Peng Chang

Collision Sensing by Stereo Vision and Radar Sensor Fusion

To take the advantages of both stereo cameras and radar, this paper proposes a fusion approach to accurately estimate the location, size, pose and motion information of a threat vehicle with respect to the host from observations obtained by both sensors. To do that, we first fit the contour of a threat vehicle from stereo depth information, and find the closest point on the contour from the vision sensor. Then the fused closest point is obtained by fusing radar observations and the vision closest point. Next by translating the fitted contour to the fused closest point, the fused contour is obtained. Finally the fused contour is tracked by using the rigid body constraints to estimate the location, size, pose and motion of the threat vehicle. Experimental results from both the synthetic data and the real world road test data demonstrate the success of the proposed algorithm.

Collision sensing by stereo vision and radar sensor fusion

To take the advantages of both stereo cameras and radar, this paper proposes a fusion approach to accurately estimate the location, size, pose and motion information of a threat vehicle with respect to the host from observations obtained by both sensors. To do that, we first fit the contour of a threat vehicle from stereo depth information, and find the closest point on the contour from the vision sensor. Then the fused closest point is obtained by fusing radar observations and the vision closest point. Next by translating the fitted contour to the fused closest point, the fused contour is obtained. Finally the fused contour is tracked by using the rigid body constraints to estimate the location, size, pose and motion of the threat vehicle. Experimental results from both the synthetic data and the real world road test data demonstrate the success of the proposed algorithm.

Stereo-Based Object Detection, Classi?cation, and Quantitative Evaluation with Automotive Applications

A real-time stereo-based pre-crash object detection and classification system is presented. The system employs a model based stereo object detection algorithm to find candidate objects from the scene, followed by a Bayesian classification framework to assign each candidate to its proper class. Our current system detects and classifies several types of objects commonly seen for automotive applications, namely vehicles, pedestrians/bikes, and poles. We describe both the detection and classification algorithms in detail along with real-time implementation issues. A quantitative analysis of performance on a static data set is also presented.

Stereo-based vision system for automotive imminent collision detection

Imminent collision detection is an important functionality in the area of automotive safety. In the event that an unavoidable collision can be detected in advance of the actual impact, various measures can be taken to mitigate injury and damage. In this paper, we demonstrate that stereo vision is a promising solution to this problem. Our prototype system has been rigorously tested for different colliding scenarios (e.g., different intersection angles and different travelling speeds), including live tests in an industrial crash-test facility. We explain the novel algorithms behind the system, including an algorithm for detecting objects in depth images, and algorithms for estimating the travelling velocity of detected vehicles. Quantitative results and representative examples are also included.

Closed-form Linear Solution To Motion Estimation In Disparity Space

Real-time stereovision systems play an important role in automotive related applications. This paper concerns the problem of rigid motion estimation with a stereovision sensor. Given a set of corresponding 3D points in Euclidean space reconstructed from stereovision, efficient linear algorithms exist to solve for the rigid motion. However it has been well known that the noise in the Euclidean reconstruction from stereovision is heteroscedastic and anisotropic, therefore the linear algorithms are only sub-optimal. A d-motion based algorithm has been developed to solve for the rigid motion directly in the disparity space, in which the noise can be approximated to be homogenous and isotropic. However this algorithm is nonlinear and requires iterative least-squares solution. By reformulating the problem, a closed-form linear solution is presented in this paper to solve for the rigid motion in disparity space. Synthetic experimental results show that this new algorithm outperforms the d-motion based algorithm in terms of both accuracy and computational cost. We believe that the closed-form linear solution is potentially very useful for applications making use of stereovision to estimate rigid motion