Segmentation of Pedestrians with Confidence Level Computation

In this work, we propose a mechanism to segment groups of pedestrians with confidence level computation for intelligent surveillance systems. The goal is to specify the number of people and locate the position and size of each individual in groups of people. Human detection and clustering techniques are combined to achieve the segmentation purpose. The histogram of oriented gradients and curvelet features are extracted for full body detection using a support vector machine classifier. Modified Haar of Oriented Gradient features are constructed for upper body and lower body detectors. A clustering algorithm is then applied to the detected humans to eliminate the redundant detection responses. The proposed mechanism requires no prior assumptions of human sizes, human heights, camera distances, and other calibration parameters. Moreover, confidence level computation can provide valuable information for subsequent surveillance applications. The proposed approach is tested with pedestrian benchmark dataset and surveillance videos. The experimental results have demonstrated the effectiveness of the proposed pedestrian segmentation mechanism.