Stereo Image Pairs Research Articles

Estimation of Gully Growth Rate and Erosion Amount Using UAV and Worldview-3 Images in Yimeng Mountain Area, China

Non-homogeneous soil’s high gravel content (also known as the “soil-rock dual structure”) may render it more prone to erosion and the significant development of gullies. In order to reveal the morphological characteristics and erosion rate of gullies in “soil-rock dual structure” areas, this study focused on the Shagou Reservoir basin in the Yimeng mountain area as the study area. Based on a complete digital orthophoto map (DOM, 0.03 m) and a digital elevation model (DEM, 0.03 m) acquired by an unmanned aerial vehicle (UAV), the researchers calculated the length (L), top width (TW), depth (D), area (A) and volume (V) of 19 gullies and built and optimized the volume estimation model. The DOM and the DEM were used to modify the morphological parameters of 43 gullies extracted from high-resolution remote sensing (RS) stereopair images (Worldview, 0.5 m), and the development and evolution of gully erosion were evaluated in large scale. The results showed that: (1) after correction, the average relative errors of parameters L, TW, D and A computed from the UAV data and the high-resolution RS stereopair image data fell below 0.005%; (2) the mean of TW/D was 5.20, i.e., the lateral erosion development of gullies far outweighed the downcutting erosion. The retrogressive erosion, lateral erosion and downcutting erosion rates of gullies were 0.01~0.83 m/a (averaged at 0.23 m/a), 0.01~0.68 m/a (averaged at 0.25 m/a) and 0.01~0.19 m/a (averaged at 0.09 m/a), respectively, between 2014 and 2021; (3) the volume-area (V-A) model for gullies is the optimal one (p < 0.01, R2 = 0.944).A total of 90.7% of the gully volume was growing at an erosion rate of 0.42~399.39 m³/a and the total erosion rate of the gullies was 3181.56 m3/a from 2014 to 2021. These research findings can serve as a basis for the quantitative modeling of gully erosion in water-eroded locations with a large-dimension “soil-rock dual structure”.

DSM Generation from Multi-View High-Resolution Satellite Images Based on the Photometric Mesh Refinement Method

Automatic reconstruction of DSMs from satellite images is a hot issue in the field of photogrammetry. Nowadays, most state-of-the-art pipelines produce 2.5D products. In order to solve some shortcomings of traditional algorithms and expand the means of updating digital surface models, a DSM generation method based on variational mesh refinement of satellite stereo image pairs to recover 3D surfaces from coarse input is proposed. Specifically, the initial coarse mesh is constructed first and the geometric features of the generated 3D mesh model are then optimized by using the information of the original images, while the 3D mesh subdivision is constrained by combining the image’s texture information and projection information, with subdivision optimization of the mesh model finally achieved. The results of this method are compared qualitatively and quantitatively with those of the commercial software PCI and the SGM method. The experimental results show that the generated 3D digital surface has clearer edge contours, more refined planar textures, and sufficient model accuracy to match well with the actual conditions of the ground surface, proving the effectiveness of the method. The method is advantageous for conducting research on true 3D products in complex urban areas and can generate complete DSM products with the input of rough meshes, thus indicating it has some development prospects.

