Apron surveillance video coding based on compositing virtual reference frame with object library
Abstract A video coding framework for the apron surveillance scene has been proposed in this paper, which aims to improve coding efficiency by eliminating long‐term redundancy at the object level. To achieve this goal, this study first develops an existing block‐based hybrid video coding framework b...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-06-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12810 |
| _version_ | 1797813781059862528 |
|---|---|
| author | Zonglei Lyu Bo Zhang |
| author_facet | Zonglei Lyu Bo Zhang |
| author_sort | Zonglei Lyu |
| collection | DOAJ |
| description | Abstract A video coding framework for the apron surveillance scene has been proposed in this paper, which aims to improve coding efficiency by eliminating long‐term redundancy at the object level. To achieve this goal, this study first develops an existing block‐based hybrid video coding framework by exploiting the video redundancy on the object level to perform video coding. Second, an object‐library mechanism is designed to collect the representative object images as coding references on larger temporal and spatial scales. Finally, a virtual reference frame, which blends background and foreground references from the object library, is adaptively composited according to the video content to improve the inter‐prediction performance. Preliminary experimental results demonstrate that the proposed method achieves a high BD rate reduction of up to 23.97% in apron surveillance video sequences, compared to the standard high efficiency video coding (HEVC). |
| first_indexed | 2024-03-13T07:57:51Z |
| format | Article |
| id | doaj.art-295672681baf478bb823a853f04cfb4f |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-03-13T07:57:51Z |
| publishDate | 2023-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-295672681baf478bb823a853f04cfb4f2023-06-02T03:06:38ZengWileyIET Image Processing1751-96591751-96672023-06-011782475248810.1049/ipr2.12810Apron surveillance video coding based on compositing virtual reference frame with object libraryZonglei Lyu0Bo Zhang1College of Computer Science and Technology Civil Aviation University of China Tianjin ChinaCollege of Computer Science and Technology Civil Aviation University of China Tianjin ChinaAbstract A video coding framework for the apron surveillance scene has been proposed in this paper, which aims to improve coding efficiency by eliminating long‐term redundancy at the object level. To achieve this goal, this study first develops an existing block‐based hybrid video coding framework by exploiting the video redundancy on the object level to perform video coding. Second, an object‐library mechanism is designed to collect the representative object images as coding references on larger temporal and spatial scales. Finally, a virtual reference frame, which blends background and foreground references from the object library, is adaptively composited according to the video content to improve the inter‐prediction performance. Preliminary experimental results demonstrate that the proposed method achieves a high BD rate reduction of up to 23.97% in apron surveillance video sequences, compared to the standard high efficiency video coding (HEVC).https://doi.org/10.1049/ipr2.12810apron surveillance video codingcompositing virtual frameobject detectionvideo coding |
| spellingShingle | Zonglei Lyu Bo Zhang Apron surveillance video coding based on compositing virtual reference frame with object library IET Image Processing apron surveillance video coding compositing virtual frame object detection video coding |
| title | Apron surveillance video coding based on compositing virtual reference frame with object library |
| title_full | Apron surveillance video coding based on compositing virtual reference frame with object library |
| title_fullStr | Apron surveillance video coding based on compositing virtual reference frame with object library |
| title_full_unstemmed | Apron surveillance video coding based on compositing virtual reference frame with object library |
| title_short | Apron surveillance video coding based on compositing virtual reference frame with object library |
| title_sort | apron surveillance video coding based on compositing virtual reference frame with object library |
| topic | apron surveillance video coding compositing virtual frame object detection video coding |
| url | https://doi.org/10.1049/ipr2.12810 |
| work_keys_str_mv | AT zongleilyu apronsurveillancevideocodingbasedoncompositingvirtualreferenceframewithobjectlibrary AT bozhang apronsurveillancevideocodingbasedoncompositingvirtualreferenceframewithobjectlibrary |