Pedestrian Lane Detection for Assistive Navigation of Vision-Impaired People: Survey and Experimental Evaluation

Lei, Yunjia; Phung, Son Lam; Bouzerdoum, A.; Le, Hoang Thanh; Luu, Khoa

doi:10.1109/access.2022.3208128

Cited by 6 publications

(2 citation statements)

References 65 publications

(134 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this research, we will discuss an improvised method for object detection using YOLOv8 and integrating it with OpenCV distance measurement [11]. The approach and performance evaluation results are discussed, aiming to contribute significantly to facilitating the mobility of blind individuals, enhancing their independence and overall quality of life.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Yolov8 with OpenCV for Blind-Friendly Object Detection and Distance Estimation

Erwin Syahrudin,

Ema Utami,

Anggit Dwi Hartanto

2024

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

The development of computer technology and computer vision has had a significant positive impact on the daily lives of blind people, especially in efforts to improve their navigation abilities. This research has the main aim of introducing a superior object detection method, especially in supporting the sustainability and effectiveness of navigation for the blind. The main focus of the research is the use of YOLOv8, the latest version of YOLO, as an object detection method, and distance measurement technology from OpenCV. The main challenge to be addressed involves improving the accuracy and performance of object detection, which is an important key to ensuring safe and effective navigation for blind people. In this context, blind people often face obstacles in their mobility, especially when walking around environments that may be full of obstacles or obstacles. Therefore, better object detection methods become essential to ensure the identification of nearby objects, which may involve obstacles or potential threats, thereby preventing possible accidents or difficulties in daily commuting. Involving YOLOv8 as an object detection method provides the advantage of a high level of accuracy, although with a slight increase in detection duration and GPU power consumption compared to previous versions. The research results show that YOLOv8 provides a low error rate, with an average error percentage of 3.15%, indicating very optimal results. Using a combined performance evaluation approach of YOLOv8 and OpenCV distance measurement metrics, this research not only seeks to improve accuracy but also efficiency in detection time and power consumption. This research makes an important contribution in presenting technological solutions that can help improve mobility and safety for blind people, bringing a real positive impact in facilitating their daily lives.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhanced Yolov8 with OpenCV for Blind-Friendly Object Detection and Distance Estimation

Erwin Syahrudin,

Ema Utami,

Anggit Dwi Hartanto

2024

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

show abstract

“…Most persons with poor vision cannot access assistive devices to correct their vision. The development of affordable, easily available, non-invasive assistive devices will help those in need to lead a fully functional life ( 1 ).…”

Section: Introductionmentioning

confidence: 99%

Discernment on assistive technology for the care and support requirements of older adults and differently-abled individuals

Muthu

Tan²,

Latha³

et al. 2023

Front. Public Health

View full text Add to dashboard Cite

Assistive technology for the differently abled and older adults has made remarkable achievements in providing rehabilitative, adaptive, and assistive devices. It provides huge assistance for people with physical impairments to lead a better self-reliant daily life, in terms of mobility, education, rehabilitation, etc. This technology ranges from simple hand-held devices to complex robotic accessories which promote the individual's independence. This study aimed at identifying the assistance required by differently-abled individuals, and the solutions proposed by different researchers, and reviewed their merits and demerits. It provides a detailed discussion on the state of art assistive technologies, their applications, challenges, types, and their usage for rehabilitation. The study also identifies different unexplored research areas related to assistive technology that can improve the daily life of individuals and advance the field. Despite their high usage, assistive technologies have some limitations which have been briefly described in the study. This review, therefore, can help understand the utilization, and pros and cons of assistive devices in rehabilitation engineering and assistive technologies.

show abstract

MSD-NAS: multi-scale dense neural architecture search for real-time pedestrian lane detection

et al. 2023

View full text Add to dashboard Cite

Accurate detection of pedestrian lanes is a crucial criterion for vision-impaired people to navigate freely and safely. The current deep learning methods have achieved reasonable accuracy at this task. However, they lack practicality for real-time pedestrian lane detection due to non-optimal accuracy, speed, and model size trade-off. Hence, an optimized deep neural network (DNN) for pedestrian lane detection is required. Designing a DNN from scratch is a laborious task that requires significant experience and time. This paper proposes a novel neural architecture search (NAS) algorithm, named MSD-NAS, to automate this laborious task. The proposed method designs an optimized deep network with multi-scale input branches, allowing the derived network to utilize local and global contexts for predictions. The search is also performed in a large and generic space that includes many existing hand-designed network architectures as candidates. To further boost performance, we propose a Short-term Visual Memory mechanism to improve information facilitation within the derived networks. Evaluated on the PLVP3 dataset of 10,000 images, the DNN designed by MSD-NAS achieves state-of-the-art accuracy (0.9781) and mIoU (0.9542), while being 20.16 times faster and 2.56 times smaller than the current best deep learning model.

show abstract

Pedestrian Lane Detection for Assistive Navigation of Vision-Impaired People: Survey and Experimental Evaluation

Cited by 6 publications

References 65 publications

Enhanced Yolov8 with OpenCV for Blind-Friendly Object Detection and Distance Estimation

Enhanced Yolov8 with OpenCV for Blind-Friendly Object Detection and Distance Estimation

Discernment on assistive technology for the care and support requirements of older adults and differently-abled individuals

MSD-NAS: multi-scale dense neural architecture search for real-time pedestrian lane detection

Contact Info

Product

Resources

About