ГЕОДЕЗІЯ, КАРТОГРАФІЯ І АЕРОФОТОЗНІМАННЯ

The purpose of the work is to investigate the digital elevation models of the mass grave of 1944, built on the basis of aerial and cartographic data of different times. The implementation of the task involves the construction of digital elevation models (DEM) on the territory of the Jewish mass grave in the city of Vynnyky and Italian prisoners of war near the city. On the territory of the Jewish mass grave in the city of Vynnyky, a DEM was created based on a stereo pair of archival aerial images obtained in 1944 and on the basis of aerial photography from a UAV conducted in 2015. Since archival aerial photographs did not contain orientation elements, they were geometrically transformed using the ErdasImagine software. After that, the stereo pair was processed in the program Digitals, where relief elements on the territory of the mass grave were obtained. Aerial photography from a UAV on the territory of the city of Vynnyky provided the data which was processed in the Agisoft PhotoScan software. It allowed us to create an orthophoto plan and an elevation map of the city territory. Elements of relief on the territory of the mass grave of 1944 and 2015 were imported into the Surfer software environment, where 3D digital elevation models were built. Since the territory of the grave did not have significant differences in height, and the relief was quite gentle, the method of constructing the DEM of the Natural Neighbor was chosen, which gave a positive result. Analyzing the digital elevation model and the vector map for 1944, the border of the mass grave is clearly distinguished, since the height difference between its edges and the rest of the territory is from 20 to 36 cm, depending on the section of the border. The analysis of the digital elevation models and the vector map for 2015 of the territory of the mass grave determined from the aerial image of 1944 showed that the characteristic height differences on the former border of the grave are observed only in the left-right corner of the grave and on a separate section of the right border. Height difference indicators range from 15 to 20 cm. It should be noted that height differences are also observed in the rest of the territory belonging to the mass grave and outside it. This can be explained by many years of human intervention and agricultural land use. With regard to the investigation of the mass graves of Italian prisoners of war near the city of Vynnyky, the modern territory is 100% wooded, which makes it impossible to apply aerial photography. Therefore, in order to compare the modern DEM with the stereo pair of aerial images of 1944, it was decided to conduct a ground tacheometric survey of the area in 2011. Tacheometric survey data was exported to the dxf exchange format, after which it was opened in Surfer and the DEM was built. In this case, digital elevation models were built using the Kriging method, since the area where the mass graves are located is quite hilly with a significant difference in elevation. According to the digital elevation models, 54 pits with burials that have survived to this day have been identified. The scientific novelty of the work consists in the development of the concept of combining disparate data for the construction of digital elevation models and the creation of a complete picture of the study of the territory of the object of historical and cultural heritage. The received data can be used by the relevant cultural heritage preservation departments of the Ministry of Culture of Ukraine for their further study.

Deep Progressive Fusion Stereo Network

Stereo matching depth estimation for rectified image pairs is of great importance to many compute vision tasks, specifically in autonomous driving. With the flourishing of convolution neural networks, responsible depth estimation of stereo matching with artificial intelligence is the most severe challenge for autonomous driving in recent years. Previous research on end-to-end trainable stereo matching networks has usually used cascading convolution blocks with down-sampling or pooling operations to extract the unary features required for matching cost construction. Such approaches lack a reconstruction stage for increasing feature map pixel-wise alignment and strength, factors which play an important role in representing the similarity between stereo image pairs. To address this issue, in this paper, we propose the progressive fusion stereo matching network (PFSM-Net). We exploit an encoder-decoder feature extraction network architecture for multi-stage and -scale dynamic feature extraction. Moreover, we propose a group-wise concatenation method to construct the cost volume, which provides a more efficient cost volume for cost aggregation. Furthermore, we propose the use of multi-scale cost aggregation networks with a progressive fusion strategy. The aggregated cost volume is progressively fused with the multi-stage and -scale cost volume as the size of the cost volume increases. Multi-stage and -scale outputs are supervised with and learned in a coarse-to-fine manner. Experimental results demonstrate that our method outperforms previous methods on the SceneFlow, KITTI 2012, and KITTI 2015 datasets.

Stereo Image Matching Using Adaptive Morphological Correlation.

A stereo matching method based on adaptive morphological correlation is presented. The point correspondences of an input pair of stereo images are determined by matching locally adaptive image windows using the suggested morphological correlation that is optimal with respect to an introduced binary dissimilarity-to-matching ratio criterion. The proposed method is capable of determining the point correspondences in homogeneous image regions and at the edges of scene objects of input stereo images with high accuracy. Furthermore, unknown correspondences of occluded and not matched points in the scene can be successfully recovered using a simple proposed post-processing. The performance of the proposed method is exhaustively tested for stereo matching in terms of objective measures using known database images. In addition, the obtained results are discussed and compared with those of two similar state-of-the-art methods.

Visual Method of Pipeline Detection by an Autonomous Underwater Vehicle using a Stereo Camera

This paper describes a method for searching and recognizing extended underwater communication using a stereo camera mounted on an autonomous uninhabited underwater vehicle (AUV). The output data is a list of coordinates in three-dimensional space. The method uses a pair of stereo images as input data. The method uses stereo images to create a dense depth map and a map of height differences, with the help of which extended structures are detected. The problem of filtering the interference present on the seabed is also solved by screening out objects whose size does not correspond to the expected size of the pipeline. The algorithm calculates the coordinates of the selected point on a two-dimensional image and projects it into three-dimensional space. Thus, the algorithm gets the coordinates of the point through which the pipeline build. The objectives of the work are: description of the method, setting up an experiment on a virtual model, description of the experiment and its results. The paper presents a step-by-step method for solving the problem, presents the results of an experiment set on a virtual model. The algorithm confidently determined the selected pipe in clean areas, and areas with interference having a height greater than the pipeline. As a result, a list of coordinates is obtained through which the virtual pipeline runs. Further development and improvement of the developed method is possible

