A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering

  title={A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering},
  author={Xin Zhao and Yue-qing Wang and Yong Dou},
  • Xin Zhao, Yue-qing Wang, Yong Dou
  • Published 2017
  • Computer Science
  • Non-maximum suppression is an important step in many object detection and object counting algorithms. In contrast with the extensive studies of object detection, NMS method has not caused too much attention. Although traditional NMS method has demonstrated promising performance in detection tasks, we observe that it is a hard decision approach, which only uses the confidential scores and Intersection-over-Unions (IoUs) to discard proposals. By this way, NMS method would keep many false… CONTINUE READING


    Publications referenced by this paper.
    Non-maximum Suppression for Object Detection by Passing Messages Between Windows
    • 92
    • PDF
    A Convnet for Non-maximum Suppression
    • 37
    • PDF
    SSD: Single Shot MultiBox Detector
    • 8,264
    • Highly Influential
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,444
    • PDF
    Efficient Non-Maximum Suppression
    • 537
    • PDF
    Mean shift analysis and applications
    • 1,038
    • PDF
    Clustering by Passing Messages Between Data Points
    • 5,079
    • PDF
    ImageNet: A large-scale hierarchical image database
    • 7,051
    • PDF