Abstract:
The performance of object detection has been improved as the success of deep architectures. The main algorithm predominantly used for general detection is Faster R-CNN be...Show MoreMetadata
Abstract:
The performance of object detection has been improved as the success of deep architectures. The main algorithm predominantly used for general detection is Faster R-CNN because of their high accuracy and fast inference time. In pedestrian detection, Region Proposal Network (RPN) itself which is used for region proposals in Faster R-CNN can be used as a pedestrian detector. Also, RPN even shows better performance than Faster R-CNN for pedestrian detection. However, RPN generates severe false positives such as high score backgrounds and double detections because it does not have downstream classifier. From this observations, we made a network to refine results generated from the RPN. Our Refinement Network refers to the feature maps of the RPN and trains the network to rescore severe false positives. Also, we found that different type of feature referencing method is crucial for improving performance. Our network showed better accuracy than RPN with almost same speed on Caltech Pedestrian Detection benchmark.
Published in: 2017 IEEE Intelligent Vehicles Symposium (IV)
Date of Conference: 11-14 June 2017
Date Added to IEEE Xplore: 31 July 2017
ISBN Information: