A computer vision and artificial intelligence based cost-effective object sensing robot

摘要

In this research, we intend to present an enhanced object detection system incorporating a few well-known computer vision techniques, machine learning algorithms, as well as smart sensors in a more organized way. In essence, a computer vision based system in cooperation with machine learning approach has been employed to detect objects in parallel with a hardware-based ultrasonic sensor unit. The units can not only operate independently but also can cooperate in terms of detection result and hence, this type of approach can be termed as a cooperative object sensing system. Moreover, another key point is the prototype can determine free path to ensure smooth traversing which makes it effective in case of unforeseen scenario. By the same token, this prototype is also able to detect the type of object which is another compelling evidence of its novelty. With this intention in mind, we conducted a field test and evaluated its performance which justified the features specified above.