Object Detection-Based Video Compression

被引:3
|
作者
Kim, Myung-Jun [1 ]
Lee, Yung-Lyul [1 ]
机构
[1] Sejong Univ, Dept Comp Engn, Seoul 05006, South Korea
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 09期
基金
新加坡国家研究基金会;
关键词
object detection; video compression; VVC (Versatile Video Coding); video coding application; quantization;
D O I
10.3390/app12094525
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Video compression is designed to provide good subjective image quality, even at a high-compression ratio. In addition, video quality metrics have been used to show the results can maintain a high Peak Signal-to-Noise Ratio (PSNR), even at high compression. However, there are many difficulties in object recognition on the decoder side due to the low image quality caused by high compression. Accordingly, providing good image quality for the detected objects is necessary for the given total bitrate for utilizing object detection in a video decoder. In this paper, object detection-based video compression by the encoder and decoder is proposed that allocates lower quantization parameters to the detected-object regions and higher quantization parameters to the background. Therefore, better image quality is obtained for the detected objects on the decoder side. Object detection-based video compression consists of two types: Versatile Video Coding (VVC) and object detection. In this paper, the decoder performs the decompression process by receiving the bitstreams in the object-detection decoder and the VVC decoder. In the proposed method, the VVC encoder and decoder are processed based on the information obtained from object detection. In a random access (RA) configuration, the average Bjontegaard Delta (BD)-rates of Y, Cb, and Cr increased by 2.33%, 2.67%, and 2.78%, respectively. In an All Intra (AI) configuration, the average BD-rates of Y, Cb, and Cr increased by 0.59%, 1.66%, and 1.42%, respectively. In an RA configuration, the averages of Delta Y-PSNR, Delta Cb-PSNR, and Delta Cr-PSNR for the object-detected areas improved to 0.17%, 0.23%, and 0.04%, respectively. In an AI configuration, the averages of Delta Y-PSNR, Delta Cb-PSNR, and Delta Cr-PSNR for the object-detected areas improved to 0.71%, 0.30%, and 0.30%, respectively. Subjective image quality was also improved in the object-detected areas.
引用
收藏
页数:18
相关论文
共 50 条
  • [41] DOMOPT: A Detection-Based Online Multi-Object Pedestrian Tracking Network for Videos
    Huan, Ruohong
    Zheng, Shuaishuai
    Xie, Chaojie
    Chen, Peng
    Liang, Ronghua
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2023, 37 (09)
  • [42] Detection of breath cycles in pediatric lung sounds via an object detection-based transfer learning method
    Park, Sa-Yoon
    Park, Ji Soo
    Lee, Jisoo
    Lee, Hyesu
    Kim, Yelin
    Suh, Dong In
    Kim, Kwangsoo
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2025, 105
  • [43] An object detection-based few-shot learning approach for multimedia quality assessment
    Chatterjee, Rajdeep
    Chatterjee, Ankita
    Islam, S. K. Hafizul
    Khan, Muhammad Khurram
    MULTIMEDIA SYSTEMS, 2023, 29 (05) : 2899 - 2912
  • [44] An object detection-based few-shot learning approach for multimedia quality assessment
    Rajdeep Chatterjee
    Ankita Chatterjee
    SK Hafizul Islam
    Muhammad Khurram Khan
    Multimedia Systems, 2023, 29 : 2899 - 2912
  • [45] Detection and tracking based tubelet generation for video object detection
    Wang, Bin
    Tang, Sheng
    Xiao, Jun-Bin
    Yan, Quan-Feng
    Zhang, Yong-Dong
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2019, 58 : 102 - 111
  • [46] EFFECT OF H.264/AVC COMPRESSION ON OBJECT DETECTION FOR VIDEO SURVEILLANCE
    Poppe, C.
    De Bruyne, S.
    Lambert, P.
    Van de Walle, R.
    2009 10TH INTERNATIONAL WORKSHOP ON IMAGE ANALYSIS FOR MULTIMEDIA INTERACTIVE SERVICES, 2009, : 129 - 132
  • [47] Object-based encoding: Next-generation video compression
    Strat, TM
    PROCEEDINGS OF WORKSHOP AND EXHIBITION ON MPEG-4, 2002, : 53 - 57
  • [48] A new object-based system for fractal video sequences compression
    Belloulata, Kamel
    Zhu, Shiping
    Journal of Multimedia, 2007, 2 (03): : 17 - 25
  • [49] Trifocal motion modeling for object-based video compression and manipulation
    Sun, ZH
    Tekalp, AM
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 1998, 8 (05) : 667 - 685
  • [50] A new object-based system for fractal video sequences compression
    Belloulata, Kamel
    Zhu, Shiping
    DCC: 2008 DATA COMPRESSION CONFERENCE, PROCEEDINGS, 2008, : 508 - 508