复杂光照下彩色圆形标签检测算法 *

针对复杂光照背景下彩色圆形标签的检测问题 ,提出了一种基于色彩信息和 Hough变换的彩色圆形标签的检测算法。该算法采用对比度拉伸来增强图像 ,然后采用自适应 Hough变换来定位场景中可能的圆形物体,目的是降低复杂背景对检测精度的影响。为了检测到各种光照变化下某一色彩的圆形标签 ,引入颜色不变量 Grayworld Normalization模型来克服光照颜色变化的影响。为了评价该算法的有效性 ,对不同恶劣光照条件下的 93幅图像进行了实验 ,其结果表明 ,该算法能有效精确地检测到指定色彩的圆形标签。

Color circle-marker detection under complex illumination

To the problems of color circle-marker detection under complex illumination conditions, this paper proposed a color circle-marker detection algorithm based on color information and Hough transform. The objective was to detect the color circle-marker under complex environments and different illumination conditions. To do so, firstly applyed an adaptive Hough trans-form to locate the position of the balls in order to reduce the influence of the complex environments. Before that, introduced the contrast stretching algorithm to enhance the image in order to improve the accuracy of the marker detection. Then, to de-tect the certain color circle-marker under different illumination conditions, introduced color invariant model Grayworld Norma-lization to overcome the influence of the color of the illumination. Finally, to evaluate the proposed ball detection in practice, carriedoutexperimentson93imagestakenfromvariousilluminations. Onthebasisofthereportedtheoryandexperimentalre-sults show that the proposed method achieves high color circle-marker detection accuracy.