A Stereo Matching Algorithm Using Adaptive Window and Search Range

Satellite remote sensing can be used effectively with a wide coverage and repeatability in large-scale Arctic sea-ice analysis. To produce reliable sea-ice information, satellite remote-sensing methods should be established and validated using accurate field data, but obtaining field data on Arctic sea-ice is very difficult due to limited accessibility. In this situation, digital surface models derived from aerial images can be a good alternative to topographical field data. However, to achieve this, we should discuss an additional issue, i.e., that low-textured surfaces on sea-ice can reduce the matching accuracy of aerial images. The matching performance is dependent on the matching cost and search window size used. Therefore, in order to generate high-quality sea-ice surface models, we first need to examine the influence of matching costs and search window sizes on the matching performance on low-textured sea-ice surfaces. For this reason, in this study, we evaluate the performance of matching costs in relation to changes of the search window size, using acquired aerial images of Arctic sea-ice. The evaluation concerns three factors. The first is the robustness of matching to low-textured surfaces. Matching costs for generating sea-ice surface models should have a high discriminatory power on low-textured surfaces, even with small search windows. To evaluate this, we analyze the accuracy, uncertainty, and optimal window size in terms of template matching. The second is the robustness of positioning to low-textured surfaces. One of the purposes of image matching is to determine the positions of object points that constitute digital surface models. From this point of view, we analyze the accuracy and uncertainty in terms of positioning object points. The last is the processing speed. Since the computation complexity is also an important performance indicator, we analyze the elapsed time for each of the processing steps. The evaluation results showed that the image domain costs were more effective for low-textured surfaces than the frequency domain costs. In terms of matching robustness, the image domain costs showed a better performance, even with smaller search windows. In terms of positioning robustness, the image domain costs also performed better because of the lower uncertainty. Lastly, in terms of processing speed, the PC (phase correlation) of the frequency domain showed the best performance, but the image domain costs, except MI (mutual information), were not far behind. From the evaluation results, we concluded that, among the compared matching costs, ZNCC (zero-mean normalized cross-correlation) is the most effective for sea-ice surface model generation. In addition, we found that it is necessary to adjust search window sizes properly, according to the number of textures required for reliable image matching on sea-ice surfaces, and that various uncertainties due to low-textured surfaces should be considered to determine the positions of object points.

A new binocular stereo matching algorithm is proposed to solve the problem that the existing stereo matching algorithm is susceptible to noise and pixel mismatch and wrong matching in weak texture areas. First, set the search window and the neighborhood window, the neighborhood window slides inside the search window, compare the similarity between the neighborhood window and the Census transformation window, and determine the degree of influence of the center pixel of the neighborhood window relative to the center pixel of the transformation window according to the similarity, and assign the weight to process the gray value of the pixel. Secondly, the Sobel operator is introduced to calculate the gradient value of the image, and the texture level of the image is divided according to the gradient value. Three thresholds are set according to the texture level, and the parallax is aggregated with the cross-domain algorithm. Finally, the disparity map is optimized by the least squares fitting plane method. Experiments show that the average mismatch rate of the disparity map processed by the algorithm is 5.39% in the test of randomly selected images. Compared with other algorithms, it is more robust to noise, smoother in low-texture areas, has higher matching accuracy of disparity maps, and better optimization of disparity maps.

Comparing with search pattern motion estimation (ME) algorithms, adaptive search range (ASR) algorithms are more fundamental, regular and flexible. In variable block size motion estimation (VBSME), ASR algorithms can be applied whether on a whole frame (frame level), or on an entire macroblock which includes up to forty-one blocks (macroblock level), or just on a single block (block level). In the other hand, in H.264/AVC, not the motion vectors (MVs) but the motion vector differences (MVDs) are coded and the median motion vector predictors (median-MVPs) are used to place the search centers. In this sense, it can be thought that the search windows (SWs) are centered at the positions pointed by median-MVPs, the search ranges (SRs) play the role of limiting MVDs. Thus it is reasonable for considering using MVDs to predict SRs. In this paper, one of the MB level and two of the block level, at all three MVD based SR prediction algorithms are proposed. VBSME based experiments are carried out to assess the proposed algorithms. Comparisons between the proposed three algorithms and the previously proposed one given in [8] are done in terms of encoding quality and computational complexity.

