Abstract:

Artificial Intelligence becomes a crucial field when robots can perform tasks that require a human skills. It incorporates Machine Learning, which enables robots to acquire skills without the intervention of humans. Deep Learning is a subset of Machine Learning in which vast amounts of data are used to teach artificial neural networks and algorithms modelled after the human brain.One of the most challenging and intriguing issues in the field of computer vision is object detection, a crucial application of AI. The prediction of a target item's class within an input image is known as image classification. The process of determining where a large number of items are located within an input picture is referred to as object localization. Combining these two processes, object detection makes it possible to locate numerous objects within an image. The two types of object detection techniques are classification methods and regional proposal methods. An approach to real-time object identification known as YOLO (You Look Only Once) recognizes predetermined items in videos, live feeds, and photos. YOLO uses deep learning techniques like OpenCV and Keras to implement features learned by a deep convolutional neural network for object identification. The alternative version of YOLO, YOLOV3, is much better at identifying objects than YOLO.

Description:

Artificial Intelligence, Machine Learning, Deep Learning, Object detection, Image classification, YOLOV3