Extraction of foreground area of pedestrian objects under thermal infrared video surveillance
-
摘要:
在热红外视频监控环境下，针对热红外图像因周围环境温度变化而导致热红外图像灰度值反转的问题，提出了一种通过热红外图像的边界特征和运动特征的融合来提取行人目标前景区域的方法。首先，利用行人目标和周围环境存在的显著性差异来提取行人目标的边界特征，对所提取的边界特征进行边界填充，并利用热红外行人目标分类器来排除误检目标，从而获取最终的边界特征提取结果；其次，利用相邻帧之间的运动信息来获取行人目标的运动特征，对所获取的运动特征进行形态学处理，并利用热红外行人目标分类器来排除误检目标，从而获取最终的运动特征提取结果；最后，对所获取的边界特征提取结果和运动特征提取结果进行融合来获得最终的检测结果。实验证明，在公开的OSU和LSI热红外图像行人目标检测数据集中，所提方法能够有效地降低环境温度变化的不利影响，并提高行人目标前景区域提取的精度。
Abstract:Under the thermal infrared video surveillance, in order to solve the problem of the gray value inversion in thermal infrared image caused by the changes in ambient temperature, this paper proposes a method of extracting the foreground area of pedestrian objects by the fusion of boundary feature and motion feature in the thermal infrared images. First, the boundary feature of the pedestrian objects are extracted by using the significant differences existing between the pedestrian objects and the surrounding environment, and then the extracted boundary feature is subjected to area filling, which is followed by the elimination of the false detection objects by using thermal infrared pedestrian objects classifier, thus obtaining the final boundary feature extraction results. Second, the motion feature of the pedestrian objects are obtained by using the motion information between adjacent frames, and then the resulting motion feature is subjected to the morphological processing, which is followed by the elimination of the false detection objects by using thermal infrared pedestrian objects classifier, thus obtaining the final motion feature extraction results. Finally, the final boundary feature extraction results and the final motion feature extraction results are fused to obtain the final detection results. Our experiments show that the proposed method can effectively reduce the adverse effects brought about by the changes in ambient temperature, and further improve the extraction accuracy of foreground area of the pedestrian objects on the OSU and LSI thermal infrared image pedestrian objects detection dataset.
-
Key words:
- boundary feature /
- motion feature /
- foreground area /
- pedestrian objects detection /
- gray value
-
图 1 行人目标前景区域提取的方法流程
Figure 1. Method flow for extraction of pedestrian object foreground area
图 4 OSU热红外行人目标检测数据集实验效果
Figure 4. Experimental results on OSU thermal infrared pedestrian objects detection dataset
图 5 LSI热红外行人目标检测数据集实验效果
Figure 5. Experimental results on LSI thermal infrared pedestrian objects detection dataset
表 1 OSU热红外行人目标检测数据集性能评价指标
Table 1. Performance evaluation indexes of OSU thermal infrared pedestrian objects detection dataset
下载: 导出CSV
-
[1] MA Y L, WU X K, YU G Z, et al.Pedestrian detection and tracking from low-resolution unmanned aerial vehicle thermal imagery[J].Sensors, 2016, 16(4):446. doi: 10.3390/s16040446 [2] 宫文靖.基于视频的红外运动目标检测研究与应用[D].成都: 电子科技大学, 2016.GONG W J.Research and application of video-based infrared moving target detection[D].Chengdu: University of Electronic Science and Technology of China, 2016(in Chinese). [3] LEE J H, CHOI J S, JEON E S, et al.Robust pedestrian detection by combining visible and thermal infrared cameras[J].Sensors, 2015, 15(5):10580-10615. doi: 10.3390/s150510580 [4] ZHANG L, WU B, NEVATIA R.Pedestrian detection in infrared images based on local shape features[C]//Proceeding of 2007 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway: IEEE Press, 2007: 1-8. [5] 李娟.基于智能视觉技术的公安视频侦查研究[J].法制与社会, 2019(33):206-207. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzysh201933105LI J.Research on public security video investigation based on intelligent vision technology[J].Legal System and Society, 2019(33):206-207(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzysh201933105 [6] 郭丽静.视频监控在公安工作中的应用[J].电子技术与软件工程, 2018(10):140. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0120181102488262GUO L J.Application of video surveillance in public security work[J].Electronic Technology and Software Engineering, 2018(10):140(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0120181102488262 [7] 夏宇.浅述公安视频监控系统现状与发展要求[J].中国安防, 2014(20):86-89. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgafcpxx201420021XIA Y.On the status and development requirements of public security video surveillance system[J].China Security, 2014(20):86-89(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgafcpxx201420021 [8] 姜正财, 周川.智能视频监控系统中引入红外热成像技术的探究[J].电子制作, 2017(16):27-28. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dzzz201716011JIANG Z C, ZHOU C.Exploration of infrared thermal imaging technology in intelligent video surveillance system[J].Electronic Production, 2017(16):27-28(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dzzz201716011 [9] BISWAS S K, MILANFAR P.Linear support tensor machine with LSK channels:Pedestrian detection in thermal infrared images[J].IEEE Transactions on Image Processing, 2017, 26(9):4229-4242. doi: 10.1109/TIP.2017.2705426 [10] WANG Y, ZHU L Q, YU Z J.Foreground detection for infrared videos with multiscale 3-D fully convolutional network[J].IEEE Geoscience and Remote Sensing Letters, 2019, 16(5):712-716. doi: 10.1109/LGRS.2018.2881053 [11] 许茗, 于晓升, 陈东岳, 等.