Title :
Hardware-friendly pedestrian detection and impact prediction
Author :
Abramson, Yotam ; Steux, Bruno
Author_Institution :
Center of robotics, Ecole des Mines de Paris, France
Abstract :
We present a system for pedestrian detection and impact prediction, from a frontal camera situated on a moving vehicle. The system combines together the output of several algorithms to form a reliable detection and positioning of pedestrians. One of the important contributions of this paper is a highly-efficient algorithm for classification of pedestrian images using a learned set of features, each feature based on a 5×5 pixels shape. The learning of the features is done using AdaBoost and genetic-like algorithms. The described application was developed as a part of the CAMELLIA project, thus all the algorithms used in this application are designed to use a special set of low level image processing operations provided by the smart imaging core developed in the project. Fusion of the various algorithms results and tracking of pedestrians is done using particle filtering, providing a good tool to predict the future movement of pedestrians, in order to estimate impact probability.
Keywords :
computer vision; filtering theory; genetic algorithms; image classification; object detection; probability; tracking; vehicles; Adaboost; CAMELLIA project; camera; genetic algorithms; hardware friendly pedestrian detection; image processing; impact prediction; impact probability; moving vehicle; particle filtering; pedestrian image classification; pedestrian position; pedestrian tracking; smart imaging core; Algorithm design and analysis; Cameras; Classification algorithms; Filtering algorithms; Image processing; Particle tracking; Pixel; Shape; Vehicle detection; Vehicles;
Conference_Titel :
Intelligent Vehicles Symposium, 2004 IEEE
Print_ISBN :
0-7803-8310-9
DOI :
10.1109/IVS.2004.1336450