Development of computer vision based obstacle detection and human tracking on smart wheelchair for disabled patient

Author(s):  
Fitri Utaminingrum ◽  
M Ali Fauzi ◽  
Randy Cahya Wihandika ◽  
Sigit Adinugroho ◽  
Tri Astoto Kurniawan ◽  
...  
2021 ◽  
Vol 336 ◽  
pp. 07004
Author(s):  
Ruoyu Fang ◽  
Cheng Cai

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.


Author(s):  
Fitri Utaminingrum ◽  
Tri Astoto Kumiawan ◽  
M. Ali Fauzi ◽  
Randy Cahya Wihandika ◽  
Putra Pandu Adikara

Elderly and people with disabilities often rely on others for their locomotion. With this emerging world of automation and technologically advanced society we live in a smart wheelchair with appropriate automation can be a life changing innovation for them. One might wonder what is the need for a wheelchair to be smart or for that matter why anything needs to be smart. The answer is simple, to overcome the limitations of the existing technology. We aim on integrating a simple Manually operated wheelchair with features like Obstacle Detection with appropriate technologies such as voice control or gesture control for people who are not able to locomote like a normal person can. With this project, not only do we help a person using a normal wheelchair more easily but also make life easier for those who have other disabilities which are standing as an obstacle making it difficult for them to walk. For instance, a blind person can use a smart wheelchair that allows voicecontrolled movement or even gesture-controlled movement. Another might be of a person who can’t speak, will now be able to control everything with his bare hands. Wheelchair coupled with the appropriate sensors that automatically detects the obstacles/objects in the proximity and takes appropriate action consequently and In addition to that it may also be controlled by another person taking care of the disabled by giving commands such as forward, backward, upright etc. This not only reduces the user's efforts but also helps people to take care of their elderly. Voice/gesture control system makes everything simple. Just visualize the application of it in a hospital where the nurse has to manually handle the patient's wheelchair for even the slightest of movement. This system on the other hand needs only text or voice input command, and based upon the predefined command received from the user, the system will execute the task. This project even enforces a GSM module which uses the sim card, which can help in tracking the wheelchair when required, like in case where a user is in difficulty and needs emergency help, a message asking for help can be sent to the intended person.


Author(s):  
Shaolin Kataria ◽  
Aditya Sunil Menon ◽  
Prerna Sultania ◽  
Sunjol Singh Paul ◽  
Kakelli Anil Kumar

Several patients face Cerebral Palsy. Such debilitating diseases impede motor control and make it difficult for them to operate traditional electric wheelchairs. Existing models of smart wheelchairs accommodate these issues to a certain extent but fail to deliver a solution for patients to use the wheelchairs completely autonomously. This paper proposes a novel model for a cost-effective smart wheelchair that takes simple gestures as input for movement, along with several quality-of-life and assistive modules such as vitals monitoring and voice memo support for patients suffering from memory loss, along with obstacle detection to ensure complete safety of the patient regardless of the terrain. The paper discusses the various modules present in the wheelchair, elaborates upon the algorithm used for input detection and calculation, and finally, the implementation of each module. Lastly, the paper enlists comparisons between existing smart wheelchair models and the proposed model and lists out its strengths, weaknesses and states its findings from the proposed system's results.


2021 ◽  
Vol 2131 (3) ◽  
pp. 032027
Author(s):  
A Timofeev ◽  
F Daeef

Abstract This article presents a new way to use special computer vision techniques to aim with assisting in controlling a transport robot in a dynamic environment under exceptional and difficult environmental conditions. An analysis and development of algorithm for obstacle detection in the robot’s environment proposed based on data from an RGB-D video camera using computer vision methods. Contour analysis was the base method to detecting objects featured fragment taking into account difficult vision conditions. Based on open-source library (Open CV), we adopted methods program implementation which confirmed its applicability to detect objects in mobile robot environment.


Sign in / Sign up

Export Citation Format

Share Document