激光雷达距离像的实时边缘检测

Real-time edge detection of Lidar range image

针对激光雷达距离像边缘检测精度低、抗噪性能差和需要人为设定阈值的问题,提出一种改进Sobel算子的边缘检测算法,算法通过增加梯度检测方向提高算法的边缘定位精度,采用中值滤波计算局部距离像边缘阈值,在实现自适应阈值的Sobel边缘检测的同时增强算法的抗噪性能,同时采用FPGA硬件加速,实现算法实时性边缘检测。此外,设计激光雷达距离像采集系统,通过实验验证该算法能够满足高精度实时边缘检测的要求,较好提取距离像的完整边缘信息,具有一定的工程应用价值。

Aiming at the problems of low-resolution lidar range image edge detection accuracy, poor anti-noise performance, and the need to set the threshold manually. An edge detection algorithm with improved Sobel operator is proposed. The improved algorithm increases the accuracy of range image edge location by adding a gradient template and uses a median filter to calculate the local edge threshold. Therefore, it can realize adaptive threshold calculation and enhance the anti-noise performance. Then FPGA hardware acceleration is used to achieve real-time edge detection of the algorithm. In addition, the lidar range image acquisition system is designed and the algorithm is verified through experiments to meet the requirements of real-time edge detection.It is better to extract the complete edge information of the range image, which has certain engineering application value.