A Method of Dynamic Target Detection and Tracking Based on Road Constraint Condition

doi:10.13474/j.cnki.11-2246.2017.0152

Abstract

Abstract: As an important part of intelligent city, intelligent transportation is an important guarantee for urban road safety. The difficulty is how to quickly detect and track dynamic targets in road monitoring images with the complex and changeable road background. According to the characteristics of road monitoring video, a dynamic target tracking method is proposed based on the combination of road constraints and color feature sets. Firstly, the moving target search region is determined by road constraints, and HSV color feature set is used for feature matching. Then the background image is updated and the dynamic target is detected based on IIR filtering background method. Finally, tracking and motion forecasting of dynamic objects are realized based on the tracking method which combines the road constraints and color features. The experimental results show that the method can detect and track the moving target accurately. It also has good response ability to the small displacement target and realizes the real-time detection and tracking of the road dynamic target.

Key words: road constraint condition, HSV color space, infinite impulse response digital filter

CLC Number:

JIAO Jinlong, LU Xiaoping. A Method of Dynamic Target Detection and Tracking Based on Road Constraint Condition[J]. 测绘通报, 2017, 0(5): 47-50.

References

[1] 谭熊, 余旭初, 刘景正,等. 基于无人机视频的运动目标快速跟踪[J].测绘通报, 2011(9):32-34.
[2] 王文龙, 李清泉. 基于蒙特卡罗算法的车辆跟踪方法[J]. 测绘学报, 2011, 40(2):200-203.
[3] 陈岩, 刘开华. 动态背景下运动目标的检测与跟踪[J]. 通信技术, 2003(12):104-106.
[4] 赵高鹏, 薄煜明, 陈益. 一种基于特征匹配的目标识别跟踪方法[J]. 火炮发射与控制学报, 2009(1):30-34.
[5] 屠礼芬, 仲思东, 彭祺,等. 基于混合差分法的运动目标检测[J]. 科学技术与工程, 2012, 12(2):325-329.
[6] 吴垠, 李良福, 肖樟树,等. 基于尺度不变特征的光流法目标跟踪技术研究[J]. 计算机工程与应用, 2013, 49(15):157-161.
[7] 谭艳, 王宇俊. 一种结合背景差分的改进CamShift目标跟踪方法[J]. 西南师范大学学报(自然科学版), 2016, 41(9):120-125.
[8] 龚鼎, 曹广忠. 一种基于背景差分算法的实时运动检测跟踪系统的设计[J]. 电脑知识与技术(学术交流), 2016, 12(8):207-209.
[9] KIM K,CHALIDABHONGSE T H,HARWOOD D, et al. Real-time Foreground-background Segmentation Using Codebook Model[J]. Real-time Imaging, 2005, 11(3):172-185.
[10] STAUFFER C, GRIMSON W E L. Adaptive Background Mixture Models for Real-time Tracking[C]//cvpr. IEEE Computer Society.[S.l.]:IEEE 1999.
[11] STAUFFER C, GRIMSON W E L. Learning Patterns of Activity Using Real-time Tracking[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2000, 22(8):747-757.
[12] 韩明, 刘教民, 孟军英,等. 一种自适应调整K-ρ的混合高斯背景建模和目标检测算法[J]. 电子与信息学报, 2014, 36(8):2023-2027.
[13] 黄玉, 殷苌茗, 周书仁. 基于YCbCr的自适应混合高斯模型背景建模[J]. 计算机工程与科学, 2015, 37(1):152-156.
[14] 范五东, 周尚波, 辛培宸. HSV颜色空间特征与Kalman滤波融合的目标跟踪[J]. 计算机工程与应用, 2011, 47(13):169-173.
[15] 杨宇腾. 基于背景差分法与虚拟区域融合的视频中车流量统计的方法[D]. 昆明:云南大学, 2015.
[16] 余绍军, 蒋钘, 蒋鑫晖. 一种基于灰度相关性的背景更新算法[J]. 电子世界, 2013(3):58-60.