Evaluating automated benthic fish detection under variable conditions

Abstract Advances in imaging systems have facilitated the collection of high-volume imagery datasets in fisheries science. To alleviate the costs of sorting these datasets, automated image processing techniques are used. In this study, we investigate a machine learning-enabled imaging technique for automating individual fish detection from stereo image pairs of orange roughy (Hoplostethus atlanticus). We performed a set of object detection experiments to investigate how well a Single Shot Multi-Box Detector (SSD) model worked under dynamic real-world conditions when trained over a small number of epochs. We tested model generalization between the port and starboard side cameras; at variable fish densities; different benthic substrates; and at different altitudes above the seafloor. We show that (1) changes in perspective between starboard and port images are not enough to break the object detector, (2) the object detector begins to have trouble differentiating individuals at high fish densities (>20 fish per image), (3) substrate type does not affect model performance, and (4) altitude is not a major factor contributing to model error. Ideally, this type of real-world dataset exploration should be performed prior to committing the resources to train the final object detector over several hundred epochs.

A novel factor graph-based optimization technique for stereo correspondence estimation

Dense disparities among multiple views are essential for estimating the 3D architecture of a scene based on the geometrical relationship between the scene and the views or cameras. Scenes with larger extents of homogeneous textures, differing scene illumination among the multiple views and with occluding objects affect the accuracy of the estimated disparities. Markov random fields based methods for disparity estimation address these limitations using spatial dependencies among the observations and among the disparity estimates. These methods, however, are limited by spatially fixed and smaller neighborhood systems or cliques. Recent learning-based methods generate rich set of stereo features for generating cost volume and estimating disparity. In this work, we present a new factor graph-based probabilistic graphical model for disparity estimation that allows a larger and a spatially variable neighborhood structure determined based on the local scene characteristics. Our algorithm improves the accuracy of disparity estimates in stereo image pairs with varying texture and illumination characteristics by enforcing spatial dependencies among scene characteristics as well as among disparity estimates. We evaluated our method using the Middlebury benchmark stereo datasets and the Middlebury evaluation dataset version 3.0 and compared its performance with recent state-of-the-art disparity estimation algorithms. Our factor graph-based algorithm provided disparity estimates with higher accuracy when compared to the recent non-learning- and learning-based disparity estimation algorithms. The factor graph formulation can be used for obtaining maximum a posteriori estimates from models or optimization problems with complex dependency structure among hidden variables. The strategies of using a priori distributions with shorter support and spatial dependencies were useful for reducing the computational cost and improving message convergence in the model. The factor-graph algorithm is also useful for other dense estimation problems such as optical flow estimation.

Adaptive Modulation and Rectangular Convolutional Network for Stereo Image Super-Resolution

• We propose a novel network for better stereo image super-resolution. • We propose an adaptive modulation alignment mechanism to modulate the aligned features. • We add rectangular convolutional layers to expand the receptive field along the disparity epipolar line . • Experimental results show that our method outperforms other state-of-the-art methods on the three stereo benchmarks. Deep learning based stereo image super-resolution algorithm can make use of the additional information in the stereo image pairs to improve the quality of the reconstructed images. However, extracting the similarity information of one image to another precisely is challenging when partially occluded regions exist in stereo images. In this paper, we propose an adaptive modulation alignment mechanism to modulate the aligned features calculated from the parallax attention mechanism and effectively deal with the inaccuracy caused by occlusion. Furthermore, because disparities of stereo image exist only along the epipolar line, we use rectangular convolution kernel in some convolution layers , to extend the receptive field horizontally. Finally, experimental results demonstrate that our method achieves state-of-the-art performance on the Middlebury, KITTI 2012 and KITTI 2015 stereo benchmarks.

