Computer Engineering and Applications ›› 2016, Vol. 52 ›› Issue (3): 184-188.

Previous Articles     Next Articles

Life jacket detection algorithm based on HSV color feature and contour area

YANG Xuesong, CAI Biye, ZHANG Jianming, LI Feng   

  1. School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China
  • Online:2016-02-01 Published:2016-02-03

基于HSV颜色特征和轮廓面积的救生衣检测算法

杨雪松,蔡碧野,张建明,李  峰   

  1. 长沙理工大学 计算机与通信工程学院,长沙 410114

Abstract: In light of few works about automatic life jacket detection at home and abroad, a novel life jacket detection algorithm is proposed to discriminate the life jacket in complex ferry environment. This paper counts the HSV range of life jacket image and identifies the likely region of life jackets from the pending image using prior color range; it calculates every contour’s area to exclude the disturb by small area region after getting the contours of all likely regions in the image by border following algorithm. Finally it gets the life jacket area. Experiments show that this method can recognize the life jacket well in complex ferry environment.

Key words: life jacket detection, HSV color space, border following, contour area

摘要: 目前国内外对渡口救生衣检测技术的研究还比较少,因此提出了复杂渡口环境下的一种能够识别救生衣的检测算法。统计救生衣的HSV颜色范围,用先验HSV颜色范围识别出待检测图像中的救生衣可能区域;通过边界跟踪得到图像中所有可能区域的轮廓,计算各个轮廓的面积来排除小面积区域的干扰;最终得到救生衣区域。实验表明,该方法能够比较准确地识别复杂环境下的渡口救生衣。

关键词: 救生衣检测, HSV颜色空间, 边界跟踪, 轮廓面积