Explore the vast range of titles available.

The lack of accurate information on the spatiotemporal variations of snow water equivalent (SWE) in mountain catchments remains a key problem in snow hydrology and water resources management. This is partly because there is no sensor to measure SWE beyond local scale. At Mt. Zugspitze, Germany, a superconducting gravimeter senses the gravity effect of the seasonal snow, reflecting the temporal evolution of SWE in a few kilometers scale radius. We used this new observation to evaluate two configurations of the Alpine3D distributed snow model. In the default run, the model was forced with meteorological station data. In the second run, we applied precipitation correction based on an 8 m resolution snow depth image derived from satellite observations (Pléiades). The snow depth image strongly improved the simulation of the snowpack gravity effect during the melt season. This result suggests that satellite observations can enhance SWE analyses in mountains with limited infrastructure. Plain Language Summary This study addresses the challenge of accurately computing the amount of water stored in snow (known as snow water equivalent or SWE) in mountainous areas, which is important for managing water resources. Typically, there are no tools that can measure SWE across large areas in complex high alpine surroundings, only at specific points. However, at Mt. Zugspitze at the border of Germany and Austria, a special device called a superconducting gravimeter can detect changes in gravity caused by the snow, providing a way to estimate SWE over large areas. We used data from this gravimeter to test two versions of a snow model called Alpine3D. In the first version, the model relied only on weather station data. In the second version, we improved the model by using satellite images to adjust the amount and spatial distribution of precipitation (snowfall) in the model. The results showed that the model gets more accurate by using satellite data to predict SWE changes during the melting season. This finding suggests that satellite images could be a useful tool for analyzing SWE in mountainous regions with limited infrastructure. Key Points Evaluation of a distributed physically based snow model using superconducting gravimetry in a high alpine area Precipitation scaling based on a single satellite snow depth image significantly improves the simulated gravity signal of the snowpack Accurate spatial distribution of snow depth is found to be key to simulate snow mass (SWE) evolution in complex alpine terrain

Deep learning-based image super-resolution research allows reconstruction of detailed images from low-resolution images in a short time. However, the existing depth image super-resolution reconstruction techniques focus on the reconstruction of low-resolution images with smaller downsampling multipliers, and the low-resolution images still contain richer depth information, and the superiority of super-resolution reconstruction techniques is not obvious enough. The reconstruction of depth images can be assisted by fully exploiting the rich details within the aligned 2D color images of the same scene and using the information contained internally. In this paper, we propose a network for reconstructing very low-resolution depth images with high-resolution 2D color images, mining the in-scale non-local features, cross-scale non-local features and its own priori information features of 2D color and depth images in the network. Fusing these features to greatly improve the detail accuracy of the reconstruction of very low-resolution depth images, we evaluated our method by comparing it with state-of-the-art methods comprehensively, and the experimental results demonstrate the superiority of our method.

Depth-image-based rendering (DIBR) is a commonly used method for synthesizing additional views using video-plus-depth (V+D) format. A critical issue with DIBR-based view synthesis is the lack of information behind foreground objects. This lack is manifested as disocclusions, holes, next to the foreground objects in rendered virtual views as a consequence of the virtual camera “seeing” behind the foreground object. The disocclusions are larger in the extrapolation case, i.e. the single camera case. Texture synthesis methods (inpainting methods) aim to fill these disocclusions by producing plausible texture content. However, virtual views inevitably exhibit both spatial and temporal inconsistencies at the filled disocclusion areas, depending on the scene content. In this paper, we propose a layered depth image (LDI) approach that improves the spatio-temporal consistency. In the process of LDI generation, depth information is used to classify the foreground and background in order to form a static scene sprite from a set of neighboring frames. Occlusions in the LDI are then identified and filled using inpainting, such that no disocclusions appear when the LDI data is rendered to a virtual view. In addition to the depth information, optical flow is computed to extract the stationary parts of the scene and to classify the occlusions in the inpainting process. Experimental results demonstrate that spatio-temporal inconsistencies are significantly reduced using the proposed method. Furthermore, subjective and objective qualities are improved compared to state-of-the-art reference methods.

Monocular depth estimation from Red-Green-Blue (RGB) images is a well-studied ill-posed problem in computer vision which has been investigated intensively over the past decade using Deep Learning (DL) approaches. The recent approaches for monocular depth estimation mostly rely on Convolutional Neural Networks (CNN). Estimating depth from two-dimensional images plays an important role in various applications including scene reconstruction, 3D object-detection, robotics and autonomous driving. This survey provides a comprehensive overview of this research topic including the problem representation and a short description of traditional methods for depth estimation. Relevant datasets and 13 state-of-the-art deep learning-based approaches for monocular depth estimation are reviewed, evaluated and discussed. We conclude this paper with a perspective towards future research work requiring further investigation in monocular depth estimation challenges.

Guided image super-resolution (GISR) aims to obtain a high-resolution (HR) target image by enhancing the spatial resolution of a low-resolution (LR) target image under the guidance of a HR image. However, previous model-based methods mainly take the entire image as a whole, and assume the prior distribution between the HR target image and the HR guidance image, simply ignoring many non-local common characteristics between them. To alleviate this issue, we firstly propose a maximum a posteriori (MAP) estimation model for GISR with two types of priors on the HR target image, i.e., local implicit prior and global implicit prior. The local implicit prior aims to model the complex relationship between the HR target image and the HR guidance image from a local perspective, and the global implicit prior considers the non-local auto-regression property between the two images from a global perspective. Secondly, we design a novel alternating optimization algorithm to solve this model for GISR. The algorithm is in a concise framework that facilitates to be replicated into commonly used deep network structures. Thirdly, to reduce the information loss across iterative stages, the persistent memory mechanism is introduced to augment the information representation by exploiting the Long short-term memory unit (LSTM) in the image and feature spaces. In this way, a deep network with certain interpretation and high representation ability is built. Extensive experimental results validate the superiority of our method on a variety of GISR tasks, including Pan-sharpening, depth image super-resolution, and MR image super-resolution. Code will be released at https://github.com/manman1995/pansharpening.

