Inter-Feature-Map Differential Coding of Surveillance Video
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912102466191360 |
|---|---|
| author | Iino, Kei Takahashi, Miho Watanabe, Hiroshi Morinaga, Ichiro Enomoto, Shohei Shi, Xu Sakamoto, Akira Eda, Takeharu |
| author_facet | Iino, Kei Takahashi, Miho Watanabe, Hiroshi Morinaga, Ichiro Enomoto, Shohei Shi, Xu Sakamoto, Akira Eda, Takeharu |
| contents | In Collaborative Intelligence, a deep neural network (DNN) is partitioned and deployed at the edge and the cloud for bandwidth saving and system optimization. When a model input is an image, it has been confirmed that the intermediate feature map, the output from the edge, can be smaller than the input data size. However, its effectiveness has not been reported when the input is a video. In this study, we propose a method to compress the feature map of surveillance videos by applying inter-feature-map differential coding (IFMDC). IFMDC shows a compression ratio comparable to, or better than, HEVC to the input video in the case of small accuracy reduction. Our method is especially effective for videos that are sensitive to image quality degradation when HEVC is applied |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_00984 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Inter-Feature-Map Differential Coding of Surveillance Video Iino, Kei Takahashi, Miho Watanabe, Hiroshi Morinaga, Ichiro Enomoto, Shohei Shi, Xu Sakamoto, Akira Eda, Takeharu Computer Vision and Pattern Recognition Image and Video Processing In Collaborative Intelligence, a deep neural network (DNN) is partitioned and deployed at the edge and the cloud for bandwidth saving and system optimization. When a model input is an image, it has been confirmed that the intermediate feature map, the output from the edge, can be smaller than the input data size. However, its effectiveness has not been reported when the input is a video. In this study, we propose a method to compress the feature map of surveillance videos by applying inter-feature-map differential coding (IFMDC). IFMDC shows a compression ratio comparable to, or better than, HEVC to the input video in the case of small accuracy reduction. Our method is especially effective for videos that are sensitive to image quality degradation when HEVC is applied |
| title | Inter-Feature-Map Differential Coding of Surveillance Video |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2411.00984 |