复杂热红外监控场景下行人检测[J].中国图象图形学报, 2018, 23(12):1829-1837. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgtxtxxb-a201812005XU M, YU X S, CHEN D Y, et al.Downward human detection in complex thermal infrared surveillance scenes[J].Journal of Image and Graphics, 2018, 23(12):1829-1837(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgtxtxxb-a201812005 [12] THOMAS O, FRANK B.Moving object detection and event recognition algorithms for smart cameras[C]//Proceedings of DARPA Image Understanding Workshop, 1997: 205-208. [13] TANG Q, DAI S G, YANG J.Object tracking algorithm based on camshift combining background subtraction with three frame difference[J].Applied Mechanics and Materials, 2013, 373-375:1116-1119. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.4028/www.scientific.net/AMM.373-375.1116 [14] APARNA A, NIDHI K, RIPUL G, et al.Adaptive contour-based statistical background subtraction method for moving target detection in infrared video sequences[J].Infrared Physics & Technology, 2013, 63:103-109. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=f83a79780372ae074f7e3e83934b8055 [15] SUN D Q, ROTH S, BLACK M J.A quantitative analysis of current practices in optical flow estimation and the principles behind them[J].International Journal of Computer Vision, 2014, 106(2):115-137. doi: 10.1007/s11263-013-0644-x [16] ALSULAMI F, AHMADI K, SALARI E.Detection and tracking of dim objects in infrared (IR) images using support vector machine[C]//2016 IEEE International Conference on Electro Information Technology (EIT).Piscataway: IEEE Press, 2016: 357-361. [17] SHAIK J, IFTEKHARUDDIN K M.Detection and tracking of targets in infrared images using Bayesian techniques[J].Optics and Laser Technology, 2009, 41(6):832-842. doi: 10.1016/j.optlastec.2008.11.007 [18] DAVIS J W, SHARMA V.Robust background-subtraction for person detection in thermal imagery[C]//IEEE International Workshop on Object Tracking & Classification Beyond the Visible Spectrum.Piscataway: IEEE Press, 2004: 128. [19] SADJADI F A.Infrared target detection with probability density functions of wavelet transform subbands[J].Applied Optics, 2004, 43(2):315-323. doi: 10.1364/AO.43.000315 [20] LEI M Y, GENG J P.Fusion of three-frame difference method and background difference method to achieve infrared human target detection[C]//2019 IEEE 1st International Conference on Civil Aviation Safety and Information Technology (ICCASIT).Piscataway: IEEE Press, 2019: 381-384. [21] 付裕, 王志高, 陈文, 等.基于高斯背景模型的红外人体运动目标检测技术[J].自动化与仪器仪表, 2020(1):63-65. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdhyyqyb202001016FU Y, WANG Z G, CHEN W, et al.Infrared human moving target detection technology based on Gaussian background model[J].Automation and Instrumentation, 2020(1):63-65(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdhyyqyb202001016 [22] VIOLA P, JONES M J, SNOW D.Detecting pedestrians using patterns of motion and appearance[C]//IEEE International Conference on Computer Vision.Piscataway: IEEE Press, 2003: 734-741. [23] JAVED O, SHAFIQUE K, SHAH M.A hierarchical approach to robust background subtraction using color and gradient information[C]//Proceedings of Workshop on Motion and Video Computing.New York: ACM, 2002: 22-27. [24] OLMEDA D, PREMEBIDA C, NUNES U, et al.Pedestrian detection in far infrared images[J].Integrated Computer-Aided Engineering, 2013, 20(4):347-360. doi: 10.3233/ICA-130441 [25] ZHANG Y G, ZHENG J, ZHANG C, et al.An effective motion object detection method using optical flow estimation under a moving camera[J].Journal of Visual Communication & Image Representation, 2018, 55:215-228. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=f29969af52c7beb46da2cd3f26c3ce15 [26] LIU X J, XUE F.Moving target detection based on adaptive edge extraction algorithm[C]//2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA).Piscataway: IEEE Press, 2018: 1206-1211. [27] WIRAYUDA T A B, LAKSITOWENING K A, STHEVANIE F, et al.Development methods for hybrid motion detection (frame difference-automatic threshold)[C]//2013 International Conference of Information and Communication Technology (ICoICT).Piscataway: IEEE Press, 2013: 218-222. [28] DAVIS J W, KECK M A.A two-stage template approach to person detection in thermal imagery[C]//IEEE Workshops on Application of Computer Vision.Piscataway: IEEE Press, 2005: 364-369. [29] LARA S L, SUN D Q, JAMPANI V, et al.Optical flow with semantic segmentation and localized layers[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway: IEEE Press, 2016: 3889-3898. [30] WANG Y, JODOIN P M, PORIKLI F, et al.CDnet 2014: An expanded change detection benchmark dataset[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway: IEEE Press, 2014: 393-400. [31] ZHU W J, LIANG S, WEI Y C, et al.Saliency optimization from robust background detection[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway: IEEE Press, 2014: 2814-2821. -
下载:
点击查看大图
计量
- 文章访问数: 551
- HTML全文浏览量: 56
- PDF下载量: 79
- 被引次数: 0
