Vision System with Audio Feedback to Assist Visually Impaired to Grasp Objects

Gautam, S.; Sivaraman, K.; Muralidharan, Hariharan; Baskar, A.

doi:10.1016/j.procs.2015.08.041

Cited by 6 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, Gautam et al [35] proposed a vision system with audio feedback to assist visually impaired individuals in grasping objects, addressing usability and complexity challenges associated with existing technologies. The system utilizes a Weighted Matrix Algorithm for object recognition, providing audio guidance to the user for locating and reaching desired objects, exemplified through the recognition of a water bottle.…”

Section: Introductionmentioning

confidence: 99%

Robotic Assistant for Object Recognition Using Convolutional Neural Network

Oluyele,

Adeyanju,

Sobowale

2024

AJERD

View full text Add to dashboard Cite

Visually impaired persons encounter certain challenges, which include access to information, environmental navigation, and obstacle detection. Navigating daily life becomes a big task with challenges relating to the search for misplaced personal items and being aware of objects in their environment to avoid collision. This necessitates the need for automated solutions to facilitate object recognition. While traditional methods like guide dogs, white canes, and Braille have offered valuable solutions, recent technological solutions, including smartphone-based recognition systems and portable cameras, have encountered limitations such as constraints relating to cultural-specific, device-specific, and lack of system autonomy. This study addressed and provided solutions to the limitations offered by recent solutions by introducing a Convolutional Neural Network (CNN) object recognition system integrated into a mobile robot designed to function as a robotic assistant for visually impaired persons. The robotic assistant is capable of moving around in a confined environment. It incorporates a Raspberry Pi with a camera programmed to recognize three objects: mobile phones, mice, and chairs. A Convolutional Neural Network model was trained for object recognition, with 30% of the images used for testing. The training was conducted using the Yolov3 model in Google Colab. Qualitative evaluation of the recognition system yielded a precision of 79%, recall of 96%, and accuracy of 80% for the Robotic Assistant. It also includes a Graphical User Interface where users can easily control the movement and speed of the robotic assistant. The developed robotic assistant significantly enhances autonomy and object recognition, promising substantial benefits in the daily navigation of visually impaired individuals.

show abstract

Section: Introductionmentioning

confidence: 99%