基于凹点匹配的黏连车辆图像分割方法
|
摘要
在利用智能交通监控系统对过往车辆进行检测时,车辆之间相互重叠、黏连的图像会给车辆计数和特征提取带来很大困难。本文针对车辆黏连图像提出一种简单快速的凹点匹配分割算法。该算法主要通过计算黏连车辆的凸闭包,得出黏连区域的凹区;再根据点到特定对角线的最小或最大距离,确定原图像的凹点集合;最后选择最优分割线对黏连车辆进行分割。仿真结果证实该算法精度高,并且稳定性好。
For the application of the intelligent traffic monitoring system to detect the passing vehicles,it is known that the overlapping and adhesion of the image will bring great difficulties to the vehicles count and feature extraction.To solve the problem of vehicles adhesion,a simple and fast algorithm for image segmentation was proposed in this paper.This algorithm began with the calculation of the convex closure of the vehicles adhesion and getting the concave area of adhesion area,followed by the determination of a set of concave points of the original image based on the minimum or maximum distance of point to diagonal distance,ended with the choice of the optimal split line to segment adhesion vehicles.Simulation results showed that the algorithm has high accuracy and good stability.
For the application of the intelligent traffic monitoring system to detect the passing vehicles,it is known that the overlapping and adhesion of the image will bring great difficulties to the vehicles count and feature extraction.To solve the problem of vehicles adhesion,a simple and fast algorithm for image segmentation was proposed in this paper.This algorithm began with the calculation of the convex closure of the vehicles adhesion and getting the concave area of adhesion area,followed by the determination of a set of concave points of the original image based on the minimum or maximum distance of point to diagonal distance,ended with the choice of the optimal split line to segment adhesion vehicles.Simulation results showed that the algorithm has high accuracy and good stability.
引文
[1]陆振晔,范影乐,庞全.基于数学形态学的重叠细胞分离方法及比较研究[J].计算机工程与应用,2004,40(6):57-59.
[2]丁伟杰,范影乐,庞全.一种改进的基于分水岭算法的粘连分割研究[J].计算机工程与应用,2007,43(10):70-72.
[3]张芹,侯德文.形态学分水岭算法在粘连图像分割中的应用[J].微型机与应用,2012,31(9):44-46.
[4]黄伟,陶俊才.一种基于k-means聚类和半监督学习的医学图像分割算法[J].南昌大学学报(理科版),2014,38(1):31-35.
[5]韦冬冬,赵豫红.基于凹点匹配的重叠图像分割算法[J].计算机与应用化学,2010,27(1):99-102.
[6]SONG H,ZHANG C,PAN J,et al.Segmentation and Reconstruction of Over-lapped Apple Images Based on Convex Hull[J].Transactions of the Chinese Society of Agricultural Engineering,2013,29(3):163-168.
[7]刘相滨,王麓雅.一种求取物体凹点的算法研究[J].计算机与现代化,2001,76(6):1-4.
[8]JI L.Intelligent Splitting in the Chromosome Domain[J].Pattern Recognition,1989,22(5):519-532.
[9]傅蓉,申洪,李本富.一种快速简易的细胞凹点搜寻算法[J].南方医科大学学报,2007,27(11):1781-1783.
[10]吴忻生,刘洋,戚其丰.基于凹性分析的粘连车辆分割倡[J].计算机应用研究,2012,29(1):344-347.
[11]许志闻,郭晓新.计算机图形学[M].北京:机械工业出版社,2010.
[2]丁伟杰,范影乐,庞全.一种改进的基于分水岭算法的粘连分割研究[J].计算机工程与应用,2007,43(10):70-72.
[3]张芹,侯德文.形态学分水岭算法在粘连图像分割中的应用[J].微型机与应用,2012,31(9):44-46.
[4]黄伟,陶俊才.一种基于k-means聚类和半监督学习的医学图像分割算法[J].南昌大学学报(理科版),2014,38(1):31-35.
[5]韦冬冬,赵豫红.基于凹点匹配的重叠图像分割算法[J].计算机与应用化学,2010,27(1):99-102.
[6]SONG H,ZHANG C,PAN J,et al.Segmentation and Reconstruction of Over-lapped Apple Images Based on Convex Hull[J].Transactions of the Chinese Society of Agricultural Engineering,2013,29(3):163-168.
[7]刘相滨,王麓雅.一种求取物体凹点的算法研究[J].计算机与现代化,2001,76(6):1-4.
[8]JI L.Intelligent Splitting in the Chromosome Domain[J].Pattern Recognition,1989,22(5):519-532.
[9]傅蓉,申洪,李本富.一种快速简易的细胞凹点搜寻算法[J].南方医科大学学报,2007,27(11):1781-1783.
[10]吴忻生,刘洋,戚其丰.基于凹性分析的粘连车辆分割倡[J].计算机应用研究,2012,29(1):344-347.
[11]许志闻,郭晓新.计算机图形学[M].北京:机械工业出版社,2010.