Matching Cost Research Articles

CNN-Based Fluid Motion Estimation Using Correlation Coefficient and Multiscale Cost Volume

Motion estimation for complex fluid flows via their image sequences is a challenging issue in computer vision. It plays a significant role in scientific research and engineering applications related to meteorology, oceanography, and fluid mechanics. In this paper, we introduce a novel convolutional neural network (CNN)-based motion estimator for complex fluid flows using multiscale cost volume. It uses correlation coefficients as the matching costs, which can improve the accuracy of motion estimation by enhancing the discrimination of the feature matching and overcoming the feature distortions caused by the changes of fluid shapes and illuminations. Specifically, it first generates sparse seeds by a feature extraction network. A correlation pyramid is then constructed for all pairs of sparse seeds, and the predicted matches are iteratively updated through a recurrent neural network, which lookups a multi-scale cost volume from a correlation pyramid via a multi-scale search scheme. Then it uses the searched multi-scale cost volume, the current matches, and the context features as the input features to correlate the predicted matches. Since the multi-scale cost volume contains motion information for both large and small displacements, it can recover small-scale motion structures. However, the predicted matches are sparse, so the final flow field is computed by performing a CNN-based interpolation for these sparse matches. The experimental results show that our method significantly outperforms the current motion estimators in capturing different motion patterns in complex fluid flows, especially in recovering some small-scale vortices. It also achieves state-of-the-art evaluation results on the public fluid datasets and successfully captures the storms in Jupiter’s White Ovals from the remote sensing images.

Online Bottleneck Matching Problem with Two Heterogeneous Sensors in a Metric Space

In this paper, we consider the online matching problem with two heterogeneous sensors s1 and s2 in a metric space (X,d). If a request r is assigned to sensor s1, the service cost of r is the distance d(r,s1). Otherwise, r is assigned to sensor s2, and the service cost of r is d(r,s2)w, where w≥1 is the weight of sensor s2. The goal is to minimize the maximum matching cost, we design an optimal online algorithm with a competitive ratio of 1+w+1w for 1≤w≤1.839, and an optimal online algorithm with a competitive ratio of w+1+w2+6w+12 for w>1.839.

How the Quadruple Aim Widens the Lens on the Transition to Residency.

How the Quadruple Aim Widens the Lens on the Transition to Residency.

Key features of the development of measures to create and increase the competitiveness of a football club

In this article, the author develops a business plan for a football club. To achieve this goal, the author analyzes the role of football in the modern world. According to the author, the opening of a football club can have a positive impact not only on the development of sports, but also on the interest of young people in football. In addition, the article examines the state of the sports market and analyzes the external environment. The author highlights a list of consistent actions that must be carried out for the successful development of a football club. Also, special attention is paid to the legal aspects of creating a club, in particular, its registration and preparation of the necessary documentation. An equally important aspect, according to the author, is the choice of a football structure in which the club's players will participate. The duration of the project is on average about a year. The article defines a number of goals that the club must achieve over this period of time. Further, the author studies in detail the issue of choosing the playing field. They study different options and select the most optimal one for a club that is just starting its activity. Then the article provides fairly detailed calculations of the costs required to implement the project. In particular, the author calculates the amount of initial investment required for the implementation of the project, the cost of tickets for the match, sales volumes, and material costs are calculated. In addition, the author pays attention to the issue of staff selection: its number, wages. Separately, the author considers the costs of the club and the expected income. Based on the above calculations, the author formulates conclusions regarding the effectiveness of the football club.

Omni-Directional Semi-Global Stereo Matching with Reliable Information Propagation

High efficiency and accuracy of semi-global matching (SGM) make it widely used in many stereo vision applications. However, SGM not only struggles in dealing with pixels in homogeneous area, but also suffers from streak artifacts. In this paper, we propose a novel omni-directional SGM (OmniSGM) with a cost volume update scheme to aggregate costs from paths along all directions and to encourage reliable information to propagate across entire image. Specifically, we perform SGM along four tree structures, namely trees in the left, right, top and bottom of root node, and then fuse the outputs to obtain final result. The contributions of pixels on each tree can be recursively computed from leaf nodes to root node, ensuring our method has linear time computational complexity. Moreover, An iterative cost volume update scheme is proposed using aggregated cost in the last pass to enhance the robustness of initial matching cost. Thus, useful information is more likely to propagate in a long distance to handle the ambiguities in low textural area. Finally, we present an efficient strategy to propagate disparities of stable pixels along the minimum spanning tree (MST) for disparity refinement. Extensive experiments in stereo matching on Middlebury and KITTI datasets demonstrate that our method outperforms typical traditional SGM-based cost aggregation methods.

