Compressed Video Quality Index Based on Saliency-Aware Artifact Detection
Video coding technology makes the required storage and transmission bandwidth of video services decrease by reducing the bitrate of the video stream. However, the compressed video signals may involve perceivable information loss, especially when the video is overcompressed. In such cases, the viewer...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/19/6429 |
| _version_ | 1797515774752980992 |
|---|---|
| author | Liqun Lin Jing Yang Zheng Wang Liping Zhou Weiling Chen Yiwen Xu |
| author_facet | Liqun Lin Jing Yang Zheng Wang Liping Zhou Weiling Chen Yiwen Xu |
| author_sort | Liqun Lin |
| collection | DOAJ |
| description | Video coding technology makes the required storage and transmission bandwidth of video services decrease by reducing the bitrate of the video stream. However, the compressed video signals may involve perceivable information loss, especially when the video is overcompressed. In such cases, the viewers can observe visually annoying artifacts, namely, Perceivable Encoding Artifacts (PEAs), which degrade their perceived video quality. To monitor and measure these PEAs (including blurring, blocking, ringing and color bleeding), we propose an objective video quality metric named Saliency-Aware Artifact Measurement (SAAM) without any reference information. The SAAM metric first introduces video saliency detection to extract interested regions and further splits these regions into a finite number of image patches. For each image patch, the data-driven model is utilized to evaluate intensities of PEAs. Finally, these intensities are fused into an overall metric using Support Vector Regression (SVR). In experiment section, we compared the SAAM metric with other popular video quality metrics on four publicly available databases: LIVE, CSIQ, IVP and FERIT-RTRK. The results reveal the promising quality prediction performance of the SAAM metric, which is superior to most of the popular compressed video quality evaluation models. |
| first_indexed | 2024-03-10T06:52:02Z |
| format | Article |
| id | doaj.art-557ee17cc9ed47179913364295bb1de7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T06:52:02Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-557ee17cc9ed47179913364295bb1de72023-11-22T16:46:01ZengMDPI AGSensors1424-82202021-09-012119642910.3390/s21196429Compressed Video Quality Index Based on Saliency-Aware Artifact DetectionLiqun Lin0Jing Yang1Zheng Wang2Liping Zhou3Weiling Chen4Yiwen Xu5Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou 350002, ChinaFujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou 350002, ChinaFujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou 350002, ChinaFujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou 350002, ChinaFujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou 350002, ChinaFujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou 350002, ChinaVideo coding technology makes the required storage and transmission bandwidth of video services decrease by reducing the bitrate of the video stream. However, the compressed video signals may involve perceivable information loss, especially when the video is overcompressed. In such cases, the viewers can observe visually annoying artifacts, namely, Perceivable Encoding Artifacts (PEAs), which degrade their perceived video quality. To monitor and measure these PEAs (including blurring, blocking, ringing and color bleeding), we propose an objective video quality metric named Saliency-Aware Artifact Measurement (SAAM) without any reference information. The SAAM metric first introduces video saliency detection to extract interested regions and further splits these regions into a finite number of image patches. For each image patch, the data-driven model is utilized to evaluate intensities of PEAs. Finally, these intensities are fused into an overall metric using Support Vector Regression (SVR). In experiment section, we compared the SAAM metric with other popular video quality metrics on four publicly available databases: LIVE, CSIQ, IVP and FERIT-RTRK. The results reveal the promising quality prediction performance of the SAAM metric, which is superior to most of the popular compressed video quality evaluation models.https://www.mdpi.com/1424-8220/21/19/6429video quality assessmentsaliency detectionperceivable encoding artifactsDense Convolutional Network (DenseNet) |
| spellingShingle | Liqun Lin Jing Yang Zheng Wang Liping Zhou Weiling Chen Yiwen Xu Compressed Video Quality Index Based on Saliency-Aware Artifact Detection Sensors video quality assessment saliency detection perceivable encoding artifacts Dense Convolutional Network (DenseNet) |
| title | Compressed Video Quality Index Based on Saliency-Aware Artifact Detection |
| title_full | Compressed Video Quality Index Based on Saliency-Aware Artifact Detection |
| title_fullStr | Compressed Video Quality Index Based on Saliency-Aware Artifact Detection |
| title_full_unstemmed | Compressed Video Quality Index Based on Saliency-Aware Artifact Detection |
| title_short | Compressed Video Quality Index Based on Saliency-Aware Artifact Detection |
| title_sort | compressed video quality index based on saliency aware artifact detection |
| topic | video quality assessment saliency detection perceivable encoding artifacts Dense Convolutional Network (DenseNet) |
| url | https://www.mdpi.com/1424-8220/21/19/6429 |
| work_keys_str_mv | AT liqunlin compressedvideoqualityindexbasedonsaliencyawareartifactdetection AT jingyang compressedvideoqualityindexbasedonsaliencyawareartifactdetection AT zhengwang compressedvideoqualityindexbasedonsaliencyawareartifactdetection AT lipingzhou compressedvideoqualityindexbasedonsaliencyawareartifactdetection AT weilingchen compressedvideoqualityindexbasedonsaliencyawareartifactdetection AT yiwenxu compressedvideoqualityindexbasedonsaliencyawareartifactdetection |