概率哈夫变换在井下煤仓煤位检测中的应用

Application of probabilistic Hough transform in detecting coal level of coal bin

针对井下煤仓煤位的检测,运用计算机视觉识别技术,提出了一种新颖的哈夫变换检测圆的算法,它通过梯度信息,使用对点(2个点)来确定一个圆,从传统的三维空间采样降为二维空间采样,在很小的参数空间内对图像痕迹进行恢复,从而使它具有精度高、速度快、占用内存少等特点.利用辅助光源将这一新算法应用到井下煤仓煤位的检测中,对高、中、低不同煤位的检测取得了满意的结果.

Using computer vision technique to detect coal level of coal bin,a new Hough transform algorithm was developed for finding-circle.It employs gradient orientation to define potential circles using point-pairs.It samples F^(2)instead of F^(3),and transforms the sampled pairs into very small sets of parameter vectors in Q.The result is high speed,increased accuracy and very low memory resources.Using the algorithm to detect coal level of coal bin,the result is satisfy.