Deep learning fusion of RGB and depth images for pedestrian detection

In this paper, we propose an effective method based on the Faster-RCNN structureto combine RGB and depth images for pedestrian detection. During the training stage,we generate a semantic segmentation map from the depth image and use it to refine theconvolutional features extracted from the RGB images. In addition, we acquire moreaccurate region proposals by exploring the perspective projection with the help of depthinformation. Experimental results demonstrate that our proposed method achieves thestate-of-the-art RGBD pedestrian detection performance on KITTI [12] datase

Jaar van publicatie:2019

Toegankelijkheid:Open