Deep Image Deblurring: A Survey

Image deblurring is a classic problem in low-level computer vision with the aim to recover a sharp image from a blurred input image. Advances in deep learning have led to significant progress in solving this problem, and a large number of deblurring networks have been proposed. This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aiming to serve the community as a useful literature review. We start by discussing common causes of image blur, introduce benchmark datasets and performance metrics, and summarize different problem formulations. Next, we present a taxonomy of methods using convolutional neural networks (CNN) based on architecture, loss function, and application, offering a detailed review and comparison. In addition, we discuss some domain-specific deblurring applications including face images, text, and stereo image pairs. We conclude by discussing key challenges and future research directions.

Encoder-Decoder Structure with Multiscale Receptive Field Block for Unsupervised Depth Estimation from Monocular Video

Monocular depth estimation is a fundamental yet challenging task in computer vision as depth information will be lost when 3D scenes are mapped to 2D images. Although deep learning-based methods have led to considerable improvements for this task in a single image, most existing approaches still fail to overcome this limitation. Supervised learning methods model depth estimation as a regression problem and, as a result, require large amounts of ground truth depth data for training in actual scenarios. Unsupervised learning methods treat depth estimation as the synthesis of a new disparity map, which means that rectified stereo image pairs need to be used as the training dataset. Aiming to solve such problem, we present an encoder-decoder based framework, which infers depth maps from monocular video snippets in an unsupervised manner. First, we design an unsupervised learning scheme for the monocular depth estimation task based on the basic principles of structure from motion (SfM) and it only uses adjacent video clips rather than paired training data as supervision. Second, our method predicts two confidence masks to improve the robustness of the depth estimation model to avoid the occlusion problem. Finally, we leverage the largest scale and minimum depth loss instead of the multiscale and average loss to improve the accuracy of depth estimation. The experimental results on the benchmark KITTI dataset for depth estimation show that our method outperforms competing unsupervised methods.

Feature-Based Correspondence Filtering Using Structural Similarity Index for Visual Odometry

The stereo correspondence problem is one of the most pre-eminent problems in a stereo vision system. With the right correspondence, a stereo vision system can help cap over diverse problems, while on the other hand, a wrong correspondence can be costly. While the performance of a feature-based correspondence approach is exceptional, the method can still produce wrong correspondences. This work presents an amalgam of feature-based and correlation-based correspondence, where the local pixels around a feature pair are compared using Structural SIMilarity index (SSIM), enhancing the correspondences, and a semantic-based filtering module, which further filters the obtained corresponding features using semantic data whenever detected in both the stereo image pair. While approaches in the literature are focused towards finding better features and their representation, the proposed approach advocates that correlation-based verification of the features can filter out bad correspondences, and in addition, aided by semantic-level filtering. These two modules establish the novelty of the work. The proposed correspondence matching algorithm is used to solve the problem of Visual Odometry to let a low-cost robot compute its pose in a novel environment. The experimental results show adequate filtering of wrong feature correspondence wherein, different environments with different lighting conditions were also considered. The proposed approach outperformed numerous state-of-the-art approaches available in the literature. The visual odometry algorithm using the proposed correspondence matching is compared against classical methods and a deep learning method, and it is observed that the proposed approach delivers lower trajectory error values in most scenarios on the KITTI dataset sequences.

A linear pushbroom satellite image epipolar resampling method for digital surface model generation

Epipolar resampling, also known as stereo rectification, is a prerequisite for optical satellite image stereo matching in digital surface model (DSM) generation. In epipolar resampling, image pairs are warped and thus can be matched pixel-to-pixel along the epipolar line. Different from the pinhole imaging model of frame cameras, the multi-center projection model of linear pushbroom sensors does not obey the epipolar geometric constraint, making it impossible to conjugate epipolar lines from stereo images. The epipolar resampling methods can resolve some of the inherent epipolar error, but not completely. The topographic relief brings high disparity values between epipolar image pairs, posing a challenge to the subsequent stereo matching to recover disparity map. In this paper, we introduce a novel epipolar resampling method for satellite imagery based on ortho rectification. This method takes full advantage of a rational function model to establish a connection between image space and object space coordinates, and thereby transform the two-dimensional disparity in ortho rectification products into one dimension. We propose a coarse-to-fine DSM generation pipeline to overcome the high-disparity-problem without additional time costs or precision decrement. We conducted experiments on various satellite stereo images, and validated both the extreme suppression on epipolar error as well as the feasibility of the proposed coarse-to-fine DSM generation pipeline. The experimental results show that the generated epipolar image pairs from our proposed method effectively solved the high disparity problem. Furthermore, the novel DSM generation method obtained an internal error below one pixel for a rectified stereo image pair in mountain area, and the lowest vertical error in the IARPA MVS dataset when compared with the common open-source programs and commercial software.

