红外图像中快速运动目标的检测与跟踪方法
|
摘要
红外热成像图像具有分辨率较低,细节模糊,对于快速运动目标适应性较差的特点。本文提出了一种结合目标检测算法,目标跟踪算法的红外图像中快速运动目标的检测与跟踪方法。该方法根据红外图像特点,使用ViBE算法检测运动目标,检测出图像中显著运动目标后,触发跟踪器,使用fDSST目标跟踪算法对显著运动目标进行跟踪。测试结果表明,该方法对于快速运动的红外图像目标能够高效检测、快速跟踪。检测与跟踪效果相对传统方法具有检测率更高、鲁棒性更好、实时性更强的优势,对于红外图像中目标检测与跟踪具有很强应用价值。
An infrared thermal image exhibits characteristics of low resolution, fuzzy details, and poor adaptability to fast-moving targets. In this paper, a fast-moving target detection and tracking method for an infrared image is proposed, which combines infrared thermal image with machine vision. According to the characteristics of an infrared image, the ViBE algorithm is used to detect moving objects. After detecting the salient moving objects in the image, the tracker is triggered and the fast discriminative scale space tracking algorithm for target tracking is used to track the salient moving objects. The test results demonstrate that this method can detect and track the fast-moving infrared image target efficiently, and its detection and tracking efficiency is higher than in the traditional method. In addition, it is robust and has real-time advantages.Therefore, this method has a strong application value for infrared image target detection and tracking.
An infrared thermal image exhibits characteristics of low resolution, fuzzy details, and poor adaptability to fast-moving targets. In this paper, a fast-moving target detection and tracking method for an infrared image is proposed, which combines infrared thermal image with machine vision. According to the characteristics of an infrared image, the ViBE algorithm is used to detect moving objects. After detecting the salient moving objects in the image, the tracker is triggered and the fast discriminative scale space tracking algorithm for target tracking is used to track the salient moving objects. The test results demonstrate that this method can detect and track the fast-moving infrared image target efficiently, and its detection and tracking efficiency is higher than in the traditional method. In addition, it is robust and has real-time advantages.Therefore, this method has a strong application value for infrared image target detection and tracking.
引文
[1]崔美玉.论红外热像仪的应用领域及技术特点[J].中国安防,2014(12):90-93.CUI Meiyu.Application field and technical characteristics of infrared thermal imager[J].China Security&Protection,2014(12):90-93.
[2]范延军.基于机器视觉的先进辅助驾驶系统关键技术研究[D].南京:东南大学,2016.FAN Yanjun.Research on key technologies of advanced assisted driving system based on machine vision[D].Nanjing:Southeast University,2016.
[3]张科,刘彦.改进的基于背景预测的红外弱小目标检测方法[J].火力与指挥控制,2008,33(11):22-24.ZHANG Ke,LIU Yan.An Improved Small Target Detection Method Based on background prediction in IR images[J].Fire Control and Command control,2008,33(11):22-24.
[4]杨阳,杨静宇.基于显著性分割的红外行人检测[J].南京理工大学学报:自然科学版,2013,37(2):251-256.YANG Yang,YANG Jingyu.Infrared pedestrian detection based on saliency segmentation[J].Journal of Nanjing University of Science and Technology,2013,37(2):251-256.
[5]魏丽,丁萌,曾丽君,等.红外图像中基于似物性与稀疏编码的行人检测[J].红外技术,2016,38(9):752-757.WEI Li,DING Meng,CENG Lijun,et al.Pedestrian detection based on quasi physical properties and sparse coding in infrared images[J].Infrared Technology,2016,38(9):752-757.
[6]Ahmed M N,Yamany S M,Mohamed N,et al.A Modified Fuzzy means Algorithm for Bias Field Estimation and Segmentation of MRI Data[J].IEEE Transactions on Medical Imaging,2002,21(3):193-199.
[7]ZHENG J,ZHANG D H,HUANG K D,et al.An Adaptive Image Segmentation Method Based on the Fuzzy means with Spatial Information[C]//IET Image Processing,2017,12(5):785-792.
[8]Henry L,Neville D,NAN X.Detection of small objects in clutterusing a GA-RBF neural network[J].IEEE Transactions on Aerospace and Electronic Systems,2002,38(1):98-118.
[9]Pinnegar C R,Mansinha L.Time-local spectral analysis for non-stationary time series:the S-transform for noisy signals[J].Fluctuation and noise letters,2003,3(3):357-364.
[10]Pinnegar C R,Eaton D W.Application of the S transform to prestack noise attenuation filtering[J].Journal of Geophysical Research,2003,108(B9):1-10.
[11]WU Bo,Nevatia Ram.Detection and tracking of multiple,partially occluded humans by Bayesian combination of edgelet based part detectors[J].International Journal of Computer Vision,2007,75(2):247-266.
[2]范延军.基于机器视觉的先进辅助驾驶系统关键技术研究[D].南京:东南大学,2016.FAN Yanjun.Research on key technologies of advanced assisted driving system based on machine vision[D].Nanjing:Southeast University,2016.
[3]张科,刘彦.改进的基于背景预测的红外弱小目标检测方法[J].火力与指挥控制,2008,33(11):22-24.ZHANG Ke,LIU Yan.An Improved Small Target Detection Method Based on background prediction in IR images[J].Fire Control and Command control,2008,33(11):22-24.
[4]杨阳,杨静宇.基于显著性分割的红外行人检测[J].南京理工大学学报:自然科学版,2013,37(2):251-256.YANG Yang,YANG Jingyu.Infrared pedestrian detection based on saliency segmentation[J].Journal of Nanjing University of Science and Technology,2013,37(2):251-256.
[5]魏丽,丁萌,曾丽君,等.红外图像中基于似物性与稀疏编码的行人检测[J].红外技术,2016,38(9):752-757.WEI Li,DING Meng,CENG Lijun,et al.Pedestrian detection based on quasi physical properties and sparse coding in infrared images[J].Infrared Technology,2016,38(9):752-757.
[6]Ahmed M N,Yamany S M,Mohamed N,et al.A Modified Fuzzy means Algorithm for Bias Field Estimation and Segmentation of MRI Data[J].IEEE Transactions on Medical Imaging,2002,21(3):193-199.
[7]ZHENG J,ZHANG D H,HUANG K D,et al.An Adaptive Image Segmentation Method Based on the Fuzzy means with Spatial Information[C]//IET Image Processing,2017,12(5):785-792.
[8]Henry L,Neville D,NAN X.Detection of small objects in clutterusing a GA-RBF neural network[J].IEEE Transactions on Aerospace and Electronic Systems,2002,38(1):98-118.
[9]Pinnegar C R,Mansinha L.Time-local spectral analysis for non-stationary time series:the S-transform for noisy signals[J].Fluctuation and noise letters,2003,3(3):357-364.
[10]Pinnegar C R,Eaton D W.Application of the S transform to prestack noise attenuation filtering[J].Journal of Geophysical Research,2003,108(B9):1-10.
[11]WU Bo,Nevatia Ram.Detection and tracking of multiple,partially occluded humans by Bayesian combination of edgelet based part detectors[J].International Journal of Computer Vision,2007,75(2):247-266.