The problem of real-time multiclass object recognition is of great practical importance in object recognition. In this paper, we describe a framework that simultaneously utilizes shared representation, reconstruction sparsity, and parallelism to enable real-time multiclass object detection with deformable part models at 5Hz on a laptop computer with almost no decrease in task performance. Our framework is trained in the standard structured output prediction formulation and is generically applicable for speeding up object recognition systems where the computational bottleneck is in multiclass, multi-convolutional inference. We experimentally demonstrate the efficiency and task performance of our method on PASCAL VOC, subset of ImageNet, Caltech101 and Caltech256 dataset.

A real-time and accurate object detection framework, C(4), is proposed in this paper. C(4) achieves 20 fps speed and the state-of-the-art detection accuracy, using only one processing thread without resorting to special hardware such as GPU. The real-time accurate object detection is made possible by two contributions. First, we conjecture (with supporting experiments) that contour is what we should capture and signs of comparisons among neighboring pixels are the key information to capture contour cues. Second, we show that the CENTRIST visual descriptor is suitable for contour based object detection, because it encodes the sign information and can implicitly represent the global contour. When CENTRIST and linear classifier are used, we propose a computational method that does not need to explicitly generate feature vectors. It involves no image preprocessing or feature vector normalization, and only requires O(1) steps to test an image patch. C(4) is also friendly to further hardware acceleration. It has been applied to detect objects such as pedestrians, faces, and cars on benchmark data sets. It has comparable detection accuracy with state-of-the-art methods, and has a clear advantage in detection speed.

A real-time and accurate human detector, C4, is proposed in this paper. C4achieves 20 fps speed and state-of-the-art detection accuracy, using only one processing thread without resorting to special hardwares like GPU. Real-time accurate human detection is made possible by two contributions. First, we show that contour is exactly what we should capture and signs of comparisons among neighboring pixels are the key information to capture contours. Second, we show that the CENTRIST visual descriptor is particularly suitable for human detection, because it encodes the sign information and can implicitly represent the global contour. When CENTRIST and linear classifier are used, we propose a computational method that does not need to explicitly generate feature vectors. It involves no image pre-processing or feature vector normalization, and only requires O(1) steps to test an image patch. C4is also friendly to further hardware acceleration. In a robot with embedded 1.2GHz CPU, we also achieved accurate and 20 fps high speed human detection.

In this paper we consider the problem of searching for a target from a camera-equipped unmanned aerial vehicle (UAV) flying in an urban area. Urban areas present challenges because buildings can hamper the ability to see regions on the ground. We describe an algorithm that constructs paths that take into account obstructions due to buildings or other large objects. The approach combines search trees and a particle filters to evaluate a large number of possible paths, while at the same time performing all the Bayes' filter innovations that would need to occur during the evaluation of each path.

We present a minimal-point algorithm for finding fundamental matrices for catadioptric cameras of the parabolic type. Central catadioptric cameras-an optical combination of a mirror and a lens that yields an imaging device equivalent within hemispheres to perspective cameras-have found wide application in robotics, tele-immersion and providing enhanced situational awareness for remote operation. We use an uncalibrated structure-from-motion framework developed for these cameras to consider the problem of estimating the fundamental matrix for such cameras. We present a solution that can compute the para-catadioptirc fundamental matrix with nine point correspondences, the smallest number possible. We compare this algorithm to alternatives and show some results of using the algorithm in conjunction with random sample consensus (RANSAC).

In this paper, we present a vision-based terrain mapping and analysis system, and a model predictive control (MPC)-based flight control system, for autonomous landing of a helicopter-based unmanned aerial vehicle (UAV) in unknown terrain. The vision system is centered around Geyer et al.'s recursive multi-frame planar parallax algorithm (2006), which accurately estimates 3D structure using geo-referenced images from a single camera, as well as a modular and efficient mapping and terrain analysis module. The vision system determines the best trajectory to cover large areas of terrain or to perform closer inspection of potential landing sites, and the flight control system guides the vehicle through the requested flight pattern by tracking the reference trajectory as computed by a real-time MPC-based optimization. This trajectory layer, which uses a constrained system model, provides an abstraction between the vision system and the vehicle. Both vision and flight control results are given from flight tests with an electric UAV.

