留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

夜间复杂场景下红外图像行人检测算法研究

赵双 陈树越 王巧月

赵双, 陈树越, 王巧月. 夜间复杂场景下红外图像行人检测算法研究[J]. 红外技术, 2021, 43(6): 575-582.
引用本文: 赵双, 陈树越, 王巧月. 夜间复杂场景下红外图像行人检测算法研究[J]. 红外技术, 2021, 43(6): 575-582.
ZHAO Shuang, CHEN Shuyue, WANG Qiaoyue. Infrared Pedestrian Detection in Complex Night Scenes[J]. Infrared Technology , 2021, 43(6): 575-582.
Citation: ZHAO Shuang, CHEN Shuyue, WANG Qiaoyue. Infrared Pedestrian Detection in Complex Night Scenes[J]. Infrared Technology , 2021, 43(6): 575-582.

夜间复杂场景下红外图像行人检测算法研究

基金项目: 

江苏省研究生科研创新基金项目 KYCX19_1770

详细信息
    作者简介:

    赵双(1995-),女,硕士,主要研究方向:模式识别(行人检测)。E-mail:zhsss1030@163.com

    通讯作者:

    陈树越(1963-),男,教授,主要研究方向:计算机视觉、图像处理。E-mail:csyue2000@163.com

  • 中图分类号: TP391

Infrared Pedestrian Detection in Complex Night Scenes

  • 摘要: 针对夜间红外图像中行人与背景灰度差异小且存在遮挡等问题,提出了一种夜间复杂场景下的红外行人检测算法。首先利用行人语义融合方法生成对目标全覆盖的显著图,与原图融合得到感兴趣区域,然后构造基于改进的方向梯度直方图特征的两分支分类器,同时提出一种遮挡判别算法,根据分类器模糊分数判断是否遮挡,设计一种头部模板实现最终的行人检测。在LSI远红外行人数据集和自主采集的冬、夏季节夜间行人数据上进行实验,结果表明:在不同环境下,所提出的方法均可快速鲁棒地检测出行人,可较显著地降低漏检率,检测率可达到94.20%。
  • 图  1  行人检测流程图

    Figure  1.  Pedestrian detection flow chart

    图  2  目标性计算示意图

    Figure  2.  Schematic diagram of target calculation

    图  3  HOG特征计算过程

    Figure  3.  HOG feature calculation process

    图  4  检测窗口分块

    Figure  4.  Detection window chunking

    图  5  头部检测模型

    Figure  5.  Head detection model

    图  6  样本示例:(a)(b)(c)冬季拍摄;(d)(e)(f)夏季拍摄

    Figure  6.  Sample diagram: (a)(b)(c) Shooting in winter; (d)(e)(f) Shooting in summer

    图  7  目标性检测

    Figure  7.  Schematic diagram of target detection

    图  8  不同算法检测效果对比

    Figure  8.  Detection effects of different algorithms

    表  1  两分支的SVM分类器训练参数

    Table  1.   SVM classifier training parameters of the two branches

    Window size Block size Cell size Step Bin Feature dimension
    Near target 48×96 16×16 8×8 8 9 1980
    Distant target 24×48 8×8 4×4 4 9 1980
    下载: 导出CSV

    表  2  测试数据的基本信息

    Table  2.   Basic information of test data

    Dataset Size/frame Date Location
    Test-L 2000 - -
    Test-W1 1578 2018/1/2 Street
    Test-W2 979 2018/1/3 Campus
    Test-S1 1123 2019/5/29 Street
    Test-S2 1089 2019/5/30 Campus
    下载: 导出CSV

    表  3  参数混淆矩阵

    Table  3.   Parameter confusion matrix

    Truth Predicted result
    Positive example Negative example
    Positive example TP FN
    Negative example FP TN
    下载: 导出CSV

    表  4  Wm标记结果

    Table  4.   Wm marking results

    Wm Picture number Pedestrian number Pedestrian mark Labeling rate/% Mark time/s
    5 500 774 630 81.4 5.94
    10 500 774 636 82.2 8.39
    50 500 774 671 86.7 12.70
    100 500 774 928 94.1 17.83
    150 500 774 751 97.0 23.29
    200 500 774 752 97.2 29.01
    350 500 774 755 97.6 44.00
    500 500 774 755 97.6 56.38
    下载: 导出CSV

    表  5  与基本算法检测结果对比

    Table  5.   Comparison of detection results with the basicalgorithm

    Algorithm ACC/% t/ms
    HOG 89.27 236.4
    TBHOG 86.19 122.8
    TBHOG+ROI extraction 91.44 159.0
    TBHOG+Occlusion handling 93.23 168.4
    TBHOG+ ROI extraction + occlusion handling 94.20 181.6
    下载: 导出CSV