Fast Shape Recognition Method Using Feature Richness Based on the Walking Minimum Bounding Rectangle over an Occluded Remote Sensing Target

Remote sensing target recognition has always been an important topic of image analysis, which has significant practical value in computer vision. However, remote sensing targets may be largely occluded by obstacles due to the long acquisition distance, which greatly increases the difficulty of recognition. Shape, as an important feature of a remote sensing target, plays an important role in remote sensing target recognition. In this paper, an occluded shape recognition method based on the local contour strong feature richness (contour pixel richness, contour orientation richness, and contour distance richness) to the walking minimum bounding rectangle (MBR) is proposed for the occluded remote sensing target (FEW). The method first obtains the local contour feature richness by using the walking MBR; it is a simple constant vector, which greatly reduces the cost of feature matching and increases the speed of recognition. In addition, this paper introduces the new concept of strong feature richness and uses the new strategy of constraint reduction to reduce the complex structure of shape features, which also speeds up the recognition speed. Validation on a self-built remote sensing target shape dataset and three general shape datasets demonstrate the sophisticated performance of the proposed method. FEW in this paper has both higher recognition accuracy and extremely fast recognition speed (less than 1 ms), which lays a more powerful theoretical support for the recognition of occluded remote sensing targets.

Transformer Based Binocular Disparity Prediction with Occlusion Predict and Novel Full Connection Layers.

The depth estimation algorithm based on the convolutional neural network has many limitations and defects by constructing matching cost volume to calculate the disparity: using a limited disparity range, the authentic disparity beyond the predetermined range can not be acquired; Besides, the matching process lacks constraints on occlusion and matching uniqueness; Also, as a local feature extractor, a convolutional neural network lacks the ability of global context information perception. Aiming at the problems in the matching method of constructing matching cost volume, we propose a disparity prediction algorithm based on Transformer, which specifically comprises the Swin-SPP module for feature extraction based on Swin Transformer, Transformer disparity matching network based on self-attention and cross-attention mechanism, and occlusion prediction sub-network. In addition, we propose a double skip connection fully connected layer to solve the problems of gradient vanishing and explosion during the training process for the Transformer model, thus further enhancing inference accuracy. The proposed model in this paper achieved an EPE (Absolute error) of 0.57 and 0.61, and a 3PE (Percentage error greater than 3 px) of 1.74% and 1.56% on KITTI 2012 and KITTI 2015 datasets, respectively, with an inference time of 0.46 s and parameters as low as only 2.6 M, showing great advantages compared with other algorithms in various evaluation metrics.

Estimation and Propagation: Scene Flow Prediction on Occluded Point Clouds

With the development of 3D sensors, estimating the point movements between two consecutive point clouds is becoming increasingly attractive. Using correlation-based deep neural networks, existing solutions achieve promising performance. However, these methods couple the non-occluded points and occluded points into the same cost volume and attempt to regress the scene flows of the occluded points from those invalid matching costs directly, which severely suppress the performance of the flow predictor. As an alternative to previous scene flow estimation methods, our method adopts a subnet to predict the occlusion mask and explicitly masks those occluded points, which ensures our flow predictor to focus on estimating the motion flows of non-occluded points from those valid matching costs. Moreover, we further improve the flow estimation performance by employing a local-adaptive cost volume, which can deal with the local structure dissimilarity induced by the sparse sampling of depth sensors (LiDAR). For occluded points, we design an uncertainties-truncated propagation network to propagate the flows of non-occluded to those occluded points. We demonstrate the effectiveness of the proposed method by quantitative and qualitative comparisons with recent baseline works on the FlyingThings3D dataset and the KITTI 2015 dataset, and our results surpass all competing methods by a large margin.

