Exploring Pseudo-Analog Video Transmission for Edge-AI Vision Applications

被引：1

作者：

Yamada, Junichiro ^{[1
]}

Suto, Katsuya ^{[1
]}

机构：

[1] Univ Elect Commun, Grad Sch Inform & Eng, Tokyo, Japan

来源：

2023 IEEE 20TH CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE, CCNC | 2023年

关键词：

Pseudo-Analog Video Transmission; Edge-AI; Object Detection;

D O I：

10.1109/CCNC51644.2023.10059990

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Edge-AI offloading is a promising solution for real-time object detection with resource-constrained edge devices. However, current edge architecture, which uses conventional digital video compression and modulation/coding, cannot provide stable object detection due to the scarcity of wireless resources and the explosive increase of edge devices. We employ pseudo-analog video transmission for Edge-AI offloading systems to cope with the issue. Although pseudo-analog video transmission cannot provide clear images, it has a substantial advantage for Edge-AI offloading systems, i.e., it can transmit higher-resolution video with limited bandwidth in lower Signal-to-Noise Ratio (SNR) links and do not need to control resolution according to wireless channel quality. This paper explores the impact of pseudo-analog video transmission on object detection accuracy.

引用

页数：2

共 10 条

[1] Closed-Loop Region of Interest Enabling High Spatial and Temporal Resolutions in Object Detection and Tracking via Wireless Camera [J].

Chen, Jack ;

Huang, Hen-Wei ;

Rupp, Philipp ;

Sinha, Anjali ;

Ehmke, Claas ;

Traverso, Giovanni .

IEEE ACCESS, 2021, 9 :87340-87350

[2] Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications [J].

Gamanayake, Chinthaka ;

Jayasinghe, Lahiru ;

Ng, Benny Kai Kiat ;

Yuen, Chau .

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2020, 14 (04) :802-816

[3] SoftCast: One-Size-Fits-All Wireless Video [J].

Jakubczak, Szymon ;

Katabi, Dina .

ACM SIGCOMM COMPUTER COMMUNICATION REVIEW, 2010, 40 (04) :449-450

[4]

Ran XK, 2018, IEEE INFOCOM SER, P1421, DOI 10.1109/INFOCOM.2018.8485905

[5]

Redmon J., 2018, PREPRINT, DOI [DOI 10.48550/ARXIV.1804.02767, 10.48550/arXiv.1804.02767]

[6] Object Recognition in Very Low Resolution Images Using Deep Collaborative Learning [J].

Seo, Jeongin ;

Park, Hyeyoung .

IEEE ACCESS, 2019, 7 :134071-134082

[7]

Wang HX, 2020, IEEE INFOCOM SER, P1379, DOI [10.1109/infocom41043.2020.9155517, 10.1109/INFOCOM41043.2020.9155517]

[8]

Xu YH, 2018, AAAI CONF ARTIF INTE, P4335

[9] Implementing Practical DNN-Based Object Detection Offloading Decision for Maximizing Detection Performance of Mobile Edge Devices [J].

Yoon, Giha ;

Kim, Geun-Yong ;

Yoo, Hark ;

Kim, Sung Chang ;

Kim, Ryangsoo .

IEEE ACCESS, 2021, 9 :140199-140211

[10] Residual Super-Resolution Single Shot Network for Low-Resolution Object Detection [J].

Zhao, Xiaotong ;

Li, Wei ;

Zhang, Yifan ;

Feng, Zhiyong .

IEEE ACCESS, 2018, 6 :47780-47793

← 1 →