Stochastic Image Transmission with CoAP for Extreme Environments

Takeshita, Erina; Sakaguchi, Asahi; Hisano, Daisuke; Inoue, Yasuhiro; Maruta, Kazuki; Hara-Azumi, Yuko; Nakayama, Yu

doi:10.48550/arxiv.2205.01852

Cited by 1 publication

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed scheme sets a lower compression rate for the background region. As part of a related study, we proposed multiple ROI transmission schemes and reduced the number of background images transmissions in a narrow bandwidth, and high packet loss [17]. H. Li et al proposed an image compression scheme focusing on the difference in the required image quality of each application [18].…”

Section: Related Workmentioning

confidence: 99%

Edge Computing-Assisted DNN Image Recognition System With Progressive Image Retransmission

et al. 2022

Self Cite

View full text Add to dashboard Cite

Deep learning-based image recognition systems have rapidly evolved. Due to the extensive processing load of the deep neural network (DNN) on graphic processing units (GPUs), the DNN model is deployed on the cloud server. Images or videos are forwarded from user terminals through the network to the server. In recent years, edge computing has gained popularity as a means of reducing the data traffic in the backbone network. However, the last one-mile access network between an edge server and user terminals will still be congested because a large amount of data such as video/image files must be forwarded. In particular, when computer vision applications such as image recognition are loaded in the edge network, a large amount of data is forwarded although the edge server always may not need the high-definition image. This paper proposes an image compression and progressive retransmission scheme for deep learning-based image recognition systems to reduce image data traffic and alleviate network congestion. The proposed method introduces an entropy-based threshold calculated from posterior probabilities from a deep learning model's output layer. Entropy is an extremely effective metric because it can be used as an indicator independent of the number of classification labels in the DNN model. The thresholding can control the image retransmission and reduce traffic while maintaining image recognition accuracy. We implement the proposed scheme on the edge server and reveal the relationship between the data compression and the recognition accuracy through simulation evaluation. As a result, we indicate that an entropy-based threshold reduces the overall ambiguity of the accuracy of image recognition. Moreover, when a higher accuracy recognition model with more accuracy is combined with a retransmission scheme, it becomes the more effective. INDEX TERMS Edge computing, computer vision, image recognition, retransmission systemI. INTRODUCTION D EEP neural network (DNN) has continued improving image recognition estimation accuracy in recent years. DNN-based image recognition has been aggressively used on Internet of things (IoT) applications. In the IoT, User terminals, such as smartphones and mobile sensors, collect data and send it to network servers, i.e., cloud, that analyze them and provide various services [1], [2]. Although the cloud computing is now one of the mainstream technologies, there are some challenges, such as increased latency and load between the user terminals with increasing IoT applications that require real-time processing and the number of user terminals. Therefore, edge computing technologies that relocate processing resources to the areas near the user terminals have been studied [3]-[7]. Edge computing can provide low-latency services because the user terminals and

show abstract

Section: Related Workmentioning

confidence: 99%