POTENTIAL EXPLORATION OF SEGMENTATION DRIVEN STEREO MATCHING OF VERY HIGH-RESOLUTION SATELLITE IMAGERY

Abstract. The automatic establishment of image relationship between oblique images can be a challenging task. Feature based image matching (FBM) establishes this relationship by detecting and matching corresponding feature points. A robust matching is beneficial for many tasks including reconstruction, mapping and localization. The need of automatic processing of remotely sensed data, like very highresolution (VHR) satellite imagery, increased over the years. Furthermore, green vegetation and water are changing the physical properties with respect to the amount of light emitted, season and pollution. In addition, with human interaction, the change in appearance increases. The Normalized Differential Vegetation Index (NDVI) is a well-known and studied index in order to detect healthy green vegetation. The Normalized Differential Water Index (NDWI) can help identify water areas in an image. They can be used to preliminarily segment images into different categories for later process. This study proposes a novel framework to explore the potential of feature based stereo matching for very high-resolution satellite imagery with segmentation. The proposed framework will perform first, image segmentation with NDVI and NDWI on stereo VHR satellite image pairs. Then, classification by threshold to detect healthy green vegetation, water and image frame. Features within these three classes are masked out and kept from being processed during the feature matching step. The idea is that, features in these classes are easy to cause miss matching because they are more prone to be affected by different image and environmental conditions in the stereo image pairs. As a result, the amount of miss matches can be reduced on average by 7.5%. Furthermore, the segmentation decreases the total amount of detected features by 13.71%, so that the processing time decreases. This study has successfully proven that segmentation can lead to improved stereo matching. In future, segmentation driven can be utilized by AI matching processes as well as traditionally photogrammetric or computer vision tasks.

Stereo Refinement Dehazing Network

The performance of stereo vision tasks degrades when haze exists in the input stereo image pair. Independently applying single image dehazing algorithm on left and right images is not optimal. To overcome the problem, we propose an effective framework, called SRDNet, for simultaneously dehazing stereo images. The main idea of SRDNet is to make full use of the stereo information from cross views improving dehazing performance. It does not explicitly employ the disparity estimation and the correlation matrix. SRDNet comprises two parts: a weight-sharing coarse dehazing network (WSCDN) and a guided separated refinement network (GSRN). The WSCDN is utilized to predict a coarse dehazed image pair. Then the GSRN is introduced to predict the residues for different views by extracting the fused information of cross views and separating the features of different views with a guided channel and spatial refinement module. The residues are added to the coarse dehazed pair so as to make refinement and remove the remained haze. Experimental results demonstrate that our proposed SRDNet surpasses previous image dehazing methods by a significant margin both quantitatively and qualitatively. Moreover, our SRDNet could be a preprocessing step of the stereo-based 3D object detection and boosts the 3D detection accuracy in hazy scenes.

TRIPLE EPIPOLAR IMAGES GENERATION AND MATCHING IN TRISTEREO IMAGING ON THE SAME ORBIT MODE

Abstract. This paper proposed the method to generate triple epipolar images in tristereo imaging on the same orbit mode. It generated projection tie points based on double projection surface in object space, and designed conversion model from epipolar images to its corresponding original images on the basis of projection tie points and created the RPC of epipolar images. During stereo matching one stereo image pairs are used as the basic pair and proposed the rapid transformation model between the current matching points and the corresponding point on the third image, which accomplished the combination of epipolar stereo matching and object space geometric constraints. After left/right bidirectional matching and occlusion area checking, a third matching was implemented. The cost of occlusion area will use the smallest one among the three and these areas were revamped. SGM was used as the optimization strategy. Experiments in three typical areas using Pleiades and ZY-3 as data recourses show that the loss of precision is negligible in the proposed epipolar image generation method. The proposed matching method combines the best of both object geometric constraint method and isolate epipolar image pair method, and the computational efficiency significantly better than these two methods. Lastly, the precision of the proposed method is significantly better than these two methods in building area and weak texture area.

