Continuously Adaptive Mean-shift Tracking Algorithm with Suppressed Background Histogram Model
-
摘要: 针对传统连续自适应均值漂移(CAMshift)跟踪算法在建立目标颜色模型阶段容易包含大量背景颜色信息从而使跟踪效果变差的问题，该文提出一种改进算法。利用混合高斯模型背景法(GMM)将原始图像分割成前景和背景的叠加，在原始图像和背景图像上运动物体所在区域分别建立色调分量直方图，利用背景图像的色调分量直方图计算原始图像中对应色调分量的权值，抑制原始图像中与背景颜色相同的色调，扩大前景与背景颜色的差异性。该方法通过对原始颜色模型中属于背景的色调进行抑制，扩大了目标颜色模型的显著性，提高了跟踪的准确性和稳定性，目标定位的最大中心误差小于20%，能够准确跟踪不发生丢失。
-
关键词:
- 目标跟踪 /
- 背景抑制 /
- 直方图 /
- 色调 /
- 连续自适应均值漂移跟踪算法
Abstract: For the deficiency of traditional Continuously Adaptive Mean-shift (CAMshift) tracking algorithm can easily contain a large number of color information which belongs to the background in the process of establishing the target color model, an improved algorithm is proposed. The original image is divided into foreground and background based on the Gaussian Mixture Model(GMM). In the original image and the background image, the histogram of the hue component is established. Hue histograms of the background image are used to calculate the weight of the hue component in the original image. The hues belonging to the background are suppressed and the color differences between foreground and background are expanded. Experiment shows that by suppressing the hue components belonging to the background, the saliency of the target color model is expanded. The accuracy and stability of the target recognition are improved. The ratio of the max deviation to the target is less than 20%, which ensures the target not to be lost. -
黄凯奇, 陈晓棠, 康运锋, 等. 智能视频监控技术综述[J]. 计算机学报, 2015, 38(6): 1093–1118. doi: 10.11897/SP.J.1016.2015.01093HUANG Kaiqi, CHEN Xiaotang, KANG Yunfeng, et al. Intelligent visual surveillance: A review[J]. Chinese Journal of Computers, 2015, 38(6): 1093–1118. doi: 10.11897/SP.J.1016.2015.01093 TIAN Yumin, ZHENG Haihong, CHEN Qichao, et al. Surveillance video synopsis generation method via keeping important relationship among objects[J]. IET Computer Vision, 2016, 10(8): 868–872. doi: 10.1049/iet-cvi.2016.0128 BELYAEV E, VINEL A, SURAK A, et al. Robust vehicle-to-infrastructure video transmission for road surveillance applications[J]. IEEE Transactions on Vehicular Technology, 2015, 64(7): 2991–3003. doi: 10.1109/TVT.2014.2354376 GARCíA-MARTíN á and MARTíNEZ J M. People detection in surveillance: Classification and evaluation[J]. IET Computer Vision, 2015, 9(5): 779–788. doi: 10.1049/iet-cvi.2014.0148 李刚, 何小海, 张生军, 等. 改进的基于GMM的运动目标检测方法[J]. 计算机应用研究, 2011, 28(12): 4738–4741. doi: 10.3969/j.issn.1001-3695.2011.12.090LI Gang, HE Xiaohai, ZHANG Shengjun, et al. Improved moving objects detection method based on GMM[J]. Application Research of Computers, 2011, 28(12): 4738–4741. doi: 10.3969/j.issn.1001-3695.2011.12.090 修春波, 魏世安. 显著性直方图模型的Camshift跟踪方法[J]. 光学精密工程, 2015, 23(6): 1749–1757. doi: 10.3788/OPE.20152306.1749XIU Chunbo and WEI Shian. Camshift tracking with saliency histogram[J]. Optics and Precision Engineering, 2015, 23(6): 1749–1757. doi: 10.3788/OPE.20152306.1749 ZHOU Hailing, KONG Hui, WEI Lei, et al. Efficient road detection and tracking for unmanned aerial vehicle[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(1): 297–309. doi: 10.1109/TITS.2014.2331353 LAN Jinhui, JIANG Yaoliang, FAN Guoliang, et al. Real-time automatic obstacle detection method for traffic surveillance in urban traffic[J]. Journal of Signal Processing Systems, 2016, 82(3): 357–371. doi: 10.1007/s11265-015-1006-4 刘嘉敏, 梁莹, 孙洪兴, 等. 融合检测和跟踪的实时人脸跟踪[J]. 中国图象图形学报, 2015, 20(11): 1473–1481. doi: 10.11834/jig.20151106LIU Jiamin, LIANG Ying, SUN Hongxing, et al. Real-time face tracking based on detecting and tracking[J]. Journal of Image and Graphics, 2015, 20(11): 1473–1481. doi: 10.11834/jig.20151106 HOCINE L, CAO Wei, DING Yong, et al. Adaptive learning rate GMM for moving object detection in outdoor surveillance for sudden illumination changes[J]. Journal of Beijing Institute of Technology, 2016, 25(1): 145–151. doi: 10.15918/j.jbit1004-0579.201625.0121 KIM Y, HAN W, LEE Y H, et al. Object tracking and recognition based on reliability assessment of learning in mobile environments[J]. Wireless Personal Communications, 2017, 94(2): 267–282. doi: 10.1007/s11277-016-3292-y 陈杏源, 郑烈心, 裴海龙. 基于Camshift和SURF的目标跟踪系统[J]. 计算机工程与设计, 2016, 37(4): 903–906. doi: 10.16208/j.issn1000-7024.2016.04.013CHEN Xingyuan, ZHENG Liexin, and PEI Hailong. Object tracking system based on Camshift and SURF[J]. Computer Engineering and Design, 2016, 37(4): 903–906. doi: 10.16208/j.issn1000-7024.2016.04.013 LI Fuliang, ZHANG Ronghui, YOU Feng. Fast pedestrian detection and dynamic tracking for intelligent vehicles within V2V cooperative environment[J]. IET Image Processing, 2017, 11(10): 833–840. doi: 10.1049/iet-ipr.2016.0931 王玲玲, 裴东, 王全州. 一种改进的Camshift视频目标跟踪算法[J]. 激光与红外, 2015, 45(10): 1266–1271. doi: 10.3969/j.issn.1001-5078.2015.10.024WANG Lingling, PEI Dong, and WANG Quanzhou. Video target tracking algorithm based on improved Camshift[J]. Laser &Infrared, 2015, 45(10): 1266–1271. doi: 10.3969/j.issn.1001-5078.2015.10.024 MORSHIDI M and TJAHJADI T. Gravity optimised particle filter for hand tracking[J]. Pattern Recognition, 2014, 47(1): 194–207. doi: 10.1016/j.patcog.2013.06.032 -
下载:
图(10)
计量
- 文章访问数: 2104
- HTML全文浏览量: 721
- PDF下载量: 48
- 被引次数: 0
