Prioritized Information Bottleneck Theoretic Framework with Distributed Online Learning for Edge Video Analytics
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912177191911424 |
|---|---|
| author | Fang, Zhengru Hu, Senkang Wang, Jingjing Deng, Yiqin Chen, Xianhao Fang, Yuguang |
| author_facet | Fang, Zhengru Hu, Senkang Wang, Jingjing Deng, Yiqin Chen, Xianhao Fang, Yuguang |
| contents | Collaborative perception systems leverage multiple edge devices, such surveillance cameras or autonomous cars, to enhance sensing quality and eliminate blind spots. Despite their advantages, challenges such as limited channel capacity and data redundancy impede their effectiveness. To address these issues, we introduce the Prioritized Information Bottleneck (PIB) framework for edge video analytics. This framework prioritizes the shared data based on the signal-to-noise ratio (SNR) and camera coverage of the region of interest (RoI), reducing spatial-temporal data redundancy to transmit only essential information. This strategy avoids the need for video reconstruction at edge servers and maintains low latency. It leverages a deterministic information bottleneck method to extract compact, relevant features, balancing informativeness and communication costs. For high-dimensional data, we apply variational approximations for practical optimization. To reduce communication costs in fluctuating connections, we propose a gate mechanism based on distributed online learning (DOL) to filter out less informative messages and efficiently select edge servers. Moreover, we establish the asymptotic optimality of DOL by proving the sublinearity of their regrets. To validate the effectiveness of the PIB framework, we conduct real-world experiments on three types of edge devices with varied computing capabilities. Compared to five coding methods for image and video compression, PIB improves mean object detection accuracy (MODA) while reducing 17.8% and reduces communication costs by 82.65% under poor channel conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00146 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prioritized Information Bottleneck Theoretic Framework with Distributed Online Learning for Edge Video Analytics Fang, Zhengru Hu, Senkang Wang, Jingjing Deng, Yiqin Chen, Xianhao Fang, Yuguang Networking and Internet Architecture Collaborative perception systems leverage multiple edge devices, such surveillance cameras or autonomous cars, to enhance sensing quality and eliminate blind spots. Despite their advantages, challenges such as limited channel capacity and data redundancy impede their effectiveness. To address these issues, we introduce the Prioritized Information Bottleneck (PIB) framework for edge video analytics. This framework prioritizes the shared data based on the signal-to-noise ratio (SNR) and camera coverage of the region of interest (RoI), reducing spatial-temporal data redundancy to transmit only essential information. This strategy avoids the need for video reconstruction at edge servers and maintains low latency. It leverages a deterministic information bottleneck method to extract compact, relevant features, balancing informativeness and communication costs. For high-dimensional data, we apply variational approximations for practical optimization. To reduce communication costs in fluctuating connections, we propose a gate mechanism based on distributed online learning (DOL) to filter out less informative messages and efficiently select edge servers. Moreover, we establish the asymptotic optimality of DOL by proving the sublinearity of their regrets. To validate the effectiveness of the PIB framework, we conduct real-world experiments on three types of edge devices with varied computing capabilities. Compared to five coding methods for image and video compression, PIB improves mean object detection accuracy (MODA) while reducing 17.8% and reduces communication costs by 82.65% under poor channel conditions. |
| title | Prioritized Information Bottleneck Theoretic Framework with Distributed Online Learning for Edge Video Analytics |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2409.00146 |