In current decades, significant advancements in robotics engineering and autonomous vehicles have improved the requirement for precise depth measurements. Depth estimation (DE) is a traditional task in computer vision that can be appropriately predicted by applying numerous procedures. This task is vital in disparate applications such as augmented reality and target tracking. Conventional monocular DE (MDE) procedures are based on depth cues for depth prediction. Various deep learning techniques have demonstrated their potential applications in managing and supporting the traditional ill-posed problem. The principal purpose of this paper is to represent a state-of-the-art review of the current developments in MDE based on deep learning techniques. For this goal, this paper tries to highlight the critical points of the state-of-the-art works on MDE from disparate aspects. These aspects include input data shapes and training manners such as supervised, semi-supervised, and unsupervised learning approaches in combination with applying different datasets and evaluation indicators. At last, limitations regarding the accuracy of the DL-based MDE models, computational time requirements, real-time inference, transferability, input images shape and domain adaptation, and generalization are discussed to open new directions for future research.

Computer vision applications in livestock are appealing since they enable measurement of traits of interest without the need to directly interact with the animals. This allows the possibility of multiple measurements of traits of interest with minimal animal stress. In the current study, an automated computer vision system was devised and evaluated for extraction of features of interest, as body measurements and shape descriptors, and prediction of body weight in pigs. From the 655 pigs that had data collected 580 had more than 5 frames recorded and were used for development of the predictive models. The cross-validation for the models developed with data from nursery and finishing pigs presented an R2 ranging from 0.86 (random selected image) to 0.94 (median of images truncated on the third quartile), whereas with the dataset without nursery pigs, the R2 estimates ranged from 0.70 (random selected image) to 0.84 (median of images truncated on the third quartile). However, overall the mean absolute error was lower for the models fitted without data on nursery animals. From the body measures extracted from the image, body volume, area, and length were the most informative for prediction of body weight. The inclusion of the remaining body measurements (width and heights) or shape descriptors to the model promoted significant improvement of the predictions, whereas the further inclusion of sex and line effects were not significant.

We introduce an improved solution to the neural image-based rendering problem in computer vision. Given a set of images taken from a freely moving camera at train time, the proposed approach could synthesize a realistic image of the scene from a novel viewpoint at test time. The key ideas presented in this paper are (i) Recovering accurate camera parameters via a robust pipeline from unposed day-to-day images is equally crucial in neural novel view synthesis problem; (ii) It is rather more practical to model object’s content at different resolutions since dramatic camera motion is highly likely in day-to-day unposed images. To incorporate the key ideas, we leverage the fundamentals of scene rigidity, multi-scale neural scene representation, and single-image depth prediction. Concretely, the proposed approach makes the camera parameters as learnable in a neural fields-based modeling framework. By assuming per view depth prediction is given up to scale, we constrain the relative pose between successive frames. From the relative poses, absolute camera pose estimation is modeled via a graph-neural network-based multiple motion averaging within the multi-scale neural-fields network, leading to a single loss function. Optimizing the introduced loss function provides camera intrinsic, extrinsic, and image rendering from unposed images. We demonstrate, with examples, that for a unified framework to accurately model multiscale neural scene representation from day-to-day acquired unposed multi-view images, it is equally essential to have precise camera-pose estimates within the scene representation framework. Without considering robustness measures in the camera pose estimation pipeline, modeling for multi-scale aliasing artifacts can be counterproductive. We present extensive experiments on several benchmark datasets to demonstrate the suitability of our approach.

The detection of concrete spalling is critical for tunnel inspectors to assess structural risks and guarantee the daily operation of the railway tunnel. However, traditional spalling detection methods mostly rely on visual inspection or camera images taken manually, which are inefficient and unreliable. In this study, an integrated approach based on laser intensity and depth features is proposed for the automated detection and quantification of concrete spalling. The Railway Tunnel Spalling Defects (RTSD) database, containing intensity images and depth images of the tunnel linings, is established via mobile laser scanning (MLS), and the Spalling Intensity Depurator Network (SIDNet) model is proposed for automatic extraction of the concrete spalling features. The proposed model is trained, validated and tested on the established RSTD dataset with impressive results. Comparison with several other spalling detection models shows that the proposed model performs better in terms of various indicators such as MPA (0.985) and MIoU (0.925). The extra depth information obtained from MLS allows for the accurate evaluation of the volume of detected spalling defects, which is beyond the reach of traditional methods. In addition, a triangulation mesh method is implemented to reconstruct the 3D tunnel lining model and visualize the 3D inspection results. As a result, a 3D inspection report can be outputted automatically containing quantified spalling defect information along with relevant spatial coordinates. The proposed approach has been conducted on several railway tunnels in Yunnan province, China and the experimental results have proved its validity and feasibility.

It is known that the human brain has a strong preference for rectangularity in interpreting pictures as 3D shapes. Symmetry is also considered to be a factor that the human vision system places high priority on when perceiving 3D objects. Thus, a question is raised: which is more basic, the rectangularity preference or the symmetry preference? To answer this question, we carried out experiments using pictures that have at least two interpretations as 3D objects, one of which was rectangular but not symmetric, and the other of which was symmetric but not rectangular. We found that the preference for rectangularity is stronger than that for symmetry. This observation will help us to understand various 3D optical illusions, including the room-size illusion and the ambiguous object illusion.