Network virtualization for real-time processing of object detection using deep learning
- PDF / 1,493,050 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 88 Downloads / 175 Views
Network virtualization for real-time processing of object detection using deep learning Dae-Young Kim 1 & Ji-Hoon Park 1 & Youngchan Lee 1 & Seokhoon Kim 2 Received: 29 May 2020 / Revised: 28 July 2020 / Accepted: 12 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
These days, networked cameras are used in various applications using deep learning. In particular, as the deep learning technology for image processing develops, image-based application services using networked camera are expanding. Object detections are the representative application in the image-based applications. Images from the networked camera are transmitted to a deep learning machine, which performs object detection using a deep neural network (DNN) algorithm. For real-time processing of the object detection, lightweight of the image learning steps is needed. Both preprocessing of training sets and lightweight learning models can reduce computing loads for image learning. However, it is most important to receive video frames from the network camera without delay. In this paper, we provide a way for the learning machine to receive video frames with minimal delay. The proposed method is a kind of network virtualization for image-based object detection. It monitors network the status of available network interfaces in networked cameras. When a camera transmit video frames, the virtualized module determines the appropriate network interface to reduce delay. The performance of the proposed method is evaluated in the image-based object detection system using deep learning. Keywords Network virtualization . Real-time processing . Object detection . Deep learning
* Seokhoon Kim [email protected] Dae-Young Kim [email protected] Ji-Hoon Park [email protected] Youngchan Lee [email protected]
1
School of Computer Software, Daegu Catholic University, Gyeongsan 38430, Republic of Korea
2
Department of Computer Software Engineering, Soonchunhyang University, Asan 31538, Republic of Korea
Multimedia Tools and Applications
1 Introduction Computer vision technology using camera systems has developed rapidly in recent years. Recent advances in the technology have allowed object detection to be applied to various application services. Currently, object detection is not only used for simple monitoring services but also for intelligent services in smart cities. For example, self-driving cars use it to recognize other cars, pedestrians, or obstacles. Intelligent transport systems monitor transport traffic in roads and provide transport traffic control, while smart parking services find proper parking area for users. In addition, population monitoring systems provides efficient management of public facilities and safety services. Object detection means to determine whether or not the object in an image belongs to given categories [11]. As deep learning technologies are applied to object detection, detection accuracy is effectively increased. Therefore, various studies using deep learning have been performed to improve
Data Loading...
