PROJECT TITLE :
A Pedestrian-Detection Method Based on Heterogeneous Features and Ensemble of Multi-View–Pose Parts
Vision-based pedestrian detection remains a challenging task, therefore far. The detection performance often suffers from the varied appearances of pedestrians, the illumination changes, and therefore the potential partial occlusions. Aiming at resolving these challenges, in this paper, a new linear kernel perform is proposed to effectively mix 2 heterogeneous features, i.e., histogram of oriented gradient and local binary pattern, which enhances the pedestrian description ability to illumination conditions and cluttered background. Then, a novel multi-view-cause half ensemble (MVPPE) detector is proposed, so as to higher handle pedestrian variability, views, and partial occlusions. Experimental ends up in public data sets demonstrate that the proposed feature combination methodology considerably improves the outline capabilities of pedestrian features. Compared with the existing multipart ensemble approaches, the proposed MVPPE detector boosts higher detection accuracy.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here