This paper addresses the daily challenges encountered by visually impaired
individuals, such as limited access to information, navigation difficulties,
and barriers to social interaction. To alleviate these challenges, we introduce
a novel visual question answering dataset. Our dataset offers two significant
advancements over previous datasets: Firstly, it features videos captured using
a 360-degree egocentric wearable camera, enabling observation of the entire
surroundings, departing from the static image-centric nature of prior datasets.
Secondly, unlike datasets centered on singular challenges, ours addresses
multiple real-life obstacles simultaneously through an innovative
visual-question answering framework. We validate our dataset using various
state-of-the-art VideoQA methods and diverse metrics. Results indicate that
while progress has been made, satisfactory performance levels for AI-powered
assistive services remain elusive for visually impaired individuals.
Additionally, our evaluation highlights the distinctive features of the
proposed dataset, featuring ego-motion in videos captured via 360-degree
cameras across varied scenarios.

针对视觉障碍者每天面临的挑战，如信息获取的限制、导航困难和社交互动的障碍，本文引入了一种新颖的视觉问答数据集。我们的数据集相对于以往的数据集具有两个重要的改进：首先，通过使用全景佩戴式摄像头拍摄的视频，观察整个环境，与以前的静态图像为中心的数据集不同；其次，与以往集中在单一挑战上的数据集不同，我们的数据集通过创新的视觉问答框架同时解决了多个现实生活中的障碍。我们使用各种先进的视频问答方法和多样化的度量验证了我们的数据集。结果表明，虽然取得了一些进展，AI 辅助服务对于视觉障碍者来说仍然没有达到满意的性能水平。此外，我们的评估突出了 360 度摄像头拍摄的视频中的自我运动特点和各种情境的独特特征。

使用主观真实感全方位相机的视觉障碍人士视频问答

Video Question Answering for People with Visual Impairments Using an  Egocentric 360-Degree Camera

The utilization of deep learning-based object detection is an effective
approach to assist visually impaired individuals in avoiding obstacles. In this
paper, we implemented seven different YOLO object detection models
\textit{viz}., YOLO-NAS (small, medium, large), YOLOv8, YOLOv7, YOLOv6, and
YOLOv5 and performed comprehensive evaluation with carefully tuned
hyperparameters, to analyze how these models performed on images containing
common daily-life objects presented on roads and sidewalks. After a systematic
investigation, YOLOv8 was found to be the best model, which reached a precision
of $80\%$ and a recall of $68.2\%$ on a well-known Obstacle Dataset which
includes images from VOC dataset, COCO dataset, and TT100K dataset along with
images collected by the researchers in the field. Despite being the latest
model and demonstrating better performance in many other applications, YOLO-NAS
was found to be suboptimal for the obstacle detection task.

深度学习目标检测在帮助视力受损者避开障碍物方面是一种有效的方法，本文通过实现并评估七种不同的 YOLO 目标检测模型（YOLO-NAS，YOLOv8，YOLOv7，YOLOv6 和 YOLOv5）来分析这些模型在道路和人行道上常见物体的图像上的表现，并发现 YOLOv8 是最佳模型，其在包含 VOC、COCO 和 TT100K 数据集的 Obstacle 数据集上表现出 80% 的精确度和 68.2% 的召回率，尽管 YOLO-NAS 是最新的模型，在其他应用中表现更好，但对于障碍物检测任务来说并不理想。

针对视障人士的户外障碍物检测研究

Investigating YOLO Models Towards Outdoor Obstacle Detection For  Visually Impaired People

Numerous applications have been developed to assist visually impaired
individuals that employ a machine learning unit to process visual input.
However, a critical challenge with these applications is the sub-optimal
quality of images captured by the users. Given the complexity of operating a
camera for visually impaired individuals, we advocate for the use of Apple Live
Photos and Android Motion Photos technologies. In this study, we introduce a
straightforward methodology to evaluate and contrast the efficacy of
Live/Motion Photos against traditional image-based approaches. Our findings
reveal that both Live Photos and Motion Photos outperform single-frame images
in common visual assisting tasks, specifically in object classification and
VideoQA. We validate our results through extensive experiments on the ORBIT
dataset, which consists of videos collected by visually impaired individuals.
Furthermore, we conduct a series of ablation studies to delve deeper into the
impact of deblurring and longer temporal crops.

我们介绍了一种评估和对比 Live/Motion 照片与传统基于图像的方法在视觉辅助任务中的有效性的简单方法，并发现 Live 照片和运动照片在常见视觉辅助任务中，特别是物体分类和 VideoQA 中，优于单帧图像。通过在视障个体采集的视频组成的 ORBIT 数据集上进行了大量实验验证了我们的结果。此外，我们进行了一系列的消融研究，以深入研究去模糊和较长时间剪辑的影响。