Adaptive Disparity Research Articles

Skeletal muscle transcriptomics of sheep acclimated to cold desert and tropical regions identifies genes and pathways accentuating their diversity.

The current study attempts to investigate the differences in gene expression in longissimus thoracis muscles between sheep breeds acclimated to diverse environments. Changthangi sheep inhabits the cold arid plateau of Ladakh, at an altitude above 3000m with prevalence of rarefied atmosphere. Muzzafarnagri sheep, on the other hand is found in the sub-tropical hot and humid plains at an altitude of about 250m. Comparative transcriptomics was used to provide a molecular perspective of the differential adaptation of the two breeds. RNA sequencing data was generated from four biological replicates of the longissimus thoracis muscles from both breeds. The common genes expressed in both breeds were involved in muscle contraction and muscle fibre organization. The most significant pathways enriched in Changthangi muscles were glycogen metabolism, reduction of cytosolic Ca++ levels and NFE2L2 regulating anti-oxidant, while those in Muzzafarnagri were extracellular matrix organization and collagen formation. The hub genes identified in Changthangi were involved in hematopoiesis and HIF signaling pathway, suggesting the molecular acclimatization of Changthangi to the high altitude cold desert of Ladakh. The nodal genes discovered in Muzzafarnagri sheep were associated with the extracellular matrix which accentuates its significance in the development, growth and repair of muscles. The observed transcriptomic differences underscore the morphological and adaptive disparity between the two breeds. The candidate genes and pathways identified in this study will form the basis for future research on adaptation to high altitude and body size in small ruminants.

Self-Supervised Monocular Depth Estimation With Positional Shift Depth Variance and Adaptive Disparity Quantization.

Recently, attempts to learn the underlying 3D structures of a scene from monocular videos in a fully self-supervised fashion have drawn much attention. One of the most challenging aspects of this task is to handle independently moving objects as they break the rigid-scene assumption. In this paper, we show for the first time that pixel positional information can be exploited to learn SVDE (Single View Depth Estimation) from videos. The proposed moving object (MO) masks, which are induced by the depth variance to shifted positional information (SPI) and are referred to as 'SPIMO' masks, are highly robust and consistently remove independently moving objects from the scenes, allowing for robust and consistent learning of SVDE from videos. Additionally, we introduce a new adaptive quantization scheme that assigns the best per-pixel quantization curve for depth discretization, improving the fine granularity and accuracy of the final aggregated depth maps. Finally, we employ existing boosting techniques in a new way that self-supervises moving object depths further. With these features, our pipeline is robust against moving objects and generalizes well to high-resolution images, even when trained with small patches, yielding state-of-the-art (SOTA) results with four- to eight-fold fewer parameters than the previous SOTA techniques that learn from videos. We present extensive experiments on KITTI and CityScapes that show the effectiveness of our method.

A Disparity Refinement in Stereo Matching based on Mean-shift Segmentation and Spatiotemporal Domain

Abstract A stereo matching algorithm is used to find the best match between a pair of images. To compute the cost of the matching points from the sequence of images, the disparity maps from video streams are estimated. However, the estimated disparity sequences may cause undesirable flickering errors. These errors result in low visibility of the synthesized video and reduce video coding. In order to solve this problem, in this article, the authors propose a spatiotemporal disparity refinement on local stereo matching based on the segmentation strategy. Based on segmentation information, matching point searching, and color similarity, adaptive disparity values to recover the disparity errors in disparity sequences can be obtained. The flickering errors are also effectively removed, and the boundaries of objects are well preserved. The procedures of the proposed approach consist of a segmentation process, matching point searching, and refinement in the temporal and spatial domains. Experimental results verify that the proposed approach can yield a high quantitative evaluation and a high-quality disparity map compared with other methods.

PRECISE DISPARITY ESTIMATION FOR NARROW BASELINE STEREO BASED ON MULTISCALE SUPERPIXELS AND PHASE CORRELATION

Abstract. With the rapid development of subpixel matching algorithms, the estimation of image shifts with an accuracy of higher than 0.05 pixels is achieved, which makes the narrow baseline stereovision possible. Based on the subpixel matching algorithm using the robust phase correlation (PC), in this work, we present a novel hierarchical and adaptive disparity estimation scheme for narrow baseline stereo, which consists of three main steps: image coregistration, pixel-level disparity estimation, and subpixel refinement. The Fourier-Mellin transform with subpixel PC is used to co-register two input images. Then, the pixel-level disparities are estimated in an iterative manner, which is achieved through multiscale superpixels. The pixel-level PC is performed with the window sizes and locations adaptively determined according to superpixels, with the disparity values calcualted. Fast weighted median filtering based on edge-aware filter is adopted to refine the disparity results. At last, the accurate disparities are calculated via a robust subpixel PC method. The combination of multiscale superpixel hierarchy, adaptive determination of the window size and location of correlation, fast weighted median filtering and subpixel PC make the proposed scheme be able to overcome the issues of either low-texture areas or fattening effect. Experimental results on a pair of UAV images and the comparison with the fixed-window PC methods, the iterative scheme with fixed variation strategy, and a sophisticated implementation using global optimization demonstrate the superiority and reliability of the proposed scheme.

