Digital image processing (2nd ed.)
Digital image processing (2nd ed.)
A People-Counting System Using a Hybrid RBF Neural Network
Neural Processing Letters
Counting People in Crowds with a Real-Time Network of Simple Image Sensors
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Tracking Multiple Humans in Complex Situations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pedestrian Detection and Tracking for Counting Applications in Crowded Situations
AVSS '06 Proceedings of the IEEE International Conference on Video and Signal Based Surveillance
Real-time high density people counter using morphological tools
IEEE Transactions on Intelligent Transportation Systems
Estimation of number of people in crowded scenes using perspective transformation
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Video security for ambient intelligence
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Hi-index | 0.00 |
Real-time human tracking and pedestrian counting in very complex situations with different directions of motion has been important for video surveillance and our daily life applications. This work presents a virtual gate method for the pedestrian detection without the need to construct a background model a priori. The proposed method utilizes motion estimation with three step search and a novel motion vector analysis algorithm which detects moving objects passing through the gate along any desired direction. This method is particularly applicable to complex situations. The experimental results demonstrate that the proposed strategy is reliable.