[1]鄂宁,王静,周翔龙,等.基于SOLOv2-RS的人工假体视觉避障研究[J].中国医学物理学杂志,2024,41(3):309-315.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.007]
　E Ning,WANG Jing,ZHOU Xianglong,et al.Obstacle avoidance in simulated prosthetic vision based on SOLOv2-RS[J].Chinese Journal of Medical Physics,2024,41(3):309-315.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.007]
点击复制

基于SOLOv2-RS的人工假体视觉避障研究()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
41卷
期数:
2024年第3期
页码:
309-315
栏目:
医学影像物理
出版日期:
2024-03-27

文章信息/Info

Title:
Obstacle avoidance in simulated prosthetic vision based on SOLOv2-RS
文章编号:
1005-202X（2024）03-0309-07
作者:
鄂宁1; 王静1; 2; 周翔龙1; 赵容锋1; 何海洋3
1.上海海洋大学信息学院， 上海 201306； 2.农业农村部渔业信息重点实验室， 上海 201306； 3.上海商汤智能科技有限公司， 上海 200231
Author(s):
E Ning1;  WANG Jing1;  2;  ZHOU Xianglong1;  ZHAO Rongfeng1;  HE Haiyang3
1. College of Information Technology, Shanghai Ocean University, Shanghai 201306, China 2. Key Laboratory of Fisheries Information, Ministry of Agriculture and Rural Affairs, Shanghai 201306, China 3. Shanghai SenseTime Intelligent Technology Co., Ltd., Shanghai 200231, China
关键词:
视觉假体; 避障; SOLOv2-RS; ResNeSt; 分级优化处理
Keywords:
Keywords: visual prosthesis obstacle avoidance SOLOv2-RS ResNeSt hierarchical optimization processing
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2024.03.007
文献标志码:
A
摘要:
面向人工假体视觉条件下的避障问题，提出改进的实例分割模型SOLOv2-RS，为植入者在低分辨率人工视觉中更准确地感知导航任务的相关实例对象提供基础。根据视觉注意力机制，采取视野中心距离和目标尺度作为各实例重要性计算准则，以得到的重要性分数作为对需规避障碍物进行分级表达的依据；同时，采用边缘信息提示盲道，并对其进行形态学膨胀处理以避免光幻视有限导致的边缘信息缺失。人工假体视觉仿真结果表明本研究提出的人工假体视觉分级优化处理策略能有效实现盲道和障碍物的优化表达，为植入者更高效地完成室外避障任务提供便利，为人工假体视觉设备图像处理研究提供良好思路。
Abstract:
Abstract: Aiming at the obstacle avoidance in simulated prosthetic vision, an improved instance segmentation model SOLOv2-RS is proposed for providing a basis for implant recipients to accurately perceive the relevant instance objects of navigation tasks in low-resolution prosthetic vision. According to the visual attention mechanism, the distance from the center of the visual field and the target scale are adopted as the importance calculation criteria for each instance, and the obtained importance score is used as the basis for the hierarchical representation of the obstacles to be avoided. Meanwhile, edge information is used to cue the tactile paving, and it is morphologically inflated for avoiding the edge information loss caused by the limited phosphene. The prosthetic vision simulation results demonstrate that the hierarchical optimization processing strategy for simulated prosthetic vision can effectively achieve the optimal representation of tactile paving and obstacles, thus facilitating the implant recipients to accomplish outdoor obstacle avoidance tasks more efficiently, and providing ideas for the research on the image processing of visual prosthetic devices.

相似文献/References:

[1]庞树茂,黄泽彬,刘兆周,等.医疗机器车避障技术的研究[J].中国医学物理学杂志,2013,30(03):4159.[doi:10.3969/j.issn.1005-202X.2013.03.017]
[2]姜广淼,赵瑛,王铁,等.仿真假体视觉下的运动感知研究[J].中国医学物理学杂志,2022,39(9):1105.[doi:DOI:10.3969/j.issn.1005-202X.2022.09.009]
　JIANG Guangmiao,ZHAO Ying,WANG Tie,et al.Motion perception in simulated prosthetic vision[J].Chinese Journal of Medical Physics,2022,39(3):1105.[doi:DOI:10.3969/j.issn.1005-202X.2022.09.009]

备注/Memo

备注/Memo:
【收稿日期】2023-10-26 【基金项目】国家自然科学基金（61806123） 【作者简介】鄂宁，研究方向：计算机视觉、医学图像处理，E-mail:2152127@st.shou.edu.cn 【通信作者】王静，博士，副教授，研究方向：计算机视觉理论及应用、医学图像处理，E-mail: wangjing@shou.edu.cn
更新日期/Last Update: 2024-03-27