水面无人艇可行域及障碍物快速分割算法研究

Research on fast segmentation algorithm of feasible region and obstacles of unmanned surface vessels

针对水面无人艇(USV)可行域及障碍物分割系统对图像处理过程的快速性和准确性要求,研究了一种根据无人艇机载视觉传感器对水上图像快速分割的算法。首先经过多地实验采集实验图像,经过数据清洗、图像去重和人工筛选构建原始数据库,并采用人在回路数据标注方法构造了无人船可行域及障碍物分割数据集,共5620张图像和25875个标签;其次实践了主流的基于深度学习的语义分割方法,包括FCN、DeeplabV3 Plus、U-Net;最后针对水上图像的特点和快速分割的任务需求,提出了一种基于改进DeeplabV3 Plus的快速分割网络DeeplabV3-CSPNet。网络学习实验、离线航行实验和模型部署结果表明,DeeplabV3-CSPNet算法取得快速且准确的分割效果,平均精度达到84.17%,运算速度达到49.26 fps,在边缘计算平台上运算速度达到45.45 fps。

Aiming at the fast and accurate requirements of the image processing for the feasible domain and obstacle segmentation system of unmanned surface vessels(USV),an algorithm for fast segmentation of images on water according to the on-board vision sensor of unmanned surface vessels(USV)is studied.Firstly,the experimental images were collected through multiple experiments,and the original database was constructed through data cleaning,image de-duplication,and manual screening.The feasible region and obstacle segmentation data set of the unmanned ship were constructed using the Human-in-the-loop annotation method,with a total of 5620 images and 25875 tags.Secondly,it practices the mainstream semantic segmentation methods based on deep learning,including FCN,DeeplabV3 Plus,U-Net.Finally,a fast segmentation network DeeplabV3-CSPNet based on improved DeeplabV3 Plus is proposed according to the characteristics of water images and the requirements of fast segmentation.The results of the network learning experiment,offline navigation experiment,and model deployment results show that the DeeplabV3-CSPNet algorithm achieves a fast and accurate segmentation with an average accuracy of 84.17%and an operation speed of 49.26 fps,which can reach 45.45 fps on the edge computing platform.