We present a parallelized differentiable traffic simulator based on the Intelligent Driver Model (IDM), a car-following framework that incorporates driver behavior as key variables. Our vehicle simulator efficiently models vehicle motion, generating trajectories that can be supervised to fit real-world data. By leveraging its differentiable nature, IDM parameters are optimized using gradient-based methods. With the capability to simulate up to 2 million vehicles in real time, the system is scalable for large-scale trajectory optimization. We show that we can use the simulator to filter noise in the input trajectories (trajectory filtering), reconstruct dense trajectories from sparse ones (trajectory reconstruction), and predict future trajectories (trajectory prediction), with all generated trajectories adhering to physical laws. We validate our simulator and algorithm on several datasets including NGSIM and Waymo Open Dataset. The code is publicly available at: https://github.com/SonSang/diffidm.

We identify a bias in a commonly used dataset for building damage detection, evaluate its effects on existing deep learning models, and devise mitigation strategies to overcome it. We find that the data contains significantly more groups of damaged buildings than single ones leading to skewed machine learning evaluations. Consequently, deep learning models heavily rely on surrounding context rather than individual building damage when classifying supporting our claim. Specifically, the dataset includes extraneous damage surrounding buildings such as debris, fallen trees, and other damaged buildings which results in deep neural networks overfitting to these features. We analyze the top-5 solutions of the xView2 challenge, which focuses on building damage classification using satellite imagery as provided by the xBD dataset. Our experiments reveal that these models struggle to accurately identify isolated damaged buildings, potentially causing oversights in critical disaster scenarios and delaying humanitarian aid. Finally, we devise a new augmentation strategy to reduce this bias in disaster datasets and show it improves real-world outcomes.

In trajectory forecasting tasks for traffic, future output trajectories can be computed by advancing the ego vehicle’s state with predicted actions according to a kinematics model. By unrolling predicted trajectories via time integration and models of kinematic dynamics, predicted trajectories should not only be kinematically feasible but also relate uncertainty from one timestep to the next. While current works in probabilistic prediction do incorporate kinematic priors for mean trajectory prediction, variance is often left as a learnable parameter, despite uncertainty in one time step being inextricably tied to uncertainty in the previous time step. In this paper, we show simple and differentiable analytical approximations describing the relationship between variance at one timestep and that at the next with the kinematic bicycle model. In our results, we find that encoding the relationship between variance across timesteps works especially well in unoptimal settings, such as with small or noisy datasets. We observe up to a 50% performance boost in partial dataset settings and up to an 8% performance boost in large-scale learning compared to previous kinematic prediction methods on SOTA trajectory forecasting architectures out-of-the-box, with no fine-tuning.

Autonomous navigation has become increasingly popular in recent years; However, most existing methods focus on on-road navigation and utilize active sensors, such as LiDAR. This paper instead focuses on autonomous off-road navigation using traversability estimation from passive sensors, specifically long-wave (LW) hyperspectral imagery (HSI). We present a method for selecting a subset of hyperspectral bands that are most useful for traversability estimation by designing a band selection module that designs a minimal sensor that measures sparsely-sampled spectral bands while jointly training a semantic segmentation network for traversability estimation. The effectiveness of our method is demonstrated using our dataset of LW HSI from diverse off-road scenes including forest, desert, snow, ponds, and open fields. Our dataset includes imagery collected both during the daytime and nighttime during various weather conditions, including challenging scenes with a wide range of obstacles. Using our method, we learn a small subset (2%) of all the HSI bands that can achieve competitive or better traversability estimation accuracy to that achieved when utilizing all hyperspectral bands. Using only 5 bands, our method is able to achieve a mean class accuracy that is only 1.3% less than that achieved using full 256-band HSI and only 0.1% less than that achieved using 250-band HSI, demonstrating the success of our method.

