Making large-scale support vector machine learning practical
Advances in kernel methods
A decision-theoretic generalization of on-line learning and an application to boosting
EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory
Detecting Pedestrians Using Patterns of Motion and Appearance
International Journal of Computer Vision
Pedestrian detection and tracking with night vision
IEEE Transactions on Intelligent Transportation Systems
Associated evolution of a support vector machine-based classifier for pedestrian detection
Information Sciences: an International Journal
| Hi-index | 0.00 |
Optical camera based detection method is a popular system to fulfill pedestrian detection; however, it is difficult to be used to detect pedestrians in complicated environment (e.g. rainy or snowy weather conditions). The difficulties mainly include: (1) The light is much weaker than in sunny days, therefore it is more difficult to design an efficient classification mechanism; (2) Since a pedestrian always be partly covered, only using its global features (e.g. appearance or motion) may be mis-detected; (3) The mirror images on wet road will cause a lot of false alarms. In this paper, based on our pervious work, we introduce a new system for pedestrian detection in rainy or snowy weather. Firstly, we propose a cascaded classification mechanism; and then, in order to improve detection rate, we adopt local appearance features of head, body and leg as well as global features. Besides that, a specific classifier is designed to detect mirror images in order to reduce false positive rate. The experiments in a single optical camera based pedestrian detection system show the effeteness of the proposed system.