Generalized LOAM: LiDAR Odometry Estimation With Trainable Local Geometric Features

This letter presents a LiDAR odometry estimation framework called Generalized LOAM. Our proposed method is generalized in that it can seamlessly fuse various local geometric shapes around points to improve the position estimation accuracy compared to the conventional LiDAR odometry and mapping (LOAM) method. To utilize continuous geometric features for LiDAR odometry estimation, we incorporate tiny neural networks into a generalized iterative closest point (GICP) algorithm. These neural networks improve the data association metric and the matching cost function using local geometric features. Experiments with the KITTI benchmark demonstrate that our proposed method reduces relative trajectory errors compared to the other LiDAR odometry estimation methods.

Three-Dimensional Reconstruction of Shoe Soles via Binocular Vision Based on Improved Matching Cost

Aiming at the problem that the toe cap and upper part of the sole of a shoe easily appear missing when using binocular vision to reconstruct the shoe sole in the industrial production process, an improved matching cost calculation method is proposed to reconstruct shoe soles in three dimensions. Firstly, a binocular vision platform is built, and Zhang’s calibration method is used to obtain the calibration parameters. Secondly, the method of fusing Census and BT costs is used to calculate the matching cost of the image, so that the matching cost calculation result is more accurate. On this basis, 4-path aggregation is performed on the obtained cost, and the optimal matching cost is selected in combination with the WTA algorithm. Finally, left–right consistency detection and median filtering are used to optimize the disparity map and combine the camera calibration parameters to reconstruct the shoe sole in three dimensions. The experimental results show that the average mismatch rate of the four images on the Middlebury website in this method is about 6.57%, the reconstructed sole point cloud contour information is complete, and there is no material missing at the toe and heel.

LANet: Stereo matching network based on linear-attention mechanism for depth estimation optimization in 3D reconstruction of inter-forest scene.

The 3D reconstruction of forests provides a strong basis for scientific regulation of tree growth and fine survey of forest resources. Depth estimation is the key to the 3D reconstruction of inter-forest scene, which directly determines the effect of digital stereo reproduction. In order to solve the problem that the existing stereo matching methods lack the ability to use environmental information to find the consistency of ill-posed regions, resulting in poor matching effect in regions with weak texture, occlusion and other inconspicuous features, LANet, a stereo matching network based on Linear-Attention mechanism is proposed, which improves the stereo matching accuracy by effectively utilizing the global and local information of the environment, thereby optimizing the depth estimation effect. An AM attention module including a spatial attention module (SAM) and a channel attention module (CAM) is designed to model the semantic relevance of inter-forest scenes from the spatial and channel dimensions. The linear-attention mechanism proposed in SAM reduces the overall complexity of Self-Attention from O(n2) to O(n), and selectively aggregates the features of each position by weighted summation of all positions, so as to learn rich contextual relations to capture long-range dependencies. The Self-Attention mechanism used in CAM selectively emphasizes interdependent channel maps by learning the associated features between different channels. A 3D CNN module is optimized to adjust the matching cost volume by combining multiple stacked hourglass networks with intermediate supervision, which further improves the speed of the model while reducing the cost of inferential calculation. The proposed LANet is tested on the SceneFlow dataset with EPE of 0.82 and three-pixel-error of 2.31%, and tested on the Forest dataset with EPE of 0.68 and D1-all of 2.15% both of which outperform some state-of-the-art methods, and the comprehensive performance is very competitive. LANet can obtain high-precision disparity values of the inter-forest scene, which can be converted to obtain depth information, thus providing key data for high-quality 3D reconstruction of the forest.

Medical residency match applicants undervalue factors that predict stress and burnout