Adaptive disparity computation using local and non-local cost aggregations

A new method is proposed to adaptively compute the disparity of stereo matching by choosing one of the alternative disparities from local and non-local disparity maps. The initial two disparity maps can be obtained from state-of-the-art local and non-local stereo algorithms. Then, the more reasonable disparity is selected. We propose two strategies to select the disparity. One is based on the magnitude of the gradient in the left image, which is simple and fast. The other utilizes the fusion move to combine the two proposal labelings (disparity maps) in a theoretically sound manner, which is more accurate. Finally, we propose a texture-based sub-pixel refinement to refine the disparity map. Experimental results using Middlebury datasets demonstrate that the two proposed selection strategies both perform better than individual local or non-local algorithms. Moreover, the proposed method is compatible with many local and non-local algorithms that are widely used in stereo matching.

Spaceborne multiview image compression based on adaptive disparity compensation with rate-distortion optimization

Disparity compensation (DC) and transform coding are incorporated into a hybrid coding to reduce the code-rate of multiview images. However, occlusion and inaccurate disparity estimations (DE) impair the performance of DC, especially in spaceborne images. This paper proposes an adaptive disparity-compensation scheme for the compression of spaceborne multiview images, including stereo image pairs and three-line-scanner images. DC with adaptive loop filter is used to remove redundancy between reference images and target images and a wavelet-based coding method is used to encode reference images and residue images. In occlusion regions, the DC efficiency may be poor because no interview correlation exists. A rate-distortion optimization method is thus designed to select the best prediction mode for local regions. Experimental results show that the proposed scheme can provide significant coding gain compared with some other similar coding schemes, and the time complexity is also competitive.

Adaptive Disparity Estimation for Auto Convergence of Region of Interest in a Video

Adaptive Disparity Estimation for Auto Convergence of Region of Interest in a Video

Boundary-preserving stereo matching with certain region detection and adaptive disparity adjustment

In this paper, we propose boundary-preserving stereo matching using certain region detection and adaptive disparity adjustment. The main contribution of the proposed method lies in the detection and adjustment of incorrect disparities. In the detection process, we detect certain regions in initial disparity maps to distinguish errors in disparity caused by the disparity discontinuity. In the adjustment process, we adjust the disparity map to reduce the adverse effect of errors in disparity using the certain region detection results. Based on the color similarity, spatial distance, and the reliability of the certain and uncertain regions, we set an adaptive support-weight to each pixel for adjusting the accuracy. Experimental results demonstrate that the proposed method produces high-quality disparity maps by successfully preserving disparity discontinuities along the object boundaries.

Multi-Resolution Disparity Processing and Fusion for Large High-Resolution Stereo Image

Large panoramic views with high resolution have the advantage of a wide field of view over regular stereo views. However, the large size and high resolution impose difficulties on the stereo matching problem such as complexity and structure ambiguity, respectively. In this paper, effective multi-resolution disparity processing to resolve the difficulties is presented. We propose to adaptively determine the disparity search range based on the combined local structure from image intensity and initial disparity. The adaptive disparity range is able to propagate the smoothness property at low resolution to high resolution while preserving fine details. It reduces structure ambiguity as well as computational complexity. To reduce the disparity quantization error at the coarse level, we propose a reliable multiple fitting algorithm that is noticeably effective on the round surface. The spatial-multi-resolution total variation method is investigated to minimize inconsistency in space-scale dimension . The experimental results on the Middlebury datasets and real-world high-resolution images demonstrate that the proposed multi-resolution scheme produces high-quality and high-resolution disparity maps by fusing individual multi-scale disparity maps, while reducing complexity.

Nonadaptive radiation in damselflies.