UAV PHOTOGRAMMETRY FOR METRIC EVALUATION OF CONCRETE BRIDGE CRACKS

Abstract. Monitoring cracks opening on concrete bridges is a key aspect for structural health assessment. Digital image processing, combined with Unmanned Aerial Vehicles (UAVs) and photogrammetry, allows for non-contact 3D reconstruction of cracks, reducing costs and potential unsafe factors involved in manual inspections. This paper presents a flexible procedure based on UAV photogrammetry for accurate evaluation of cracks geometry, that can be implemented for periodic structural monitoring. Stereo-pair of images, acquired with UAVs close to the cracked surface, are used to build a scaled photogrammetric model through Structure-from-Motion. Cracks are detected on images by image binarization and digital image processing techniques. Thereafter, one single image is used to reconstruct crack 3D geometry, by back-projecting crack image coordinates on a 3D model of the object. This can be built from the current stereo-pair of images, or based on an existing photogrammetric model, in the case of a periodic monitoring set-up. Crack width is accurately estimated in 3D world. The procedure is tested and evaluated in a case study, obtaining millimetric accurate results, which is in line with the average ground sample distance of the images employed. Results highlight the potentials of UAVs and photogrammetry not only for bridge inspections and damages localization, but also for accurately evaluating cracks geometry and helping structural engineers to assess structure health conditions.

The roughness of martian topography: A metre-scale fractal analysis of six selected areas

Studies of the roughness of natural surfaces (landscapes) provide useful information for planetary geology. This paper covers the mapping and analysis of the spatial variability of the surface roughness of Martian topography at a high spatial resolution (metre-scale). The methodology provides new images of the Martian surface texture at the metre-scale that can assist in the interpretation of geological events, processes and formations. It can also assist in geological mapping and in the evaluation of sites that merit further exploration. Digital elevation models, generated by stereo-pair HiRISE images, of six different terrains (aeolian, volcanic, hydrated, cratered, reticulate and sublimated) were used to characterize the metre-scale terrain roughness of representative test sites on Mars. Surface roughness was evaluated by using the local fractal dimension and the results show that the mean of the local fractal dimension ranges from 2.17 in reticulate terrain to 2.71 in sublimated terrain in the southern polar cap. The roughness of the sublimated terrain is significantly higher than the roughness of typical terrains on Earth. Basically, the roughness of the Martian terrain at the metre-scale depends on the rugosity of the landscape, which can be quantified as the number of metric-scale closed depressions and mounds present on the terrain. The information provided by the spatial variability patterns of metre-scale roughness maps provides a significant resource for local planetary geology research at high resolution scale.

L1B+: A PERFECT SENSOR LOCALIZATION MODEL FOR SIMPLE SATELLITE STEREO RECONSTRUCTION FROM PUSH-FRAME IMAGE STRIPS

Abstract. We propose a novel method to generate a single image product from a multi-image strip acquired by a push-frame satellite imaging system. The images of the push-frame strips are combined into a large scale mosaic simulating a perfect sensor geometry. The local camera models of the input images are leveraged to produce a new localization model that covers the output mosaic entirely. Among other applications, this simplifies the task of stereo reconstruction enormously: instead of treating multiple stereo pairs of small images, it is possible to reconstruct the entire area covered by the push-frame acquisition using a single pair of mosaics incorporating all the images. We test our method using strips of SkySat L1B scenes and denote the output images as L1B+. To evaluate the quality of the L1B+ images and their localization models, the stereo reconstructions obtained with L1B+ are compared with those obtained with L1B and with a lidar reference model.

AN IMPROVED ENERGY SEGMENTATION BASED STEREO MATCHING ALGORITHM

Abstract. The stereo matching algorithm is commonly used in dealing with disparity discontinuous areas. However, the algorithm may have higher computational complexity and lack of well-aligned input images. To improve that, this paper presents an improved energy segmentation based stereo matching algorithm. The proposed algorithm incorporates gradient information of each segmented region into the energy function according to the facts that gradients inside the same segmentation should be closer than those from different segmentation. The invalid matching pixels are interpolated with vertical-horizontal nearest neighboring pixels to keep the consistency of stereo image pairs in the initial disparity map. Thus, the proposed method can reduce the deviations and the number of executions of the Random Sample Consensus (RANSAC) which arises from misalignment of input image pairs. Experiments results demonstrate that the proposed algorithm has a better disparity result while the running time is decreased by about 20%.