Real time object detection and trackingsystem for video surveillance system
- PDF / 2,049,076 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 56 Downloads / 239 Views
Real time object detection and tracking system for video surveillance system Sudan Jha 1 & Changho Seo 2 & Eunmok Yang 3 & Gyanendra Prasad Joshi 4 Received: 14 November 2019 / Revised: 28 July 2020 / Accepted: 27 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
This paper introduces a system capable of real-time video surveillance in low-end edge computing environment by combining object detection tracking algorithm. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as region-based convolutional network, which has two stages for inferencing. One-stage detection algorithms such as single shot detector and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as general-purpose graphics processing unit is required to achieve excellent object detection performance and speed. In this study, we propose an approach called N-YOLO which is instead of resizing image step in YOLO algorithm, it divides into fixed size images used in YOLO and merges detection results of each divided sub-image with inference results at different times using correlation-based tracking algorithm the amount of computation for object detection and tracking can be significantly reduced. In addition, we propose a system that can guarantee real-time performance in various edge computing environments by adaptively controlling the cycle of object detection and tracking. Keywords Object detection . Object tracking . Video surveillance . Edge computing . Artificial intelligence
* Gyanendra Prasad Joshi [email protected]
1
School of Computer Science and Engineering, Lovely Professional University, Phagwara, Punjab 144411, India
2
Department of Convergence Science, Kongju National University, Gongju 32588, South Korea
3
Department of Financial Information Security, Kookmin University, Seoul 02707, South Korea
4
Department of Computer Science and Engineering, Sejong University, Seoul 05006, South Korea
Multimedia Tools and Applications
1 Introduction Object detection has seen substantial improvements during the last couple of years due to the recent advancement in deep learning-based algorithms. Many researchers have investigated object detection by considering each frame of video as image to detect object in video. However, humans do not regard each frame as an independent image in the process of recognizing an object in a video, rather track a major motion in relation to a previous frame. Thus, video detection technology such as video surveillance, automotive driving, and intelligent robotics is a combination of object detection and object tracking technologies. Recently, algorithms such as region-based convolutional network (R-CNN), single shot detector (SSD), and you only look once (YOLO) have emerged, which show remarkable performance in the field of real time object detection [7, 22, 23]. However, very highperf
Data Loading...