We present a novel approach for the estimation of 3D-motion directly from two images using the Radon transform. We assume a similarity function defined on the cross-product of two images which assigns a weight to all feature pairs. This similarity function is integrated over all feature pairs that satisfy the epipolar constraint. This integration is equivalent to filtering the similarity function with a Dirac function embedding the epipolar constraint. The result of this convolution is a function of the five unknown motion parameters with maxima at the positions of compatible rigid motions. The breakthrough is in the realization that the Radon transform is a filtering operator: If we assume that images are defined on spheres and the epipolar constraint is a group action of two rotations on two spheres, then the Radon transform is a convolution/correlation integral. We propose a new algorithm to compute this integral from the spherical harmonics of the similarity and Dirac functions. The resulting resolution in the motion space depends on the bandwidth we keep from the spherical transform. The strength of the algorithm is in avoiding a commitment to correspondences, thus being robust to erroneous feature detection, outliers, and multiple motions. The algorithm has been tested in sequences of real omnidirectional images and it outperforms correspondence-based structure from motion.

In this paper we consider the images taken from pairs of parabolic catadioptric cameras separated by discrete motions. Despite the nonlinearity of the projection model, the epipolar geometry arising from such a system, like the perspective case, can be encoded in a bilinear form, the catadioptric fundamental matrix. We show that all such matrices have equal Lorentzian singular values, and they define a nine-dimensional manifold in the space of 4 /spl times/ 4 matrices. Furthermore, this manifold can be identified with a quotient of two Lie groups. We present a method to estimate a matrix in this space, so as to obtain an estimate of the motion. We show that the estimation procedures are robust to modest deviations from the ideal assumptions.

Catadioptric sensors refer to the combination of lens-based devices and reflective surfaces. These systems are useful because they may have a field of view which is greater than hemispherical, providing the ability to simultaneously view in any direction. Configurations which have a unique effective viewpoint are of primary interest, among these is the case where the reflective surface is a parabolic mirror and the camera is such that it induces an orthographic projection and which we call paracatadioptric. We present an algorithm for the calibration of such a device using only the images of lines in space. In fact, we show that we may obtain all of the intrinsic parameters from the images of only three lines and that this is possible without any metric information. We propose a closed-form solution for focal length, image center, and aspect ratio for skewless cameras and a polynomial root solution in the presence of skew. We also give a method for determining the orientation of a plane containing two sets of parallel lines from one uncalibrated view. Such an orientation recovery enables a rectification which is impossible to achieve in the case of a single uncalibrated view taken by a conventional camera. We study the performance of the algorithm in simulated setups and compare results on real images with an approach based on the image of the mirror's bounding circle.

In this paper we present a new algorithm for structure from motion from point correspondences in images taken from uncalibrated catadioptric cameras with parabolic mirrors. We assume that the unknown intrinsic parameters are three: the combined focal length of the mirror and lens and the intersection of the optical axis with the image. We introduce a new representation for images of points and lines in catadioptric images which we call the circle space. This circle space includes imaginary circles, one of which is the image of the absolute conic. We formulate the epipolar constraint in this space and establish a new 4/spl times/4 catadioptric fundamental matrix. We show that the image of the absolute conic belongs to the kernel of this matrix. This enables us to prove that Euclidean reconstruction is feasible from two views with constant parameters and from three views with varying parameters. In both cases, it is one less than the number of views necessary with perspective cameras.

Surround perception is crucial for an immersive sense of presence in communication and for efficient navigation and surveillance in robotics. To enable surround perception, new omnidirectional systems were designed which gave a new impetus for rethinking the way images are acquired and analyzed. Based on insights gained from such designs, we formulate a novel unifying theory of imaging. We prove that all single viewpoint mirror-lens devices are equivalent to projective mappings from the sphere to the plane. These mappings are paired with a duality principle which relates points to line projections. The commonly used parabolic mirror projection is shown to be equivalent to the stereographic projection, providing therefore the invariants of a conformal mapping. It turns out that conventional cameras, which are only a special case in our theory, provide the barest minimum of information about the environment. We review current approaches to omnidirectional imaging and present a framework for calibration of omnidirectional cameras from single views.

Catadioptric systems are realizations of omnidirectional vision through mirror-lens combinations. Designs preserving the uniqueness of an effective viewpoint have recently gained attraction. We present here a novel approach for estimating the intrinsic parameters of a well-known catadioptric system consisting of a paraboloid mirror and an orthographic lens. We introduce the geometry of catadioptric line projection and we show that the vanishing points lie on a conic section which encodes the entire calibration information. Projections of two sets of parallel lines suffice for intrinsic calibration from one view as well as for metric rectification of a plane. Our approach overcomes limitations of existing manual calibration methods and was successfully tested on the task of back-warping real-images images onto virtual planes.