Disparity refinement is an essential step of local stereo matching methods to produce fine dense disparity maps. The inherent defect of local stereo methods results in erroneous disparity in occluded areas. In this paper, we present a novel post processing method which can effectively improve the accuracy of dense disparity maps by rectifying disparity errors iteratively. Invalid disparities are first detected by left-right consistency check and color-disparity consistency check. For each invalid pixel, supports from valid pixels in the neighborhood are collected to determine the plane parameters of the local window. An iterative strategy is adopted to gradually propagate disparity information from valid pixels to invalid areas. We apply the proposed method to disparity maps produced by two recent stereo matching methods, and compare the refining results with other post processing methods. Experimental results show the effectiveness of our method in improving dense disparity maps.

We present a new stereo matching algorithm using epipolar geometry. The proposed algorithm does not completely rely on the fundamental matrix for the identification of the corresponding pairs. In fact, it uses epipolar geometry to locate the corresponding epipolar line in the other image in order to reduce the search space from the whole image plane to just one-dimension. A search window around the point is selected and a correlation-based matching algorithm is used to identify the corresponding points on the epipolar lines. An optimized search window size for correlation computation is also presented in the proposed algorithm. The algorithm provides more accurate results over normal stereo matching algorithms at the cost of marginal computational complexity

As-planar-as-possible depth map estimation

In this paper, we present an effective hierarchical depth processing and fusion for large stereo images. We propose the adaptive disparity search range based on the combined local structure from image and initial disparity. The adaptive search range can propagate the smoothness property at the coarse level to the fine level while preserving details and suppressing undesirable errors. The spatial-multiscale total variation method is investigated to enforce the spatial and scaling consistency of multi-scale depth estimates. The experimental results demonstrate that the proposed hierarchical scheme produces high quality and high resolution depth maps by fusing individual multi-scale depth maps, while reducing complexity.

We present a new window-based stereo matching algorithm which focuses on robust outlier rejection during aggregation. The main difficulty for window-based methods lies in determining the best window shape and size for each pixel. Working from the assumption that depth discontinuities occur at colour boundaries, we segment the reference image and consider all window pixels outside the image segment that contains the pixel under consideration as outliers and greatly reduce their weight in the aggregation process. We developed a variation on the recursive moving average implementation to keep processing times independent from window size. Together with a robust matching cost and the combination of the left and right disparity maps, this gives us a robust local algorithm that approximates the quality of global techniques without sacrificing the speed and simplicity of window-based aggregation.

Stereo vision finds a wide range of applications in automotive, object detection, robot navigation, agriculture mapping, and others. Stereo matching is a stereo algorithm targeted to identify the corresponding pixels from two or more images. This study shows the implementation of stereo matching using the Sum of Absolute Difference (SAD) algorithm to extract the object's depth or disparity from stereo images. Our key objective revolves around the implementation of the stereo matching algorithm for a small field-programmable gate array (FPGA)—requiring relatively few resources while maintaining the processing speed as well as disparity map. For meeting this requirement, we used small window buffers to compute the stereo matching. The occluded pixels were reduced by introducing secondary consistency checking implementation. From the results of experiments performed using the Zynq UltraScale+ ZCU102 FPGA board with SDSoC compiler, the processing speed for computing the stereo matching algorithm with a 4×4 window buffer was 0.038 s for an image size of 486×720 pixels and 0.051 s for 375×1242 pixels resolution. The proposed design needed 1% each of BRAM and FF and 7% of LUT. An 18% reduction in the pixel errors has been observed when employing the secondary consistency matching on the post-processing.

The stereo matching <span>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.</span>

Stereo matching is to obtain disparity map from two or more images whose pixels existing disparity between each other. Aim at the difficulty of meeting both accuracy and speed when using the adaptive support-weight algorithm, an improved adaptive support-weight sparse region-based algorithm accorded with HVS is proposed. First, improve the traditional support-weight formula, and the support-weight of the points can be calculated according to the improved support-weight formula. Second, the dense disparity map is obtained by sparse region-based matching. Third, left-right consistency check and blocking filling is performed for the obtained disparity map. Finally, median filter is used to remove isolated mismatching points and noise points. Experiment results show that, using the presented method, the matching efficiency is above 90 times faster than that of the adaptive support-weight algorithm proposed by Yoon; and the matching accuracy is 12.34% higher than that of SSD. So the improved algorithm is verified for obtaining accurate disparity map fast and meeting the requirements of system practicability.

