面向遮挡行人检测的自适应收缩非极大值抑制方法
CSTR:
作者:
作者单位:

1. 中国科学院沈阳自动化研究所 光电信息处理重点实验室,沈阳 110016;2. 中国科学院机器人与智能制造创新研究院,沈阳 110169;3. 中国科学院大学,北京 100049

作者简介:

通讯作者:

E-mail: luohb@sia.cn.

中图分类号:

TP391

基金项目:


Adaptive shrinkage non-maximum suppression for occluded pedestrian detection
Author:
Affiliation:

1. Key Laboratory of Opto-Electronic Information Processing,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;2. Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110169,China;3. University of Chinese Academy of Sciences,Beijing 100049,China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    基于视觉的行人检测是目标检测中的重要研究方向.如今主流的基于锚框的行人检测器输出的结果是大量冗余的,在结果输出之前需要对冗余预测进行非极大值抑制,因而非极大值抑制的效果将直接影响检测器的性能.行人检测任务中最大的挑战在于目标之间互相遮挡的现象,而严重重叠的目标使得传统的基于固定阈值的非极大值抑制方法难以在高召回率与低虚警率之间取得平衡.针对以上问题,提出一种根据重叠度自适应收缩预测框的非极大值抑制方法.根据对应目标的重叠度将预测框进行自适应的收缩,以降低预测框之间的重叠度.对收缩后的预测框进行非极大值抑制,可避免高重叠预测框对处理结果的影响.此外,指向性不明确的预测框将影响本算法的性能,为此提出一种中心点排斥损失函数,通过在重叠框的中心点之间施加排斥力来减少介于两目标之间的指向性不明确的模糊预测框数量,增强自适应收缩非极大值抑制算法的效果.仿真实验结果表明,所提算法可以有效提升基于锚框的检测器对重叠行人目标的检测性能.

    Abstract:

    Vision-based pedestrian detection is an important research field in object detection. The outputs of current main-stream anchor-based detectors are redundancy, and the non-maximum suppression(NMS) is necessary before output predictions. Therefore, the effectiveness of NMS will influence detectors performance directly. The biggest challenge in pedestrian detection is the occlusion issue. Heavily overlapping objects make it difficult for NMS to balance between high recall rate and low false positive rate. An adaptive shrinkage NMS(AS-NMS) is proposed to reduce the overlapping degree of occluded objects' boxes by adaptively shrinking the corresponding prediction boxes. Implementing NMS to the shrunken prediction boxes can avoid the impact of occlusion issue. In addition, ambiguous prediction boxes will have negative impact toward AS-NMS, and a center point repulsion loss(CPR loss) is proposed to reduce the numbers of ambiguous boxes hovering between two objects by implement a repulsion force between the center points of overlapping boxes. The experimental results demonstrate that the proposed algorithm can significantly boost the performance of anchor-based detectors towards occluded pedestrian detection.

    参考文献
    相似文献
    引证文献
引用本文

李翔,何淼,罗海波.面向遮挡行人检测的自适应收缩非极大值抑制方法[J].控制与决策,2024,39(7):2177-2185

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-06-06
  • 出版日期: 2024-07-20
文章二维码