[1]张岩,赵瑛,曹凤,等.基于显著目标检测的人工视觉物体识别图像处理策略[J].中国医学物理学杂志,2025,42(7):883-891.[doi:DOI:10.3969/j.issn.1005-202X.2025.07.007]
　ZHANG Yan,ZHAO Ying,CAO Feng,et al.Image processing strategy for object recognition in artificial vision based on salient object detection[J].Chinese Journal of Medical Physics,2025,42(7):883-891.[doi:DOI:10.3969/j.issn.1005-202X.2025.07.007]
点击复制

基于显著目标检测的人工视觉物体识别图像处理策略()

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

卷:
42
期数:
2025年第7期
页码:
883-891
栏目:
医学影像物理
出版日期:
2025-07-25

文章信息/Info

Title:
Image processing strategy for object recognition in artificial vision based on salient object detection
文章编号:
1005-202X（2025）07-0883-09
作者:
张岩1; 赵瑛2; 曹凤3; 姜广淼2; 何洋2; 王盛2; 王楠1
1.齐鲁理工学院计算机与信息工程学院，山东 济南 250200；2.内蒙古科技大学数智产业学院，内蒙古 包头 014010；3.齐鲁理工学院智能制造与控制工程学院，山东 济南 250200
Author(s):
ZHANG Yan1;  ZHAO Ying2;  CAO Feng3;  JIANG Guangmiao2;  HE Yang2;  WANG Sheng2;  WANG Nan1
1. School of Computer and Information Engineering, Qilu Institute of Technology, Ji’nan 250200, China; 2. School of Digital andIntelligent Industry, Inner Mongolia University of Science and Technology, Baotou 014010, China; 3. School of IntelligentManufacturing and Control Engineering, Qilu Institute of Technology, Ji’nan 250200, China
关键词:
视觉假体; 仿真假体视觉; 显著目标检测; 物体识别; 图像处理策略
Keywords:
visual prosthesis;  simulated prosthetic vision;  salient object detection;  object recognition;  image processing strategy
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2025.07.007
文献标志码:
A
摘要:
目的：为了优化有限分辨率下假体视觉信息的呈现，提出一种基于显著目标检测算法的图像处理策略，旨在检测和增强场景中的显著目标，去除背景信息。方法：首先，结合CNN与Transformer提出一种显著目标检测模型提取显著目标,在此基础上利用目标放大，轮廓增强与对比度增强等方法对图像信息进行优化,并在5种分辨率（16×16、24×24、32×32、48×48、64×64）下进行心理物理学实验。结果：在仿真假体视觉下该图像处理策略对于提高被试的物体识别能力效果显著。在16×16、24×24、32×32、48×48、64×64分辨率下，本文方法均取得了最高的图像内容识别准确率，分别为34%±6%、56%±9%、72%±9%、89%±4%和96%±2%。结论：使用显著目标检测方法和图像处理策略对显著目标进行提取和增强可以帮助假体植入者有效提高物体识别能力。
Abstract:
Abstract: Objective To propose a image processing strategy based on salient object detection algorithm for optimizing thepresentation of prosthetic visual information at a limited resolution level, aiming to detect and enhance the salient objects inthe scene and remove the background information. Methods A salient object detection model combining CNN andTransformer was used to extract salient objects. On this basis, methods such as object magnification, contour enhancementand contrast enhancement were utilized to optimize the image information. Psychophysical experiments were carried out at 5resolution levels (16×16, 24×24, 32×32, 48×48 and 64×64). Results In the simulated prosthetic vision, this image processingstrategy had a remarkable effect on improving the object recognition ability of the subjects. Regardless of the resolutions of16×16, 24×24, 32×32, 48×48 and 64×64, the proposed strategy achieved the highest recognition accuracies, specifically34%±6%, 56%±9%, 72%±9%, 89%±4% and 96%±2%. Conclusion Using the salient object detection method and imageprocessing strategy to extract and enhance salient objects can help prosthesis implant recipients effectively improve theirobject recognition ability.

相似文献/References:

[1]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(7):1105.[doi:DOI:10.3969/j.issn.1005-202X.2022.09.009]
[2]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.[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(7):309.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.007]
[3]崔晓晨,赵瑛,张岩,等.仿真假体视觉下的空间导航研究[J].中国医学物理学杂志,2026,43(7):879.[doi:DOI:10.3969/j.issn.1005-202X.2026.07.007]
　CUI Xiaochen,ZHAO Ying,ZHANG Yan,et al.Spatial navigation in simulated prosthetic vision[J].Chinese Journal of Medical Physics,2026,43(7):879.[doi:DOI:10.3969/j.issn.1005-202X.2026.07.007]

备注/Memo

备注/Memo:
【收稿日期】2025-02-19【基金项目】国家自然科学基金（81460279）；齐鲁理工学院科研项目基金（QIT24NN047）【作者简介】张岩，硕士，研究方向：计算机视觉，E-mail: zhangyan_5533@163.com【通信作者】曹 凤 ，博 士 ，副 教 授 ，研 究 方 向 ：图 像 处 理 ，E-mail:caofeng5354@163.com
更新日期/Last Update: 2025-07-25