Stereo matching is a difficult and challenging task due to many uncontrollable factors that affect the results. These factors include the non-ideal radiometric conditions and the presence of weak-textured regions. A stereo matching algorithm including cost computation, cost aggregation, disparity computation, and disparity refinement is proposed to overcome these limitations. First, census, gradient, and HSL measures are combined as the pixel-wise matching cost to reduce the radiometric distortions. Second, a second-order smoothness constraint based on angle direction priors is utilized to improve the matching accuracy in the weak-textured regions. Then, the matching cost and smoothness constraint are applied to semi-global matching. Third, a winner-takes-all strategy is adopted to calculate the initial disparity maps. Finally, a coarse-to-fine simple linear iterative clustering superpixel segmentation is proposed to split the image into some regions with similar colors, adjacent pixels, and similar disparity planes. Through the segmentation result, boundary lines are classified into occluded, hinge, and coplanar lines. Slanted plane iterative optimization is performed to obtain the optimized disparity maps according to the segmentation result and boundary lines classification. The algorithm is evaluated in the Middlebury and KITTI datasets. The experimental results show that the method has good performance under non-ideal radiometric conditions and in the weak-textured regions. The disparity maps obtained by the method have a lower mismatching rate compared with other algorithms.

Depth information can be obtained using stereo matching algorithms, which compute the horizontal displacement (disparity) of the corresponding points and convert to depth information using the triangular relation. However, the matching process is challenging with presence of textureless regions. This paper proposes a novel disparity refinement method for stereo matching based on Semi-global Matching (SGM) algorithm for texture less images. To be brief, the SGM algorithm is a high-performance matching algorithm of a stereo image pair and it reaches a trade off between matching quality and computing complexity. The main contribution comes from the improvement of matching quality on texture less regions. At the end of SGM, a right-to-left consistency check is performed to remove the invalid pixels in the disparity map. The proposed method is added after the right-to-left consistent check. We assume that the texture less regions in the original stereo pairs are planar. We employ edge detection to extract the textureless regions. The fitting method is employed in horizontal and vertical directions respectively. If the distance of two adjacent edge pixels is sufficiently large, the corresponding line segment will be considered as texturelss. For every texturelss line segment, the RANSAC algorithm is performed on the corresponding line segment in the disparity map. We use the well-known Middlebury dataset to compare our method with the normal SGM and other matching algorithms. It shows that our method performs well for most texture less stereo pairs.

Innovative applications in rapidly evolving domains such as robotic navigation and autonomous (driverless) vehicles rely on binocular computer vision systems that meet stringent response time and accuracy requirements. A key problem in these vision systems is stereo matching, which involves matching pixels from two input images in order to construct the output, a 3D map. Building upon the existing local stereo matching algorithms, this paper proposes a novel stereo matching algorithm that is based on a weighted guided filtering foundation. The proposed algorithm consists of three main steps; each step is designed with the goal of improving accuracy. First, the matching costs are computed using a unique combination of complementary methods (absolute difference, Census, and gradient algorithms) to reduce errors. Second, the costs are aggregated using an adaptive weighted guided image filtering method. Here, the regularization parameters are adjusted adaptively using the Canny method, further reducing errors. Third, a disparity map is generated using the winner-take-all strategy; this map is subsequently refined using a densification method to reduce errors. Our experimental results indicate that the proposed algorithm provides a higher level of accuracy in comparison to a collection of the existing state-of-the-art local algorithms.

Stereo vision is used in many application areas, such as robot-assisted manufacturing processes. Recently, many different efficient stereo matching algorithms based on deep learning have been developed to solve the limitations of traditional correspondence point analysis, among others. The challenges include texture-poor objects or non-cooperative objects. One of these end-to-end learning algorithms is the Adaptive Aggregation Network (AANet/AANet+), which is divided into five steps: feature extraction, cost volume construction, cost aggregation, disparity computation and disparity refinement. By combining different components, it is easy to create an individual stereo matching model. Our goal is to develop efficient learning methods for robot-assisted manufacturing processes for cross-domain data streams. The aim is to improve recognition tasks and process optimisation. To achieve this, we have investigated the AANet+ in terms of usability and efficiency on our own test-dataset with different measurement setups (passive stereo system). Input of the AANet+ are rectified stereo pairs of the test-dataset and a pre-trained model. Instead of generating our own training dataset, we used two pre-trained models based on the KITTI-2015 and SceneFlow datasets. Our research has shown that the pretrained model based on the Scene Flow dataset predicts disparities with better object delimination. Due to the Out-of-Distribution inputs, only reliable disparity predictions of the AANet are possible for test data sets with parallel measurement setup. We compared the results with two traditional stereo matching algorithms (SemiGlobal block matching and DAISY). Compared to the traditionally computed disparity maps, the AANet+ is able to robustly detect texture-poor objects and optically non-cooperative objects.