Abstract:Typically, point cloud encoders allocate a similar bitrate for geometry and attributes (usually RGB color components) information coding. This paper reports a quality study considering different coding bitrate tradeoff between geometry and attributes. A set of five point clouds, representing different characteristics and types of content was encoded with the MPEG standard Geometry Point Cloud Compression (G-PCC), using octree to encode geometry information, and both the Region Adaptive Hierarchical Transform and the Prediction Lifting transform for attributes. Furthermore, the JPEG Pleno Point Cloud Verification Model was also tested. Five different attributes/geometry bitrate tradeoffs were considered, notably 70%/30%, 60%/40%, 50%/50%, 40%/60%, 30%/70%. Three point cloud objective metrics were selected to assess the quality of the reconstructed point clouds, notably the PSNR YUV, the Point Cloud Quality Metric, and GraphSIM. Furthermore, for each encoder, the Bjonteegaard Deltas were computed for each tradeoff, using the 50%/50% tradeoff as a reference. The reported results indicate that using a higher bitrate allocation for attribute encoding usually yields slightly better results.
Abstract:The quality evaluation of three deep learning-based coding solutions for point cloud geometry, notably ADLPCC, PCC GEO CNNv2, and PCGCv2, is presented. The MPEG G-PCC was used as an anchor. Furthermore, LUT SR, which uses multi-resolution Look-Up tables, was also considered. A set of six point clouds representing landscapes and objects were used. As point cloud texture has a great influence on the perceived quality, two different subjective studies that differ in the texture addition model are reported and statistically compared. In the first experiment, the dataset was first encoded with the identified codecs. Then, the texture of the original point cloud was mapped to the decoded point cloud using the Meshlab software, resulting in a point cloud with both geometry and texture information. Finally, the resulting point cloud was encoded with G-PCC using the lossless-geometry-lossy-atts mode, while in the second experiment the texture was mapped directly onto the distorted geometry. Moreover, both subjective evaluations were used to benchmark a set of objective point cloud quality metrics. The two experiments were shown to be statistically different, and the tested metrics revealed quite different behaviors for the two sets of data. The results reveal that the preferred method of evaluation is the encoding of texture information with G-PCC after mapping the texture of the original point cloud to the distorted point cloud. The results suggest that current objective metrics are not suitable to evaluate distortions created by machine learning-based codecs.
Abstract:This paper reports on a subjective quality evaluation of static point clouds encoded with the MPEG codecs V-PCC and G-PCC, the deep learning-based codec RS-DLPCC, and the popular Draco codec. 18 subjects visualized 3D representations of distorted point clouds using a Head Mounted Display, which allowed for a direct comparison with their reference. The Mean Opinion Scores (MOS) obtained in this subjective evaluation were compared with the MOS from two previous studies, where the same content was visualized either on a 2D display or a 3D stereoscopic display, through the Pearson Correlation, Spearman Rank Order Correlation, Root Mean Square Error, and the Outlier Ratio. The results indicate that the three studies are highly correlated with one another. Moreover, a statistical analysis between all evaluations showed no significant differences between them.
Abstract:Quality assessment is a key element for the evaluation of hardware and software involved in image and video acquisition, processing, and visualization. In the medical field, user-based quality assessment is still considered more reliable than objective methods, which allow the implementation of automated and more efficient solutions. Regardless of increasing research in this topic in the last decade, defining quality standards for medical content remains a non-trivial task, as the focus should be on the diagnostic value assessed from expert viewers rather than the perceived quality from na\"{i}ve viewers, and objective quality metrics should aim at estimating the first rather than the latter. In this paper, we present a survey of methodologies used for the objective quality assessment of medical images and videos, dividing them into visual quality-based and task-based approaches. Visual quality based methods compute a quality index directly from visual attributes, while task-based methods, being increasingly explored, measure the impact of quality impairments on the performance of a specific task. A discussion on the limitations of state-of-the-art research on this topic is also provided, along with future challenges to be addressed.
Abstract:Magnetic Resonance Imaging (MRI) is a non-invasive tool for the clinical assessment of low-prevalence neuromuscular disorders. Automated diagnosis methods might reduce the need for biopsies and provide valuable information on disease follow-up. In this paper, three methods are proposed to classify target muscles in Collagen VI-related myopathy cases, based on their degree of involvement, notably a Convolutional Neural Network, a Fully Connected Network to classify texture features, and a hybrid method combining the two feature sets. The proposed methods was evaluated on axial T1-weighted Turbo Spin-Echo MRI from 26 subjects, including Ullrich Congenital Muscular Dystrophy or Bethlem Myopathy patients at different evolution stages. The best results were obtained with the hybrid model, resulting in a global accuracy of 93.8\%, and F-scores of 0.99, 0.82, and 0.95, for healthy, mild and moderate/severe cases, respectively.
Abstract:Segmentation of skeletal muscles in Magnetic Resonance Images (MRI) is essential for the study of muscle physiology and diagnosis of muscular pathologies. However, manual segmentation of large MRI volumes is a time-consuming task. The state-of-the-art on algorithms for muscle segmentation in MRI is still not very extensive and is somewhat database-dependent. In this paper, an automated segmentation method based on AdaBoost classification of local texture features is presented. The texture descriptor consists of the Histogram of Oriented Gradients (HOG), Wavelet-based features, and a set of statistical measures computed from both the original and the Laplacian of Gaussian filtering of the grayscale MRI. The classifier performance suggests that texture analysis may be a helpful tool for designing a generalized and automated MRI muscle segmentation framework. Furthermore, an atlas-based approach to individual muscle segmentation is also described in this paper. The atlas is obtained by overlaying the muscle segmentation ground truth, provided by a radiologist, after image alignment using an appropriate affine transformation. Then, it is used to define the muscle labels upon the AdaBoost binary segmentation. The developed atlas method provides reasonable results when an accurate muscle tissue segmentation was obtained.