2020/06/15 by Nils Gählert, Niklas Hanselmann, Gählert, Nils +5 · 18 citations
Computer Science · Engineering · Neuroscience · Psychology · #Advanced Neural Network Applications #Amodal perception #Artificial intelligence #Boosting (machine learning) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #FOS: Electrical engineering #Geography #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Neuroscience #Perception #Psychology #Robotics (cs.RO) #Video Surveillance and Tracking Methods #Visibility #Visual Attention and Saliency Detection #cs.CV #cs.LG #cs.RO #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2006.08547
published in arXiv (Cornell University) (Cornell University) · Machine Learning for Autonomous Driving Workshop at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada
arxiv created 2020/06/15 · openalex publication_date 2020/06/15 · arxiv updated 2020/06/16 · openalex created_date 2020/06/19 · openalex updated_date 2026/07/28
Object detection is an important task in environment perception for autonomous driving. Modern 2D object detection frameworks such as Yolo, SSD or Faster R-CNN predict multiple bounding boxes per object that are refined using Non-Maximum-Suppression (NMS) to suppress all but one bounding box. While object detection itself is fully end-to-end learnable and does not require any manual parameter selection, standard NMS is parametrized by an overlap threshold that has to be chosen by hand. In practice, this often leads to an inability of standard NMS strategies to distinguish different objects in crowded scenes in the presence of high mutual occlusion, e.g. for parked cars or crowds of pedestrians. Our novel Visibility Guided NMS (vg-NMS) leverages both pixel-based as well as amodal object detection paradigms and improves the detection performance especially for highly occluded objects with little computational overhead. We evaluate vg-NMS using KITTI, VIPER as well as the Synscapes dataset and show that it outperforms current state-of-the-art NMS.