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales. Such models overlook scale-specific information in the data for scale-dependent domains, such as remote sensing. In this paper, we present Scale-MAE, a pretraining method that explicitly learns relationships between data at different, known scales throughout the pretraining process. Scale-MAE pre-trains a network by masking an input image at a known input scale, where the area of the Earth covered by the image determines the scale of the ViT positional encoding, not the image resolution. Scale-MAE encodes the masked image with a standard ViT backbone, and then decodes the masked image through a bandpass filter to reconstruct low/high frequency images at lower/higher scales. We find that tasking the network with reconstructing both low/high frequency images leads to robust multiscale representations for remote sensing imagery. Scale-MAE achieves an average of a 2.4 − 5.6% non-parametric kNN classification improvement across eight remote sensing datasets compared to current state-of-the-art and obtains a 0.9 mIoU to 1.7 mIoU improvement on the SpaceNet building segmentation transfer task for a range of evaluation scales.

In this paper, we present the Multi-view Extended Videos with Identities (MEVID) dataset for large-scale, video person re-identification (ReID) in the wild. To our knowledge, MEVID represents the most-varied video person ReID dataset, spanning an extensive indoor and outdoor environment across nine unique dates in a 73-day window, various camera viewpoints, and entity clothing changes. Specifically, we label the identities of 158 unique people wearing 598 outfits taken from 8, 092 tracklets, average length of about 590 frames, seen in 33 camera views from the very-large-scale MEVA person activities dataset. While other datasets have more unique identities, MEVID emphasizes a richer set of information about each individual, such as: 4 outfits/identity vs. 2 outfits/identity in CCVID, 33 viewpoints across 17 locations vs. 6 in 5 simulated locations for MTA, and 10 million frames vs. 3 million for LS-VID. Being based on the MEVA video dataset, we also inherit data that is intentionally demographically balanced to the continental United States. To accelerate the annotation process, we developed a semi-automatic annotation framework and GUI that combines state-of-the-art real-time models for object detection, pose estimation, person ReID, and multi-object tracking. We evaluate several state-of-the-art methods on MEVID challenge problems and comprehensively quantify their robustness in terms of changes of outfit, scale, and background location. Our quantitative analysis on the realistic, unique aspects of MEVID shows that there are significant remaining challenges in video person ReID and indicates important directions for future research.

The goal of person search is to localize a target person from a gallery set of scene images, which is extremely challenging due to large scale variations, pose/viewpoint changes, and occlusions. In this paper, we propose the Cascade Occluded Attention Transformer (COAT) for end-to-end person search. Our three-stage cascade design focuses on detecting people in the first stage, while later stages simultaneously and progressively refine the representation for person detection and re-identification. At each stage the occluded attention transformer applies tighter intersection over union thresholds, forcing the network to learn coarse-to-fine pose/scale invariant features. Meanwhile, we calculate each detection's occluded attention to differentiate a person's tokens from other people or the background. In this way, we simulate the effect of other objects occluding a person of interest at the token-level. Through comprehensive experiments, we demonstrate the benefits of our method by achieving state-of-the-art performance on two benchmark datasets.

This paper introduces a novel geometrical solution for the pose estimation of a stereo camera system as commonly used in robotics, where the camera system balances between coverage and overlap. The proposed approach considers a set of features observed, respectively, in four, three and two views. In contrast to most algebraic solutions our constraints are geometrically meaningful. Initially, we use a four view feature to restrict our translation vector to lie on the surface of a sphere while setting orientation as a function of translation up to a single rotational degree of freedom. Next, we use a three view feature to restrict the translation vector to lie on a circle on the sphere, while completely defining orientation as a function of translation. Finally, we use a two view feature to determine the translation vector lying on the intersection of the circle and one of the generator lines of a doubly ruled quadric. We show how for this final step, the problem can be reduced to the intersection of two coplanar circles. We also analyze the degenerate configurations of the proposed solver and perform an experimental evaluation.

In this paper we present a novel system for real-time, six degree of freedom visual simultaneous localization and mapping using a stereo camera as the only sensor. The system makes extensive use of parallelism both on the graphics processor and through multiple CPU threads. Working together these threads achieve real-time feature tracking, visual odometry, loop detection and global map correction using bundle adjustment. The resulting corrections are fed back into to the visual odometry system to limit its drift over long sequences. We demonstrate our system on a series videos from challenging indoor environments with moving occluders, visually homogenous regions with few features, scene parts with large changes in lighting and fast camera motion. The total system performs its task of global map building in real time including loop detection and bundle adjustment on typical office building scale scenes.

