a sky/ground partitioning criterion associated with the specific geometric characteristics of the catadioptric sensor provides very interesting results. Experimental results obtained on real sequences are presented and compared with inertial sensor measures

This paper introduces a vision system for road traffic surveillance from sequences acquired from an unmanned aerial vehicle (UAV). During the navigation of the UAV, the vision system acquires sequences which are treated in order to detect vehicles. The dynamic behavior of the UAV-camera system makes a fixed background impossible : we present a new approach based on the "common fate" principle : image primitives which have the same type of movement (or displacement) are grouped. The detection of vehicles is then based on the spatiotemporal grouping of primitives formulated as a normalized cuts problem. A verification step based on the Dempster-Shafer theory is also proposed in order to recognize vehicles.

This paper presents a vision system for road traffic surveillance from sequences acquired from an unmanned aerial vehicle (UAV). This UAV is able to follow a path considered as the surveillance area and defined by a set of ordered GPS points. During the navigation of the UAV, the vision system acquires sequences which are treated in real-time in order to detect vehicles. This detection allows to perform a traffic estimation or to track a pointed out vehicle. The detection of vehicles is based on the spatiotemporal grouping of primitives formulated as a normalized cuts problem. A verification step based on the Dempster-Shafer theory is also proposed in order to recognize the vehicles.

Central catadioptric sensors enable to acquire panoramic images on a 360 degree field of view while preserving a single viewpoint. These advantages account for the growing use of these sensors in applications such as surveillance, navigation or modelling. However, the deformations of the image do not allow to apply classical perspective image algorithms or operators. Typically, straight line detection in perspective image becomes a delicate and complex conic detection problem in central catadioptric image. Previous methods proposed in the literature were essentially motivated by particular cases such as horizontal line detection or paracatadioptric line detection. In this paper, we propose an algorithm which consists in performing the detection in the space of the equivalent sphere which is the unified domain of central catadioptric sensors. On this sphere, real lines are projected into great circles that we detect thanks to the Hough transform. We also propose to apply this unifying model in order to perform the calibration of the intrinsic parameters required for the projection on the sphere. We show results on synthetic and real catadioptric images (parabolic, hyperbolic) to demonstrate the relevance of the detection on the sphere.

We present a method to calibrate the omnidirectional sensor used in our laboratory, named SYCLOP (conic system for localization and perception). This system, which is able to capture a panoramic image of a 2/spl pi/ radian field, consists of a CCD camera and a vertically oriented conic shaped reflector. In order to have a better precision than that obtained in classical applications using this kind of sensors, we consider the importance of calibration for the whole sensor. After having briefly recalled the theoretical framework used in hard calibration, we design the different transformations made between world object, cone reflector and pictures, as well as the different types of relationship between the world, the cone, the camera and the image coordinates. Finally, we present results obtained with the SYCLOP simulator and an experiment.

In this article we present a navigation system allowing a mobile robot to be localized in an indoor environment which is only partially known. This system integrates an environment map updating module allowing the mobile robot to estimate the position of new vertical landmarks along its path. An extended Kalman filter is used on the one hand to estimate the mobile robot position and on the other hand to extract observations which will be used to determine the positions of unlisted landmarks. The integration of new landmarks into the environment global map is managed from the covariance matrix associated with each unlisted landmark. We present the experimental results we have got with SARAH, our mobile robot.

In this paper we present a dynamic localization system which allows a mobile robot to evolve autonomously in a structured environment. Our system is based on the use of two sensors: an odometer and an omnidirectional vision system which gives a reference in connection with a set of natural beacons. Our navigation algorithm gives a reliable position estimation due to a systematic dynamic resetting. To merge the data obtained we use the extended Kalman filter. Our proposed method allows us to treat efficiently the noise problems linked to the primitive extraction, which contributes to the robustness of our system. Thus, we have developed a reliable and quick navigation system which can deals with the constraints of moving the robots in an industrial environment. We give the experimental results obtained from a mission realized in an a priori known environment.