Year: 2009
Type: preprint
Abstract: This paper shows how to improve the real-time object detection in complex robotics applications, by exploring new visual features as AdaBoost weak classifiers. These new features are symmetric Haar filters (enforcing global horizontal and vertical symmetry) and N-connexity control points. Experimental evaluation on a car database show that the latter appear to provide the best results for the vehicle-detection problem.
Source: arXiv (Cornell University)
Institution: Centre de Robotique
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1886134489