[1]付长斐,叶宾,李会军.基于HSV颜色空间的运动目标识别[J].控制与信息技术,2020,(01):1.[doi:10.13889/j.issn.2096-5427.2020.01.001]
 FU Changfei,YE Bin,LI Huijun.Moving Target Recognition Based on HSV Color Space[J].High Power Converter Technology,2020,(01):1.[doi:10.13889/j.issn.2096-5427.2020.01.001]
点击复制

基于HSV颜色空间的运动目标识别()
分享到:

《控制与信息技术》[ISSN:2095-3631/CN:43-1486/U]

卷:
期数:
2020年01期
页码:
1
栏目:
出版日期:
2020-02-05

文章信息/Info

Title:
Moving Target Recognition Based on HSV Color Space
作者:
付长斐1叶宾12李会军12
(1.中国矿业大学信息与控制工程学院,江苏 徐州,221116)
Author(s):
FU Changfei 1 YE Bin 12 LI Huijun 12
( 1. School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China;
2. Xuzhou Key Laboratory of Artificial Intelligence and Big Data, Xuzhou, Jiangsu 221116, China )
关键词:
运动目标跟踪感兴趣区域图像分类特征检测HSV颜色空间
Keywords:
moving targets tracking region of interest image classification feature extracting HSV color space
分类号:
TP399
DOI:
10.13889/j.issn.2096-5427.2020.01.001
文献标志码:
A
摘要:
图像感兴趣区域(Region of Interest, ROI)提取在运动目标的检测与跟踪等领域有着广泛的应用。HSV(Hue Saturation Value)是根据颜色的直观特性创建的一种颜色空间,用于对颜色进行定量描述。本文将HSV颜色空间用于图像中颜色信息的计算,识别颜色特征。针对RoboMaster全国机器人大赛中,实时捕捉敌方和己方移动机器人装甲这一基本问题,提出一种基于色彩特征的目标识别方法。首先对图像进行阈值分割,计算二值图像轮廓的形状描述参数,以寻找图像中所有的高亮类矩形,再用HSV颜色空间进行伪ROI颜色判定。在此过程中,进行了目标灯柱彩色像素的分析,结合HSV各种颜色对应像素值范围和图像样本像素范围,确定了算法所采用的像素值范围。最终识别目标的判定准则是灯柱区域中,处于分析所得范围内的像素占整个区域的比例。经测试,该方法对于640×480的一组图片,平均处理速度可达到102.33帧/秒,平均识别率为97.4%。在RoboMaster全国大学生机器人大赛中的应用实践验证了该目标识别算法的有效性。
Abstract:
Extracting of ROI (region of interest) has been widely used in the fields of detecting and tracking moving objects. HSV (hue saturation value) is a color space created according to the visual properties of colors, which can be used to describe colors quantitively. Based on HSV, we calculate the color information and recognize the color features in images. For the basic task of recognizing and capturing the armors mounted on the opponent robots in real-time in the RoboMaster National University Robot Competition, a detecting algorithm based on the color features is proposed. Firstly, we apply threshold segmentation to the source image, and calculate the shape parameters of the contours to find out all bright light bar in this image. Then HSV color space is used to judge the color of preliminary ROI to confirm whether it is our target or not. Before this procedure, we need analyze the pixels of the right colorful light bar to confirm a pixel range of HSV and RGB parameters. This range is also determined according to a sheet about corresponding pixel parameters of typical colors in HSV and RGB color space. The criterion to judge the right object is the percentage of the pixels whose HSV and RGB parameters are in the range we confirmed before. Experiments show that the average processing speed of the proposed method can reach 102.33 frame per second and the recognition accuracy is about 97.4%. This algorithm has been successfully applied in the RoboMaster Robot Competition and the results showed that robot can effectively track a moving robot in real-time.

参考文献/References:

[1] 高文,朱明,贺柏根,等.目标跟踪技术综述[J].中国光学,2014,7(03):365-375.

[2] 雷琳,李智勇,粟毅.基于ROI特征匹配融合的图像多目标跟踪算法[J].中国图象图形学报,2008(03):580-585.

[3] 张鹏,王润生. 静态图像中的感兴趣区域检测技术[J]. 中国图象图形学报,2005(03):142-148.

[4] 李琦,崔建江,薛定宇,等.一种手背静脉感兴趣区域提取算法[J].系统仿真学报,2019-04-13:1-7.

[5] 陈高攀,徐美华,王琪,等. 一种基于单目视觉的前方车辆检测算法[J].上海大学学报(自然科学版),2019,25(01):56-65.

[6] J. Park and K. Hong, "A study on the stress-index estimation using face image," 2016 International Conference on Information and Communication Technology Convergence (ICTC), Jeju, 2016, pp. 45-47.

[7] 古新展,陈文天,战跃福. 模糊C均值聚类算法在肺部CT图像感兴趣区域特征提取中的临床应用研究[J].中国医学装备,2019,16(02):20-23.

[8] Y. Xiao and J. Li, "Crack Detection Algorithm based on the Fusion of Percolation Theory and Adaptive Canny Operator," 2018 37 th Chinese Control Conference (CCC), Wuhan, 2018, pp. 4295-4299.

[9] 张青,邹湘军,林桂潮,等.草莓重量和形状图像特征提取与在线分级方法[J].系统仿真学报,2019,31(01):7-15.

[10] 冯运发,王新彦,佘银海,等.基于HALCON软件与HSV模型的树木检测算法研究[J].江苏农业科学,2019,47(6):188-192.

[11] Y. Xia, L. Cheng, W. Li and S. Ning, "A Region of Interest Extraction Approach Based on Adaptive Threshold in Intelligent Transportation System," 2009 Asia-Pacific Conference on Information Processing, Shenzhen, 2009, pp. 120-123.

[12] 郝蓓,杨大利,侯凌燕,等.一种基于快速图像增强的生产线倒瓶检测方法[J].北京信息科技大学学报(自然科学版), 2017,32(05):39-44.

[13] 崔昌华,朱敏琛.基于肤色HSV颜色模型下的人脸实时检测与跟踪[J].福州大学学报(自然科学版),2006(06):826-830.

[14] 马玲,张晓辉.HSV颜色空间的饱和度与明度关系模型[J].计算机辅助设计与图形学学报,2014,26(08):1272-1278.

[15] 兰红,胡涵.结合HSV空间的改进二维Otsu免疫组化图像分割[J].计算机应用与软件,2016,33(05):200-203.

[16] 袁奋杰,周晓,丁军,等.基于FPGA的RGB和HSV色空间转换算法实现[J].电子器件,2010,33(04):493-497.

[17] 耿庆田,于繁华,赵宏伟,等.基于颜色特征的火焰检测新算法[J].吉林大学学报(工学版),2014,44(06):1787-1792.

[18] Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing[M].Third Edition. Prentice Hall, NewYork, 2007.

相似文献/References:

[1]付长斐,叶 宾,李会军.基于 HSV 颜色空间的运动目标识别[J].控制与信息技术,2020,(02):70.[doi:10.13889/j.issn.2096-5427.2020.01.600]
 FU Changfei,YE Bin,LI Huijun.Moving Target Recognition Based on HSV Color Space[J].High Power Converter Technology,2020,(01):70.[doi:10.13889/j.issn.2096-5427.2020.01.600]

备注/Memo

备注/Memo:
作者简介:付长斐(1997—), 男,本科生,主要研究方向为机器视觉。
基金项目:徐州市应用基础研究计划项目(KC18069)。
更新日期/Last Update: 2020-01-21