熊 锐,程 亮,胡 涛,吴佳蓉,王洪金,闫雪梅,何赟泽.水面无人艇可行域及障碍物快速分割算法研究[J].电子测量与仪器学报,2023,37(2):11-20 |
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 regionand obstacles of unmanned surface vessels |
|
DOI: |
中文关键词: 水面无人艇 DeeplabV3-CSPNet 快速分割算法 深度学习 注意力机制 |
英文关键词:unmanned surface vessels deeplabV3-CSPNet fast segmentation algorithm deep learning attention mechanism |
基金项目:湖南省自然科学基金杰出青年基金(2022JJ10017)、珠海云洲智能科技有限公司委托课题(H202091400311)项目资助 |
|
|
摘要点击次数: 633 |
全文下载次数: 817 |
中文摘要: |
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 5 620 张图像和 25 875 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。 |
英文摘要: |
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 5 620
images and 25 875 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. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|