Symmetry-based recognition of vehicle rears
Pattern Recognition Letters
A Trainable System for Object Detection
International Journal of Computer Vision - special issue on learning and vision at the center for biological and computational learning, Massachusetts Institute of Technology
International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
A Grouping Principle and Four Applications
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
On-Road Vehicle Detection: A Review
IEEE Transactions on Pattern Analysis and Machine Intelligence
From Gestalt Theory to Image Analysis: A Probabilistic Approach
From Gestalt Theory to Image Analysis: A Probabilistic Approach
Survey of Pedestrian Detection for Advanced Driver Assistance Systems
IEEE Transactions on Pattern Analysis and Machine Intelligence
An A-Contrario Approach for Subpixel Change Detection in Satellite Imagery
IEEE Transactions on Pattern Analysis and Machine Intelligence
Simultaneous localization and object detection using an a-contrario approach
Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
Fast obstacle detection for urban traffic situations
IEEE Transactions on Intelligent Transportation Systems
Pedestrian Protection Systems: Issues, Survey, and Challenges
IEEE Transactions on Intelligent Transportation Systems
On Color-, Infrared-, and Multimodal-Stereo Approaches to Pedestrian Detection
IEEE Transactions on Intelligent Transportation Systems
Detecting moving objects, ghosts, and shadows in video streams
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
In the context of automotive driver assistance, we focus on object detection problem considering data acquired by an on-board stereo pair of cameras. The proposed approach is based on a two-level a-contrario model previously in the context of a fixed camera. In this study, the movement of the camera makes necessary the prediction of the current frame to the following instant. The objects are then detected at a window level as exceptional occurrences of clusters of also exceptional occurrences of significantly high pixel values in the image representing the difference with the predicted image from the previous frame. The term ‘exceptional realizations' refers to a ‘naive' model describing roughly the absence of objects. We show that such an approach is successful even when the movement of the camera is only approximately known, since the optimization of our criterion provides also the precise movement. Results on simulated and real data illustrate these statements.