ABSTRACT In the medical residency match process, applicants’ ranking decisions are influenced by multiple factors related to training, geography, and lifestyle expectations. Ranking decisions directly impact match results, with implications for emotional outcomes such as happiness and stress. The present study explored the decision factors considered most important by applicants when creating rank order lists (ROLs), and how match outcomes and program factors predicted happiness, enthusiasm, stress, and life satisfaction. Senior medical students (n = 182) at a large public university in California completed surveys at three timepoints, spanning from shortly before Match Day to several months into PGY-1. Study findings support that both program-related (e.g., training quality, program size) and non-program-related (e.g., geography, work life balance) factors are important to applicants when making ROL decisions. Applicants who matched with their top choice program initially experienced emotional benefits, but these emotional differences did not persist into PGY-1, where all matched applicants had similar levels of emotion and life satisfaction. The emotional cost and benefits of matching with programs of different ROL positions (e.g., matching with top-choice program or not) were most apparent shortly after matching but in the long-term, a stronger predictor of PGY-1 emotions was perceived person-program alignment. Person-program alignment (e.g., call schedule, patient caseload) also predicted burnout in the first few months of a residency program. These findings show that, when applicants are making ranking decisions, they undervalue factors that predict stress and burnout during residency.

Small Candidate Set for Translational Pattern Search

In this paper, we study the following pattern search problem: Given a pair of point sets A and B in fixed dimensional space \(\mathbb {R}^d\), with \(|B| = n,|A| = m\) and \(n \ge m\), the pattern search problem is to find the translations \(\mathcal {T}\)’s of A such that each of the identified translations induces a matching between \(\mathcal {T}(A)\) and a subset \(B'\) of B with cost no more than some given threshold, where the cost is defined as the minimum bipartite matching cost of \(\mathcal {T}(A)\) and \(B'\). We present a novel algorithm to produce a small set of candidate translations for the pattern search problem. For any \(B' \subseteq B\) with \(|B'| = |A|\), there exists at least one translation \(\mathcal {T}\) in the candidate set such that the minimum bipartite matching cost between \(\mathcal {T}(A)\) and \(B'\) is no larger than \((1+\epsilon )\) times the minimum bipartite matching cost between A and \(B'\) under any translation (i.e., the optimal translational matching cost). We also show that there exists an alternative solution to this problem, which constructs a candidate set of size \(O_{d,\epsilon }(n \log ^2 n)\) in \(O_{d,\epsilon }(n \log ^2 n)\) time with high probability of success. As a by-product of our construction, we obtain a weak \(\epsilon \)-net for hypercube ranges, which significantly improves the construction time and the size of the candidate set. Our technique can be applied to a number of applications, including the translational pattern matching problem.

SPNet: Learning Stereo Matching With Slanted Plane Aggregation

Matching cost aggregation plays a critical role for the stereo matching task. Existing CNN-based methods commonly use 3D convolutions to aggregate matching costs from a local 3D space. However, the high computational cost of 3D convolutions limits their applications. Traditional methods show that a slanted support window in 3D space can help to aggregate matching costs from informative regions, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.,</i> the surfaces of objects. Motivated by this idea, we propose a SPNet with differentiable slanted plane aggregation. Our slanted plane aggregation layers aggregate matching costs from a learnable slanted plane in a local 3D space to reduce computational and memory costs. Experimental results show that our slanted plane aggregation layers can learn to fit the surfaces of objects and effectively aggregate matching costs. Comparison with previous stereo matching methods shows that our network achieves competitive performance with higher efficiency.

Leveraging Local Planar Motion Property for Robust Visual Matching and Localization

One primary difficulty preventing the visual localization for service robots is the robustness against changes, including environmental changes and perspective changes. In recent years, learning-based feature matching methods have been widely studied and effectively verified in practical applications. Learning-based feature matching effectively solves the problem of environmental changes, including illumination changes and man-made changes. However, there is still room for improvement dealing with large perspective changes. In this letter, we leverage local planar motion property to simplify the affine transform and propose an augmentation-based feature matching method that greatly enhances the robustness to perspective changes. The proposed feature matching approach maintains low matching costs as the augmentation is performed on the simplified affine matrix space. Combined with the motion property aided minimal solution for pose estimation, an end-to-end robust visual localization system is proposed which is shown to bring 67% improvement in localization performance under large perspective changes in publicly available OpenLORIS dataset, while increasing computational cost by only 20% by using batch processing techniques with a single GPU. In addition, a guide for map frame selection is presented to support robust localization with very sparse map frames in storage. Experiments on the classified dataset with environmental changes and perspective changes validate the effectiveness of the proposed system.

