Leveraging robust CNN architectures for real-time object recognition from conveyor belt

Abstract

In the innovative era, the problem of recognizing undesirable objects and individuals on conveyor belts is addressed by various architectural or algorithmic approaches. Conveyor belts are those by which things go in a straight line for transportation, and it works as an object-carrying medium. Sometimes some unwanted objects go through the belt mistakenly, which can be very dangerous. Moreover, detection accuracy is much needed to avoid such deadly occurrences. Better accuracy can be achieved by performing detection in real-time. Furthermore, this upgraded system will assist individuals by lowering the danger of any accidents and provide a real-time example of an airport conveyor belt by detecting any unwanted moving objects with the help of a camera sensor and by applying different algorithms and methods of the neural network. Therefore, in this paper, we have implemented a few algorithms that comprise a customized Convolutional Neural Network, YOLOv5, YOLOv7, and Vision Transformer as well as some Transfer learning methods over a few pre-trained models such as VGG16, ResNet50, and MobileNetv2 to produce a better strategy on our customized dataset to boost the accuracy of recognition.