室内视频监控下基于混合算法的人体异常行为检测和识别方法
|
摘要
针对目前室内人体异常行为检测和识别中照明变化、遮挡、相机移动和背景等因素对检测准确性的影响,提出一种多技术混合跟踪方法。该方法基于连续自适应均值漂移(CAMS),引入校正背景权重直方图(CBWH)和无味粒子滤波(UPF)技术处理遮挡和相似颜色对象的干扰。采用基于稀疏表达的检测方式从多种场景对目标对象的异常行为进行检测和识别,并利用均方误差统计量评估所提方法的性能。同时在公开数据集UMN上进行仿真验证。实验结果表明,该方法在不同场景中有障碍物遮挡或是具有相似颜色的其他对象情况下都能准确检测和识别目标对象。此外,该技术还可能进一步改善复杂场景下多摄像机中目标对象的跟踪性能。
Aiming at the influence of illumination variations, occlusions, camera movements, and background clutters on monitoring accuracy in the detection and recognition of human abnormal behavior, a hybrid multi-technique tracking method was proposed. Based on continuous adaptive mean shift(CAMS), we introduced corrected background weight histogram(CBWH) and unscented particle filter(UPF) to deal with the interference of shading and similar color objects. The sparse expression detection method was utilized to identify the abnormal behavior of the target object in various scenarios. The performance of the proposed method was evaluated by using the mean square error(MSE), and the simulation was carried out on the open data set UMN. The experimental results show that the method can accurately detect and recognize the target object under the condition of obstacle occlusion or similar color object in different scenes. In addition, this technique may further improve the tracking performance of target objects in multiple cameras and complex scenes.
Aiming at the influence of illumination variations, occlusions, camera movements, and background clutters on monitoring accuracy in the detection and recognition of human abnormal behavior, a hybrid multi-technique tracking method was proposed. Based on continuous adaptive mean shift(CAMS), we introduced corrected background weight histogram(CBWH) and unscented particle filter(UPF) to deal with the interference of shading and similar color objects. The sparse expression detection method was utilized to identify the abnormal behavior of the target object in various scenarios. The performance of the proposed method was evaluated by using the mean square error(MSE), and the simulation was carried out on the open data set UMN. The experimental results show that the method can accurately detect and recognize the target object under the condition of obstacle occlusion or similar color object in different scenes. In addition, this technique may further improve the tracking performance of target objects in multiple cameras and complex scenes.
引文
[1] 邵振峰,蔡家骏,王中元,等.面向智能监控摄像头的监控视频大数据分析处理[J].电子与信息学报,2017,39(5):1116-1122.
[2] 邓磊,陈宝华,赖伟良,等.三维监控系统中基于三维重构的交互式标定[J].电子学报,2017,45(3):527-533.
[3] 潘志安,朱三元.移动摄像视频的多运动目标实时跟踪算法[J].控制工程,2017,24(4):836-843.
[4] 沈铮,吴薇.基于图像处理的公交车内人群异常情况检测[J].计算机工程与设计,2018,39(1):165-171.
[5] 罗建华.基于改进提升模型的视频目标跟踪算法[J].计算机应用与软件,2018,35(1):261-263.
[6] 侯晴宇,卞春江,逯力红,等.红外图像中快速小目标的均值移位跟踪[J].哈尔滨工业大学学报,2013,45(4):79-83.
[7] Sabokrou M,Fayyaz M,Fathy M,et al.Deep-Cascade:Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes[J].IEEE Transactions on Image Processing,2017,26(4):1992-2004.
[8] Chaker R,Aghbari Z A,Junejo I N.Social Network Model for Crowd Anomaly Detection and Localization[J].Pattern Recognition,2017,61:266-281.
[9] Xiu C,Ba F.Target tracking based on the improved Camshift method[C]// 2016 Chinese Control and Decision Conference(CCDC).IEEE,2016.
[10] 陈文会,张晶,樊养余,等.一种基于背景减法和帧差的运动目标检测算法[J].电子设计工程,2013,21(3):24-26.
[11] Hsia C H,Liou Y J,Chiang J S.Directional Prediction CamShift algorithm based on Adaptive Search Pattern for moving object tracking[J].Journal of Real-Time Image Processing,2016,12(1):183-195.
[12] Feng X,Jiang J,Lin P,et al.Radar target detection method based on particle filter theory under correlated non-Gaussian clutter backgrounds[C]// IET International Radar Conference 2015.IET,2016.
[13] 张赛钰,朱小玲,汪衍广,等.基于帧差法与Mean-shift算法相结合的运动熔滴识别与跟踪方法[J].上海交通大学学报,2016,50(10):1605-1608.
