Stereoscopic Video Quality Assessment Using Oriented Local Gravitational Force Statistics

Hou, Yujian; Liu, Lixiong; Zhang, Yongmei; Sang, Qingbing

doi:10.1109/access.2020.3041612

Cited by 3 publications

(5 citation statements)

References 50 publications

(75 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We repeated the training-testing process 1000 times and take the median of SROCC, PLCC and RMSE as the performance indicator of the evaluation model. We selected some classic 2D image/video quality assessment models, such as PSNR, SSIM 27 , VIS3 28 , and some 3D image/video quality assessment models, such as SINQ 29 , SJND 24 , BSVQE 4 , LBP-TOP 20 , SVIPOS 30 , as comparison algorithms. For the image quality assessment models, we evaluated the quality of each frame of the stereoscopic video pair, and took the average of quality scores of all frames as the final quality score for the stereoscopic video.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

No-reference stereoscopic video quality assessment based on Tchebichef moment

Chen

Wen²

2022

Fourteenth International Conference on Digital Image Processing (ICDIP 2022)

View full text Add to dashboard Cite

We propose a no-reference (NR) stereoscopic video quality assessment (SVQA) model based on Tchebichef moment in this paper. Specifically, we extract keyframes according to mutual information between adjacent frames, and then the extracted keyframes are segmented to patches to calculate low-order Tchebichef moments. Since the strong description ability of Tchebichef moment, and different order of Tchebichef moment can represent independent features with minimal information redundancy, we extract statistical features of Tchebichef moment on computed patches as spatial features. Considering the influence of distortions in spatiotemporal domain to video quality, we use the three-dimensional derivative of Gaussian filters to calculate the spatiotemporal energy responses and extract statistical features from the responses as spatiotemporal features. Finally, we combine the spatial and spatiotemporal features to predict the quality of stereoscopic videos. The proposed model is evaluated on the NAMA3DS1-COSPAD1, SVQA and Waterloo IVC phase I databases. The experimental results show that the proposed model achieved competitive performance as compared with existing SVQA models.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Existing SVQA methods often extract features from all frames of the videos [3][4][5][6] . Extracting features on keyframes can reduce redundant information and computational complexity.…”

Section: Introductionmentioning

confidence: 99%

No-reference stereoscopic video quality assessment based on Tchebichef moment

Chen

Wen²

2022

Fourteenth International Conference on Digital Image Processing (ICDIP 2022)

View full text Add to dashboard Cite

show abstract

“…Experiments have shown that the method still maintains good performance and in the case of other types of distortion [ 18 ]. Hou et al used oriented local gravitational force (OLGF) statistics to extract local gravity responses from monocular maps, product images and frame difference maps and mapped the gravity response statistics to the quality score of stereo video [ 2 ] using SVR.…”

Section: Related Workmentioning

confidence: 99%

“…At present, 3D video is mainly PGC. In the process of 3D image acquisition, professionals control the quality of video shooting professionally and strictly [ 2 ]. However, due to the limitations of hardware equipment and technical level, video has varying degrees of distortion in storage, transmission, display and other links, which makes the viewing experience of users decline.…”

Section: Introductionmentioning

confidence: 99%

No-Reference Quality Assessment of Stereoscopic Video Based on Temporal Adaptive Model for Improved Visual Communication

Zhang

2022

Sensors

View full text Add to dashboard Cite

An objective stereo video quality assessment (SVQA) strives to be consistent with human visual perception while ensuring a low time and labor cost of evaluation. The temporal–spatial characteristics of video make the data processing volume of quality evaluation surge, making an SVQA more challenging. Aiming at the effect of distortion on the stereoscopic temporal domain, a stereo video quality assessment method based on the temporal–spatial relation is proposed in this paper. Specifically, a temporal adaptive model (TAM) for a video is established to describe the space–time domain of the video from both local and global levels. This model can be easily embedded into any 2D CNN backbone network. Compared with the improved model based on 3D CNN, this model has obvious advantages in operating efficiency. Experimental results on NAMA3DS1-COSPAD1 database, WaterlooIVC 3D Video Phase I database, QI-SVQA database and SIAT depth quality database show that the model has excellent performance.

show abstract

“…Hou et al 85 developed an NR S3D VQA algorithm called Stereoscopic Video Integrity Predictor using OLGF Statistics (SVIPOS) based on a proposed oriented local gravitational force (OLGF) descriptor in the space-time domain, which is an extension of an existing local gravitational force descriptor with two added new components of relative local gravitational force magnitude and orientation. Considering the left and the right views of the video sequences as input parameters, the cyclopean image and product image is generated in the spatial domain to measure the correlation between these two videos, and considering only the left video sequence, a frame difference image is generated in the temporal domain.…”

Section: Nr Objective Metricsmentioning

confidence: 99%

On the practical applications of objective quality metrics for stereoscopic 3D imaging

Biswas

Appina

Tamboli³

et al. 2021

Applications of Machine Learning 2021

View full text Add to dashboard Cite

Objective quality metrics provide cost-efficient methods for quality evaluation, as they are practically algorithms, models, that avoid the necessity of subjective assessment, which is a precise but resource-consuming approach. Their ultimate measure of prediction accuracy fundamentally relies on the correlation between the estimated levels of quality and the actual subjective scores of perceived quality, rated by human individuals. Such metrics have already been developed for every single emerging technology where quality, in general, is relevant. This applies to stereoscopic 3D imaging as well, which is utilized in both industry, healthcare, education and entertainment. In this paper, we introduce an exhaustive analysis regarding the practical applications of objective quality metrics for stereoscopic 3D imaging. Our contribution addresses each and every state-of-the-art objective metric in the scientific literature, separately for image and video quality. The study differentiates the metrics by input requirements and supervision, and examines performance via statistical measures. Machine learning algorithms are particularly emphasized within the paper, such as the Deep Edge and COlor Signal INtegrity Evaluator (DECOSINE) using Segmented Stacked Auto-Encoder (S-SAE), different Convolutional Neural Network (CNN) frameworks, and transfer-learning-based methods like the Xception model, AlexNet, ResNet-18, ImageNet, Caffe, GoogLeNet, and also our very own transfer-learning-based methods. The paper focuses on the actual practical applications of the predictive models, and highlights relevant criteria, along with general feasibility, suitability and usability. The analysis of the investigated use cases also addresses potential future research questions and specifies the appropriate directives for quality-focused, user-centric development.

show abstract

Stereoscopic Video Quality Assessment Using Oriented Local Gravitational Force Statistics

Cited by 3 publications

References 50 publications

No-reference stereoscopic video quality assessment based on Tchebichef moment

No-reference stereoscopic video quality assessment based on Tchebichef moment

No-Reference Quality Assessment of Stereoscopic Video Based on Temporal Adaptive Model for Improved Visual Communication

On the practical applications of objective quality metrics for stereoscopic 3D imaging

Contact Info

Product

Resources

About