Detailed Facial Geometry Recovery from Multi-View Images by Learning an Implicit Function

Recovering detailed facial geometry from a set of calibrated multi-view images is valuable for its wide range of applications. Traditional multi-view stereo (MVS) methods adopt an optimization-based scheme to regularize the matching cost. Recently, learning-based methods integrate all these into an end-to-end neural network and show superiority of efficiency. In this paper, we propose a novel architecture to recover extremely detailed 3D faces within dozens of seconds. Unlike previous learning-based methods that regularize the cost volume via 3D CNN, we propose to learn an implicit function for regressing the matching cost. By fitting a 3D morphable model from multi-view images, the features of multiple images are extracted and aggregated in the mesh-attached UV space, which makes the implicit function more effective in recovering detailed facial shape. Our method outperforms SOTA learning-based MVS in accuracy by a large margin on the FaceScape dataset. The code and data are released in https://github.com/zhuhao-nju/mvfr.

Stereo matching algorithm based on combined matching cost computation and edge preserving filters

The stereo matching &lt;span&gt;process is one of the key areas that impact the stereo vision technologies which are commonly used in the application of three-dimensional reconstructions. The accuracy of the depth information used in three-dimensional reconstruction is directly proportional to the accuracy of the disparity obtained from stereo matching. The challenging issue in the stereo matching process is to determine the accurate corresponding point between the left image and right image, especially for image pairs that have different exposure such as different illumination and image pair with less texture region. In order to increase the accuracy of disparity value, a new stereo matching algorithm is proposed based on the combination of Sum of absolute different and census transform at matching cost computation. guided filter was used in the matching cost aggregation in order to remove noise and preserve the edge of the image. In the optimization step, the winner take all strategy is used to select the minimum matching cost. Finally, a median filter is applied to the initial disparity map for refinement purposes. The experimental results show that the algorithm is effective in reducing the error and improving the accuracy of the disparity map in different illumination regions, less textured regions and different environmental exposure.&lt;/span&gt;

Symmetry Weight-sharing for Patch-based Stereo Matching

Neural networks are becoming more popular than traditional methods in stereo matching. The networks can be decomposed into four sub-modules: feature extraction / matching cost computation, cost aggregation, disparity computation / optimization, and disparity refinement. A typical design for the feature extraction networks is that the left and right branches share the same weights. However, the Siamese networks are weak at distinguishing neighboring patches because of the interference of geometric distortion on slanted surfaces. This paper proposes symmetry weight-sharing to improve the feature extraction networks. The geometry of feature extraction and patch comparison has been analyzed, which shows that symmetry weight-sharing can fulfill the geometry on slanted surfaces. A half-translation module is proposed to implement symmetry weight-sharing without additional computational costs. Experiments on the KITTI 2012 and KITTI 2015 datasets show that the symmetry weight-sharing networks have better performance than the weight-sharing networks.

Binocular Images Dense Matching considering Image Adaptive Color Weights and Feature Points

When the matching cost function in Semiglobal Matching is unstable, the inaccurate matching cost values will be propagated in the cost aggregation process. It will lead to a serious mismatching phenomenon. To address the problem, a binocular images dense matching method considering image adaptive color weights and feature points was proposed. Firstly, The Color Birchfield Tomasi (CBT) matching cost calculation method was proposed to obtain a stable initial cost volume, which combined image adaptive color weights and gradient information. Secondly, the Scale-invariant Feature Transform matching algorithm was used to extract the a priori feature points from binocular images. Then, the feature points were filtrated. The cost volume was optimized by using their coordinate information and disparity information. Finally, an aggregation path segmentation rectification method was adopted to optimize the SGM aggregation paths and reduce the propagation of incorrect paths. Experimental results demonstrate that the proposed method can effectively improve the stability and accuracy of dense matching, reduce the mismatching phenomenon, and finally produce high-quality disparity maps.

House Price Markups and Mortgage Defaults

AbstractThe transaction price of identical housing units can vary widely due to heterogeneity in buyer and seller preferences, matching, and search costs, generating what we term “markups” above or below the average market price. We measure markups for 3.4 million purchase‐money mortgages and show that they can predict mortgage defaults and credit losses conditional on default even after accounting for collateral coverage (loan‐to‐value ratio) and a comprehensive set of other covariates. The findings suggest that standard collateral coverage estimation may be inaccurate, with implications for both individual and portfolio‐level credit risk assessment.