[14] 王宇霞,赵清杰,蔡艺明,等.基于自重构粒子滤波算法的目标跟踪[J].计算机学报,2016,39(7):1294-1306.
[15] 杨超,蔡晓东,王丽娟,等.一种改进的CAMShift跟踪算法及人脸检测框架[J].计算机工程与科学,2016,38(9):1863-1869.
[16] Ning J,Zhang L,Zhang D,et al.Robust mean-shift tracking with corrected background-weighted histogram[J].Iet Computer Vision,2012,6(1):62-69.
[17] 基于三维直方图修正和灰度熵分解的图像分割[J].计算机工程,2014,40(5):234-237.
[18] 崔汪莉,卫军胡,纪鹏,等.基于加权局部梯度直方图的头部三维姿态估计[J].西安交通大学学报,2015,49(11):71-76.
[19] Yang Y,Jia Y X,Rong C Z,et al.Object Tracking Based on Corrected Background-Weighted Histogram Mean Shift and Kalman Filter[J].Advanced Materials Research,2013,765-767:720-725.
[20] Zhao F,Ge S S,Jie Z,et al.Celestial navigation in deep space exploration using spherical simplex unscented particle filter[J].Iet Signal Processing,2018,12(4):463-470.
[2] 邓磊,陈宝华,赖伟良,等.三维监控系统中基于三维重构的交互式标定[J].电子学报,2017,45(3):527-533.
[3] 潘志安,朱三元.移动摄像视频的多运动目标实时跟踪算法[J].控制工程,2017,24(4):836-843.
[4] 沈铮,吴薇.基于图像处理的公交车内人群异常情况检测[J].计算机工程与设计,2018,39(1):165-171.
[5] 罗建华.基于改进提升模型的视频目标跟踪算法[J].计算机应用与软件,2018,35(1):261-263.
[6] 侯晴宇,卞春江,逯力红,等.红外图像中快速小目标的均值移位跟踪[J].哈尔滨工业大学学报,2013,45(4):79-83.
[7] Sabokrou M,Fayyaz M,Fathy M,et al.Deep-Cascade:Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes[J].IEEE Transactions on Image Processing,2017,26(4):1992-2004.
[8] Chaker R,Aghbari Z A,Junejo I N.Social Network Model for Crowd Anomaly Detection and Localization[J].Pattern Recognition,2017,61:266-281.
[9] Xiu C,Ba F.Target tracking based on the improved Camshift method[C]// 2016 Chinese Control and Decision Conference(CCDC).IEEE,2016.
[10] 陈文会,张晶,樊养余,等.一种基于背景减法和帧差的运动目标检测算法[J].电子设计工程,2013,21(3):24-26.
[11] Hsia C H,Liou Y J,Chiang J S.Directional Prediction CamShift algorithm based on Adaptive Search Pattern for moving object tracking[J].Journal of Real-Time Image Processing,2016,12(1):183-195.
[12] Feng X,Jiang J,Lin P,et al.Radar target detection method based on particle filter theory under correlated non-Gaussian clutter backgrounds[C]// IET International Radar Conference 2015.IET,2016.
[13] 张赛钰,朱小玲,汪衍广,等.基于帧差法与Mean-shift算法相结合的运动熔滴识别与跟踪方法[J].上海交通大学学报,2016,50(10):1605-1608.
[14] 王宇霞,赵清杰,蔡艺明,等.基于自重构粒子滤波算法的目标跟踪[J].计算机学报,2016,39(7):1294-1306.
[15] 杨超,蔡晓东,王丽娟,等.一种改进的CAMShift跟踪算法及人脸检测框架[J].计算机工程与科学,2016,38(9):1863-1869.
[16] Ning J,Zhang L,Zhang D,et al.Robust mean-shift tracking with corrected background-weighted histogram[J].Iet Computer Vision,2012,6(1):62-69.
[17] 基于三维直方图修正和灰度熵分解的图像分割[J].计算机工程,2014,40(5):234-237.
[18] 崔汪莉,卫军胡,纪鹏,等.基于加权局部梯度直方图的头部三维姿态估计[J].西安交通大学学报,2015,49(11):71-76.
[19] Yang Y,Jia Y X,Rong C Z,et al.Object Tracking Based on Corrected Background-Weighted Histogram Mean Shift and Kalman Filter[J].Advanced Materials Research,2013,765-767:720-725.
[20] Zhao F,Ge S S,Jie Z,et al.Celestial navigation in deep space exploration using spherical simplex unscented particle filter[J].Iet Signal Processing,2018,12(4):463-470.