Luo Shaofeng, Zou Xiangjun, Z. Yuanqin, Luo Lufeng, Liang Jinhui
{"title":"一种减轻非均匀光照干扰的目标检测方法","authors":"Luo Shaofeng, Zou Xiangjun, Z. Yuanqin, Luo Lufeng, Liang Jinhui","doi":"10.1109/M2VIP.2016.7827277","DOIUrl":null,"url":null,"abstract":"Non-uniform illumination makes it's difficult to detect and extract the target. To locate multiple target under complicate illumination, an improved vision system was designed in this paper. After analyzed kinds of image-binaryzation strategy, we choose the adaptive threshold binarization as the image binarization strategy. Through image processing, morphological processing, adaptive threshold binarization and contour detecting algorithm, a vision system have been designed out on the platform of Virtual Studio 2013. Experiment shows that vision system can locate multiple target efficiently under non-uniform illumination.","PeriodicalId":125468,"journal":{"name":"2016 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A target detection method to mitigate interference of non-uniform illumination\",\"authors\":\"Luo Shaofeng, Zou Xiangjun, Z. Yuanqin, Luo Lufeng, Liang Jinhui\",\"doi\":\"10.1109/M2VIP.2016.7827277\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Non-uniform illumination makes it's difficult to detect and extract the target. To locate multiple target under complicate illumination, an improved vision system was designed in this paper. After analyzed kinds of image-binaryzation strategy, we choose the adaptive threshold binarization as the image binarization strategy. Through image processing, morphological processing, adaptive threshold binarization and contour detecting algorithm, a vision system have been designed out on the platform of Virtual Studio 2013. Experiment shows that vision system can locate multiple target efficiently under non-uniform illumination.\",\"PeriodicalId\":125468,\"journal\":{\"name\":\"2016 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP)\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/M2VIP.2016.7827277\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/M2VIP.2016.7827277","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
光照不均匀给目标的检测和提取带来了困难。针对复杂光照条件下的多目标定位问题,设计了一种改进的视觉系统。在分析了各种图像二值化策略后,我们选择自适应阈值二值化作为图像二值化策略。通过图像处理、形态学处理、自适应阈值二值化和轮廓检测算法,在Virtual Studio 2013平台上设计了一个视觉系统。实验表明,该视觉系统可以在非均匀光照条件下对多个目标进行有效定位。
A target detection method to mitigate interference of non-uniform illumination
Non-uniform illumination makes it's difficult to detect and extract the target. To locate multiple target under complicate illumination, an improved vision system was designed in this paper. After analyzed kinds of image-binaryzation strategy, we choose the adaptive threshold binarization as the image binarization strategy. Through image processing, morphological processing, adaptive threshold binarization and contour detecting algorithm, a vision system have been designed out on the platform of Virtual Studio 2013. Experiment shows that vision system can locate multiple target efficiently under non-uniform illumination.