Abstract
For many pedestrian detectors, background vs. foreground errors heavily influence the detection quality. Our main contribution is to design semantic regions of interest that extract the foreground target roughly to reduce the background vs. foreground errors of detectors. First, we generate a pedestrian heat map from the input image with a full convolutional neural network trained on the Caltech Pedestrian Dataset. Next, semantic regions of interest are extracted from the heat map by morphological image processing. Finally, the semantic regions of interest divide the whole image into foreground and background to assist the decision-making of detectors. We test our approach on the Caltech Pedestrian Detection Benchmark. With the help of our semantic regions of interest, the effects of the detectors have varying degrees of improvement. The best one exceeds the state-of-the-art.
Highlights
Pedestrian detection is a canonical instance of object detection [1]
Pedestrian detection methods were basically based on HOG + SVM published in Conference on Computer Vision and Pattern Recognition (CVPR) 2005, worked out by French researchers Dalal and Triggs [2]
With our semantic regions of interest (SROI), the miss rate of HOG + SVM is reduced from 69% to 54% on the reasonable subset of the Caltech Pedestrian Detection Benchmark
Summary
Pedestrian detection is a canonical instance of object detection [1]. It is a challenging but important problem because it is a key technology in automotive safety, robotics and intelligent video surveillance.As these tasks have attracted much attention in the last few years, more and more researchers are involved in the study of pedestrian detection.In response to the challenges of pedestrian detection, three methods are often mentioned by researchers: HOG (Histogram of Oriented Gradient) + SVM (Support Vector Machine) rigid templates, deformable part detectors (DPM) and convolutional neural networks (ConvNets) [1]. Pedestrian detection is a canonical instance of object detection [1] It is a challenging but important problem because it is a key technology in automotive safety, robotics and intelligent video surveillance. As these tasks have attracted much attention in the last few years, more and more researchers are involved in the study of pedestrian detection. Deep learning has been the most popular method in the field of image processing. It has achieved perfect results in tracking, detection, segmentation and other fields
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
