融合时域和分水岭信息的车辆检测算法

doi:10.3778/j.issn.1002-8331.2008-0249

摘要/Abstract

摘要：

在实时视频图像车辆目标检测时，为了克服行进中车辆背景噪声和阴影带来的准确率低、漏检率高等问题，提出一种时空融合和内外标记的分水岭车辆检测算法。通过相邻视频三帧差法得到的时域运动变化信息结合Canny算子得到的边缘图像相结合，得到时域掩模图像。利用文中提出的基于二次重构、内外区域标记、梯度修正的分水岭空域算法对运动区域及其周围区域进行分割，解决了一般分水岭算法的过分割现象。将得到的结果进行投影，以提高运动状态下车辆的检测精度。实验结果表明，在车辆背景噪声和阴影的影响下，该算法的检测效果仍然较好，车辆漏检率降低到4.90%，算法的准确性、鲁棒性和适应性较好。

关键词: 智能交通, 车辆检测, Canny边缘检测, 内外区域标记, 分水岭变换, 融合时空

Abstract:

In order to overcome the low accuracy and high omission rate caused by background noise and shadow of moving vehicles in real-time video image vehicle target detection, a watershed vehicle detection algorithm based on space-time fusion and internal and external marking is proposed. The time domain mask image is obtained in combination with time-domain motion change information obtained by the adjacent video three-frame difference method with the edge image obtained by Canny operator. The moving region and its surrounding region are segmented by using the watershed spatial algorithm based on quadratic reconstruction, inner and outer region marking and gradient correction, which solves the over segmentation phenomenon of general watershed algorithm. The results are projected to improve the detection accuracy of the vehicle in motion. Experimental results show that, the proposed algorithm detecting effect is still better, which reduces vehicle missing rate to 4.90%, and the algorithm accuracy, robustness and adaptability are better under the influence of background noise and shadow of the vehicle.

Key words: intelligent transportation, vehicle detection, Canny edge detection, internal and external area marking, watershed transformation, fusion of space and time

马庆禄，唐小垚. 融合时域和分水岭信息的车辆检测算法[J]. 计算机工程与应用, 2021, 57(24): 227-233.

MA Qinglu, TANG Xiaoyao. Vehicle Detection Algorithm Combining Time Domain and Watershed Information[J]. Computer Engineering and Applications, 2021, 57(24): 227-233.

参考文献

[1] CHEN D，JIN G，LU L，et al.Infrared imagevehicle detection based on haar-like feature[C]//2018 IEEE 3rd Advanced Information Technology，Electronic and Automation Control Conference（IAEAC），2018.
[2] SIVARAMAN S，TRIVERDI M M.Looking at vehicles on the road：a survey of vision-based vehicle detection，tracking，and behavior analysis[J].IEEE Transactions on Intelligent Transportation Systems，2013，14（4）：1773-1795.
[3] LIU H，MA J，XU T，et al.Vehicle detection and classification using distributed fiber optic acoustic sensing[J].IEEE Transactions on Vehicular Technology，2020，69（2）：1363-1374.
[4] JIN L，FU M Y，WANG M L，et al.Vehicle detection based on vision and millimeter wave radar[J].Journal of Infrared & Millimeter Waves，2014，33（5）：465-471.
[5] 李丽，柴文婷，梅树立.基于自适应全局阈值融合标记的遥感图像建筑群分割[J].农业机械学报，2013，44（7）：222-228.
LI L，CHAI W T，MEI S L.Segmentation of remote sensing images based on adaptive global threshold and fused markers[J].Transactions of the Chinese Society for Agricultural Machinery，2013，44（7）：222-228.
[6] 马文科，王玲，何浩.一种指纹图像的局部阈值分割算法[J].计算机工程与应用，2009，45（34）：177-179.
MA W K，WANG L，HE H.Local threshold segmentation algorithm for fingerprint image[J].Computer Engineering and Applications，2009，45（34）：177-179.
[7] GANGODKAR D，KUMAR P，MITTAL A.Robust segmentation of moving vehicles under complex outdoor conditions[J].IEEE Transactions on Intelligent Transportation Systems，2012，13（4）：1738-1752.
[8] 娄路，赵玲，耿涛.运动车辆检测与跟踪方法[J].交通运输工程学报，2012，12（4）：107-113.
LOU L，ZHAO L，GENG T.Detecting and tracking method of moving vehicle[J].Journal of Traffic and Transportation Engineering，2012，12（4）：107-113.
[9] ZHANG W，FANG X Z，YANG X.Moving vehicles segmentation based on Bayesian framework for Gaussian motion model[J].Pattern Recognition Letters，2006，27（9）：956-967.
[10] MECH R.Robust 2d shape estimation of moving objects considering spatial and temporal coherency in one map detection rule[C]//Proceedings 2000 International Conference on Image Processing，2000.
[11] RASHMI，KUMAR M，SAXENA R.Algorithm and technique on various edge detection：a survey[J].Signal & Image Processing An International Journal，2013，4（3）：65-75.
[12] 张兆杨，杨高波，刘志.视频对象分割提取的原理和应用[M].北京：科学出版社，2009：52-60.
ZHANG Z Y，YANG G B，LIU Z.The principle and application of video object segmentation[M].Beijing：Science Press，2009：52-60.
[13] 牛武泽，石林锁，金广智.融合时空信息的运动目标检测算法[J].计算机工程，2011，37（18）：171-173.
NIU W Z，SHI L S，JIN G Z.Moving object detection algorithm with fusion of time and spatial information[J].Computer Engineering，2011，37（18）：171-173.
[14] 李建，蓝金辉，李杰.一种新型快速运动目标检测算法[J].中南大学学报（自然科学版），2013，44（3）：978-984.
LI J，LAN J H，LI J.A novel fast moving target detection method[J].Journal of Central South University（Natural Science），2013，44（3）：978-984.
[15] 朱仲杰，蒋刚毅，郁梅.一种基于时空信息的运动目标提取新方法[J].中国图像图形学报，2003，8（4）：422-426.
ZHU Z J，JIANG G Y，YU M.New algorithm for extracting moving object based on spatial-temporal information[J].Journal of Image and Graphics，2003，8（4）：422-426.
[16] 蔡子文，费向东.基于标记的数学形态学滤波分水岭算法[J].计算机技术与发展，2013，22（3）：38-44.
CAI Z W，FEI X D.Mathematical-morphological watershed algorithm based on marking[J].Compute Technology and Development，2013，22（3）：38-44.
[17] RAFAEL C G，RICHARD E W，STEVEN L E.Digital image processing using MATLAB[M].Beijing：Publishing House of Electronics Industry，2005：260-280.
[18] 杨高波，杜青松，MATLAB图像/视频处理应用及实例[M].北京：电子工业出版社，2010：152-178.
YANG G B，DU Q S.MATLAB image/video processing applications and examples[M].Beijing：Publishing House of Electronics Industry，2010：152-178.
[19] 赵琳琳.时空融合视频对象分割技术研究[D].长春：吉林大学，2012：20-25.
ZHAO L L.Research of video object segmentation based on spatial-temporal technology[D].Changchun：Jilin University，2012：20-25.