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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Refine pedestrian detections by referring to features in different ways


    Contributors:
    Lee, Jaemyung (author) / Lee, Sihaeng (author) / Kim, Youngdong (author) / Lee, Janghyeon (author) / Kim, Junmo (author)


    Publication date :

    2017-06-01


    Size :

    1334056 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Refine Pedestrian Detections by Referring to Features in Different Ways

    Lee, Jaemyung / Lee, Sihaeng / Kim, Youngdong et al. | British Library Conference Proceedings | 2017


    Distant Pedestrian Re-detection from an In-vehicle Camera Based on Detections by Other Vehicles

    Kawanishi, Yasutomo / Deguchi, Daisuke / Ide, Ichiro et al. | IEEE | 2015



    Electronics refine transmission control

    Bendix,Electr.and Engine Control Syst.Group,US | Automotive engineering | 1980


    Manufacturers refine their ranges

    British Library Online Contents | 2000