智能科学与技术学报 ›› 2021, Vol. 3 ›› Issue (3): 294-303.doi: 10.11959/j.issn.2096-6652.202130

• 专刊:目标智能检测与识别 • 上一篇    

基于差分特征注意力机制的无锚框多光谱行人检测算法

沈继锋1, 刘岳1, 韦浩2, 左欣3, 杨万扣4   

  1. 1 江苏大学电气信息工程学院,江苏 镇江 212013
    2 中电海康集团有限公司,浙江 杭州310000
    3 江苏科技大学计算机学院,江苏 镇江 212003
    4 东南大学自动化学院,江苏 南京 210003
  • 修回日期:2021-08-12 出版日期:2021-09-01 发布日期:2021-09-01
  • 作者简介:沈继锋(1980− ),男,博士,江苏大学电气信息工程学院副教授,主要研究方向为计算机视觉与模式识别
    刘岳(1994− ),男,江苏大学电气信息工程学院硕士生,主要研究方向为计算机视觉
    韦浩(1995− ),男,就职于中电海康集团有限公司,主要研究方向为计算机视觉
    左欣(1980− ),女,博士,江苏科技大学计算机学院副教授,主要研究方向为计算机视觉与模式识别
    杨万扣(1979− ),男,博士,东南大学自动化学院副研究员、博士生导师,主要研究方向为计算机视觉、模式识别与机器学习
  • 基金资助:
    国家自然科学基金资助项目(61903164);江苏省自然科学基金资助项目(BK20191427)

Anchor free multispectral pedestrian detection algorithm based on differential feature attention mechanism

Jifeng SHEN1, Yue1 LIU1, Hao WEI2, Xin ZUO3, Wankou YANG4   

  1. 1 School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China
    2 China Electric Haikang Group Co., Ltd., Hangzhou 310000, China
    3 School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, China
    4 School of Automation, Southeast University, Nanjing 210003, China
  • Revised:2021-08-12 Online:2021-09-01 Published:2021-09-01
  • Supported by:
    The National Natural Science Foundation of China(61903164);The Natural Science Foundation of Jiangsu Province(BK20191427)

摘要:

针对多光谱行人检测系统存在特征融合质量低、模型超参数多且锚框匹配算法复杂等问题,提出了一种基于差分特征注意力机制的无锚框多光谱行人检测算法。该算法首先采用差分特征感知融合方法挖掘多模态特征间的互补信息来优化通道特征;然后利用具有高效无锚框机制的CenterNet检测框架大大降低了模型计算复杂度,从而提升检测速度;最后引入差分特征注意力机制,改善特征融合质量,进一步提升检测精度。在KAIST、CVC14和FLIR这3个公开数据集上的实验结果表明,提出的算法和其他先进方法相比,能够同时有效提升检测精度和速度,具有较好的实际应用前景。

关键词: 多光谱行人检测, 无锚框机制, CenterNet模型, 注意力机制

Abstract:

Multispectral pedestrian detection system suffers with low feature fusion quality, high quantity of model hyper-parameters and complex anchor matching algorithm.To deal with these problems, an anchor free multispectral pedestrian detection algorithm based on differential feature attention mechanism was proposed.Firstly, differential modality aware fusion was used to obtain the complementary information between different modalities to optimize the channel features.Secondly, the CenterNet detection framework with anchor free mechanism was adopted to greatly reduce the computational complexity of the model and thus improve the detection speed.Finally, differential feature guided attention mechanism was introduced to improve the quality of feature fusion and further enhance the detection accuracy.Experimental results on three open datasets, KAIST, CVC14 and FLIR, show that the proposed algorithm can effectively improve the detection accuracy and speed compared with the current advanced methods, and has a good practical application prospect.

Key words: multispectral pedestrian detection, anchor free mechanism, CenterNet model, attention mechanism

中图分类号: 

No Suggested Reading articles found!