Comparative Study on Obstacle Detection and Avoidance System by Using Real-Time Image Processing and Artificial Intelligence in Autonomous Wheelchair Application

Abstract

The research objective of this project conducts a comparative performance study between real time image processing and Artificial Intelligence object recognition in the application of obstacle avoidance system for an autonomous wheelchair. The proposed obstacle detection system is achieved through the application of camera sensor with the implementation of Artificial Intelligence techniques in image processing. A pre-trained Convolutional Neural Network model known as MobileNet SSD, and Deep Neural Network (DNN) module in OpenCV library (for live video streams) are utilized in developing the object recognition algorithm. An Arduino and a pair of DC brushed motors together with Smart Drive 40 motor drivers made up the motion control system that acts correspondingly to the inputs obtained from the obstacle detection system(s). Comparative researches on the performance of both obstacle detection algorithms were carried out experimentally. The considered performance is the success rate in obstacle avoidance and this performance was analyzed based on varying light intensity, motor speed, and wall detection. The results obtained indicate that Artificial Intelligence based obstacle detection algorithm performed better than real time image processing with vary light intensity environment. However, it has a relatively low performance with varying motor speed and wall detection when compared to the Image Processing based obstacle detection system.