Detection of Electronic Devices in real images using Deep Learning Techniques

Abstract

Object Detection from real world scenario is a subset of Computer Vision, that uses state-of-the-art algorithms and techniques in deep learning to identify and locate the objects in an image or video. Latest advancements in Deep Learning, especially Convolutional Neural Networks (CNN) and in the field of image processing has further improved the process of object detection. Deep learning algorithms that are developed over the years aim to solve several challenges associated with object detection which includes localizing the object in an image, classifying the object correctly with a high confidence score and realtime detection of objects. The performance of the existing algorithms involves a tradeoff between accuracy and detection speed. Algorithms like Faster Region based Convolutional Neural Networks (R-CNN) and Single Shot Detector (SSD) that achieved high accuracy in classifying objects were slow in detecting the objects. Such algorithms were not able to keep up with the pace of detection with video input in realtime and thus were not suitable for implementation in critical applications. The drawbacks associated with these algorithms can be eliminated by following a unified one-state approach. The approach is to fully identify and classify the required objects of interest by passing the image only once through the network. This approach thus decreases detection time considerably. You Only Look Once (YOLO) family of algorithms is one such single shot detector that uses CNNs to detect objects. In our work, we have used the YOLOv3 algorithm to develop a model that detects electronic devices. The model was also tested against realtime input from webcam and mean Average Precision (mAP) of YOLOv3 has been computed and compared with another model developed using Faster R-CNN.