Accelerating Object Detection with YOLOv4 for Real-Time Applications

TL;DR

This paper discusses the use of YOLOv4, a deep learning-based object detection framework, and proposes modifications to improve accuracy in real-time applications like surveillance.

Contribution

The paper introduces specific modifications to the YOLOv4 architecture to enhance detection accuracy, especially for small objects, in real-time scenarios.

Findings

Modified YOLOv4 achieves higher accuracy in detecting small objects.

Proposed architecture maintains real-time processing speeds.

Improvements are validated on standard datasets.

Abstract

Object Detection is related to Computer Vision. Object detection enables detecting instances of objects in images and videos. Due to its increased utilization in surveillance, tracking system used in security and many others applications have propelled researchers to continuously derive more efficient and competitive algorithms. However, problems emerges while implementing it in real-time because of their dynamic environment and complex algorithms used in object detection. In the last few years, Convolution Neural Network (CNN) have emerged as a powerful tool for recognizing image content and in computer vision approach for most problems. In this paper, We revived begins the brief introduction of deep learning and object detection framework like Convolutional Neural Network(CNN), You only look once - version 4 (YOLOv4). Then we focus on our proposed object detection architectures along with some modifications. The traditional model detects a small object in images. We have some modifications to the model. Our proposed method gives the correct result with accuracy.