In this paper we present a new minimal solver for the relative pose of a calibrated stereo camera (i.e. a pair of rigidly mounted cameras). Our method is based on the fact that a feature visible in all four images (two image pairs acquired at two points in time) constrains the relative pose of the second stereo camera to lie on a sphere around this feature, which has a known, triangulated position in the first stereo camera coordinate frame. This constraint leaves three degrees of freedom; two for the location of the second camera on the sphere, and the third for the rotation in the respective tangent plane. We use three 2D correspondences, in particular two correspondences from the left (or right) camera and one correspondence from the other camera, to solve for these three remaining degrees of freedom. This approach is amenable to stereo cameras having a small overlap in their views. We present an efficient solution for this novel relative pose problem, describe the incorporation of our proposed solver into the RANSAC framework, evaluate its performance given noise and outliers, and demonstrate its use in a real-time structure from motion system.

In this paper we present a real-time simultaneous localization and mapping system which uses a stereo camera as its only input. We combine the benefits of KLT feature tracking, which include high speed and robustness to repetitive features, with wide baseline features, which allow for feature matching after large camera motions. Updating the map of feature locations and camera poses is considerably more expensive than performing KLT tracking. For this reason we use the optical flow measured by the KLT tracker to adaptively select key frames for which we do a full map and camera pose update. In this way we limit the processing to only ¿interesting¿ parts of the video sequence. Additionally, we maintain a consistent scene scale at low cost by using a GPU implementation of multi-camera scene flow, a generalization of KLT to the motion of image features in three dimensions. The system uses multiple sub-maps; scalable, bag of features recognition and geometric verification to recover from motion estimation failure or ¿kidnapping¿. This architecture allows the robot to grow the existing map online and in real time while storing all of the data necessary for an off-line optimization to complete loops. We demonstrate the robustness of our system in a challenging indoor environment that includes semi-reflective glass walls and people moving in the scene.

The robust alignment of images and scenes seen from widely different viewpoints is an important challenge for camera and scene reconstruction. This paper introduces a novel class of viewpoint independent local features for robust registration and novel algorithms to use the rich information of the new features for 3D scene alignment and large scale scene reconstruction. The key point of our approach consists of leveraging local shape information for the extraction of an invariant feature descriptor. The advantages of the novel viewpoint invariant patch (VIP) are: that the novel features are invariant to 3D camera motion and that a single VIP correspondence uniquely defines the 3D similarity transformation between two scenes. In the paper we demonstrate how to use the properties of the VIPs in an efficient matching scheme for 3D scene alignment. The algorithm is based on a hierarchical matching method which tests the components of the similarity transformation sequentially to allow efficient matching and 3D scene alignment. We evaluate the novel features on real data with known ground truth information and show that the features can be used to reconstruct large scale urban scenes.

This paper introduces a novel, robust approach for 6DOF motion estimation of a multi-camera system with non-overlapping views. The proposed approach is able to solve the pose estimation, including scale, for a two camera system with non-overlapping views. In contrast to previous approaches, it degrades gracefully if the motion is close to degenerate. For degenerate motions the technique estimates the remaining 5DOF. The proposed technique is evaluated on real and synthetic sequences.

We introduce a novel approach to on-line structure from motion, using a pipelined pair of extended Kalman filters to improve accuracy with a minimal increase in computational cost. The two filters, a leading and a following filter, run concurrently on the same measurements in a synchronized producer-consumer fashion, but offset from each other in time. The leading filter estimates structure and motion using all of the available measurements from an optical flow based 2D tracker, passing the best 3D feature estimates, covariances, and associated measurements to the following filter, which runs several steps behind. This pipelined arrangement introduces a degree of noncausal behavior, effectively giving the following filter the benefit of decisions and estimates made several steps ahead. This means that the following filter works with only the best features, and can begin full 3D estimation from the very start of the respective 2D tracks. We demonstrate a reduction of more than 50% in mean reprojection errors using this approach on real data.