    表  6  与其他算法检测效果对比

    Table  6.   Comparison of detection effect with other algorithms

    Algorithm LSI FIR test-W test-S
    ACC/% t/ms ACC/% t /ms ACC/% t/ms
    HOG 89.27 236.4 80.59 289.7 62.77 274.1
    LBP 85.21 202.3 77.90 304.5 59.25 294.5
    HOG-LBP 93.64 333.7 84.03 375.8 68.17 373.8
    ACF 94.05 1008 85.54 1469 64.28 1742
    RetinaNet 90.13 1364 82.21 1730 63.09 2297
    Proposed 94.20 181.6 89.17 264.7 73.64 285.3
    下载: 导出CSV
  • [1] XU Z, ZHUANG J, LIU Q, et al. Nighttime FIR pedestrian detection benchmark dataset for ADAS[C]// Proceedings of Pattern Recognition and Computer Vision, 2018: 323-333.
    [2] TAO Y, FU D, SHU P. Pedestrian tracking for infrared image sequence based on trajectory manifold of spatio-temporal slice[J]. Multimedia Tools and Applications, 2017, 76: 11021-11035. doi:  10.1007/s11042-016-3461-8
    [3] 刘洋. 基于LS-DYNA的汽车正面碰撞计算机模拟仿真[D]. 西安: 西华大学, 2011.

    LIU Yang. Simulation on the Front Impact of Vehicle Based on LS-DYNA[D]. Xi'an: Xihua University, 2011.
    [4] Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection[C]// 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 2005, 1(1): 886-893.
    [5] Bosch A, Zisserman A, Munoz X. Representing shape with a spatial pyramid kernel[C]//Acm International Conference on Image & Video Retrieval, 2007: 401-408(doi: https://doi.org/10.1145/1282280.1282340).
    [6] Sangeetha D, Deepa P. A low-cost and high-performance architecture for robust human detection using histogram of edge oriented gradients[J]. Microprocessors and Microsystems, 2017, 53: 106-119. doi:  10.1016/j.micpro.2017.07.009
    [7] ZHENG C H, PEI W J, YAN Q, et al. Pedestrian detection based on gradient and texture feature integration[J]. Neurocomputing, 2017, 228: 71-78. doi:  10.1016/j.neucom.2016.09.085
    [8] 朱聪聪, 项志宇. 基于梯度方向和强度直方图的红外行人检测[J]. 计算机工程, 2014, 40(12): 195-198, 204. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC201412037.htm

    ZHU Congcong, XIANG Zhiyu. Infrared pedestrian detection based on histograms of oriented gradients and intensity[J]. Computer Engineering, 2014, 40(12): 195-198, 204. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC201412037.htm
    [9] Itti L, Koch E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Trans., 1998, 20(11): 1254-1259 http://dl.acm.org/citation.cfm?id=297870
    [10] Radhakrishna A, Sheila H, Francisco E, et al. Frequency-tuned salient region detection[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009: (doi: 10.1109/CVPR.2009.5206596).
    [11] HOU X D, ZHANG L Q. Saliency detection: a spectral residual approach[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007: (doi: 10.1109/CVPR.2007.383267).
    [12] Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows[J]. IEEE Transactions on Software Engineering, 2012, 34(11): 2189-2202. http://newmed.wanfangdata.com.cn/Paper/Detail/PeriodicalPaper_PM22248633
    [13] WANG X, HAN T X, YAN S. An HOG-LBP human detector with partial occlusion handling[C]//12th International Conference on Computer Vision of IEEE, 2010: (doi: 10.1109/ICCV.2009.5459207).
    [14] Javier M N, Vazquez D, Lopez A M, et al. Occlusion handling via random subspace classifiers for human detection[J]. IEEE sTransactions on Cybernetics, 2013, 44(3): V342-354. http://www.ncbi.nlm.nih.gov/pubmed/23757554
    [15] Broggi A, Bertozzi M, Fascioli A, et al. Shape-based pedestrian detection[C]//IEEE Intelligent Vehicles Symposium, 2000: (doi: 10.1109/IVS.2000.898344).
    [16] Brehar R, Vancea C, Nedevschi S. Pedestrian detection in infrared images using aggregated channel features[C]//IEEE International Conference on Intelligent Computer Communication & Processing, 2014: (doi: 10.1109/ICCP.2014.p6936964).
    [17] LIN T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 99: 2999-3007. doi:  10.1109/ICCV.2017.324
    [18] 车凯, 向郑涛, 陈宇峰, 等. 基于改进Fast R-CNN的红外图像行人检测研究[J]. 红外技术, 2018, 40(6): 578-584. http://hwjs.nvir.cn/article/id/hwjs201806010

    CHE Kai, XIANG Zhengtao, CHEN Yufeng, et al. Research on infrared image pedestrian detection based on improved fast R-CNN[J]. Infrared Technology, 2018, 40(6): 578-584. http://hwjs.nvir.cn/article/id/hwjs201806010
  • 加载中
图(8) / 表(6)
计量
  • 文章访问数:  379
  • HTML全文浏览量:  223
  • PDF下载量:  57
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-07-02
  • 修回日期:  2019-11-25
  • 刊出日期:  2021-06-20

目录

    /

    返回文章
    返回