Detection of Real Time Objects Using TensorFlow and OpenCV
Ajay K. Talele, Aseem Patil, Bhushan Barse · Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146 · 2019
Detecting and recognizing objects in unstructured aswell as structured environments is one of the most challengingtasks in computer vision and artificial intelligence research.This paper introduces a new computer vision-based obstacledetection method for mobile technology and its applications.Each individual image pixel is classified as belonging either toan obstacle based on its appearance. The method uses a singlelens webcam camera that performs in real-time, and alsoprovides a binary obstacle image at high resolution. In theadaptive mode, the system keeps learning the appearance ofthe obstacle during operation. The system has been testedsuccessfully in a variety of environments, indoors as well asoutdoors, making it suitable for all kinds of hurdles. It alsotells us the type of obstacle which has been detected by thesystem.