嵌入式解决方案用于检测和分类头部水平物体使用立体视觉视觉障碍者与音频反的视觉障碍者
Muñoz Kevin1, Chavarria Mario2, Luisa Ortiz3
1School of Electrical and Electronic Engineering, Universidad del Valle, Cali, Colombia.
Scientific reports
|May 19, 2025
概括
这项研究介绍了一种人工智能驱动的立体视觉系统,以帮助盲人检测和分类头部水平物体. 该系统为增强导航和安全提供关键的音频反.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 辅助技术 辅助技术 辅助技术
背景情况:
- 视力障碍者面临着难以导航环境的挑战,因为他们难以检测头部层面的障碍物.
- 现有的辅助技术可能缺乏全面的实时物体检测和空间感知能力.
研究的目的:
- 开发和评估嵌入式立体视觉系统,用于检测和分类头部水平物体,以帮助盲人.
- 为了提供实时的音频反,探测到的物体的范围和方向.
主要方法:
- 开发一个定制的数据集,其中包含五类与视力受损用户相关的头层对象.
- 实现深度神经网络 (YoloV5) 用于对象检测和分类.
- 整合立体视觉来计算对象的距离和方向,加上音频反.
主要成果:
- 在自定义数据集上实现了0.89的平均平均精度 (mAP@0.95),用于头级对象分类.
- 在范围 (0.028 m ± 0.004 m) 和方向 (2.05° ± 0.09°) 估计方面表现出高精度.
- 实地测试在各种条件下为物体分类提供了98.21%的精度和93.75%的回忆.
- 用户测试报告了91%的头部识别准确度和88.75%的障碍回避效率.
结论:
- 嵌入式立体视觉系统有效地检测和分类头部水平对象的视力受损用户.
- 该系统提供准确的空间信息 (距离和方向),并提高了航行安全.
- 用户反表明,提高盲人的独立性和安全性有很大的潜力.
相关概念视频
01:15Depth Perception and Spatial Vision
503
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
503
01:24Vision
52.9K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
52.9K