Pedestrian Detection Based on Background Compensation with Block-Matching Algorithm
Khouloud Chebli, Anouar Ben Khalifa · 2018
The development of autonomous vehicle is an important and active research area. In the last few years, pedestrian detection methods for a moving camera have been severely developed. This field presents many challenges in order to avoid the camera motion and recognize the dynamic objects. This paper proposes a background compensation method for pedestrian detection with a moving Camera. This method relies on motion compensation to transfer the background model from the current frame to the previous frame in order to detect dynamic obstacles. This motion compensation is carried out using different block matching algorithms and the gradient information of the images to establish the background's model motion. The proposed method was evaluated on a public benchmark system: the CVC14 and achieved promising results as shown in this article.