Adaptive radiations have long served as living libraries to study the build-up of species richness; however, they do not provide good models for radiations that exhibit negligible adaptive disparity. Here, we review work on damselflies to argue that nonadaptive mechanisms were predominant in the radiation of this group and have driven species divergence through sexual selection arising from male-female mating interactions. Three damselfly genera (Calopteryx,Enallagma and Ischnura) are highlighted and the extent of (i) adaptive ecological divergence in niche use and (ii) nonadaptive differentiation in characters associated with reproduction (e.g. sexual morphology and behaviours) was evaluated. We demonstrate that species diversification in the genus Calopteryx is caused by nonadaptive divergence in coloration and behaviour affecting premating isolation, and structural differentiation in reproductive morphology affecting postmating isolation. Similarly, the vast majority of diversification events in the sister genera Enallagma and Ischnura are entirely driven by differentiation in genital structures used in species recognition. The finding that closely related species can show negligible ecological differences yet are completely reproductively isolated suggests that the evolution of reproductive isolation can be uncoupled from niche-based divergent natural selection, challenging traditional niche models of species coexistence.

Feature matching in stereo images encouraging uniform spatial distribution

Finding feature correspondences between a pair of stereo images is a key step in computer vision for 3D reconstruction and object recognition. In practice, a larger number of correct correspondences and a higher percentage of correct matches are beneficial. Previous researches show that the spatial distribution of correspondences are also very important especially for fundamental matrix estimation. So far, no existing feature matching method considers the spatial distribution of correspondences. In our research, we develop a new algorithm to find good correspondences in all the three aspects mentioned, i.e., larger number of correspondences, higher percentage of correct correspondences, and better spatial distribution of correspondences. Our method consists of two processes: an adaptive disparity smoothing filter to remove false correspondences based on the disparities of neighboring correspondences and a matching exploration algorithm to find more correspondences according to the spatial distribution of correspondences so that the correspondences are as uniformly distributed as possible in the images. To find correspondences correctly and efficiently, we incorporate the cheirality constraint under an epipole polar transformation together with the epipolar constraint to predict the potential location of matching point. Experiments demonstrate that our method performs very well on both the number of correct correspondences and the percentage of correct correspondences; and the obtained correspondences are also well distributed over the image space.

Short-term saccadic adaptation in the macaque monkey: a binocular mechanism

Saccadic eye movements are rapid transfers of gaze between objects of interest. Their duration is too short for the visual system to be able to follow their progress in time. Adaptive mechanisms constantly recalibrate the saccadic responses by detecting how close the landings are to the selected targets. The double-step saccadic paradigm is a common method to simulate alterations in saccadic gain. While the subject is responding to a first target shift, a second shift is introduced in the middle of this movement, which masks it from visual detection. The error in landing introduced by the second shift is interpreted by the brain as an error in the programming of the initial response, with gradual gain changes aimed at compensating the apparent sensorimotor mismatch. A second shift applied dichoptically to only one eye introduces disconjugate landing errors between the two eyes. A monocular adaptive system would independently modify only the gain of the eye exposed to the second shift in order to reestablish binocular alignment. Our results support a binocular mechanism. A version-based saccadic adaptive process detects postsaccadic version errors and generates compensatory conjugate gain alterations. A vergence-based saccadic adaptive process detects postsaccadic disparity errors and generates corrective nonvisual disparity signals that are sent to the vergence system to regain binocularity. This results in striking dynamical similarities between visually driven combined saccade-vergence gaze transfers, where the disparity is given by the visual targets, and the double-step adaptive disconjugate responses, where an adaptive disparity signal is generated internally by the saccadic system.

71.3: Study on Reducing the Cardboard Effect for Natural Perception Using Adaptive Disparity Mapping

AbstractWe propose the adaptive disparity mapping method for reducing the cardboard effect. The method is divided into two parts. At first, the perceptual model is defined for modifying spatial layout. Secondly, the differences of adjacent disparities in the objects are interpolated. We conducted a subjective test to evaluate the proposed method applied to the 3D image taken by a smartphone equipped with a twin‐lens camera. The results of our experiments show that the proposed method makes 3D images more roundness and gives a sense of depth.

A Trinocular Stereo-Matching Algorithm Based on Adaptive Support-Weight for Mobile Service Robot

A trinocular stereo-matching algorithm based on adaptive support-weight and disparity adjustment has been proposed to improve the accuracy of trinocular vision. Adaptive support-weight which is an efficient window selection method in binocular stereo is applied in the trinocular stereo. A robust target image selection method is also proposed for using the information of different target images in trinocular stereo-vision system efficiently. So occlusion can be handled well by this means. The vision system is tested in the project Family Life Support Multi-Robot Systems.

Low complexity multiview video plus depth coding

Multiview video plus depth (MVD) is a new 3D video format that would support 3D applications developed by MPEG. Such a format is a combination of texture video and associated depth maps. Consequently, for the efficient transmission of 3D video signals, the compression of texture video and also the depth maps is required. Since high computational complexity of jointly coding between the texture video and depth map is still an open question, this paper introduces a low complexity MVD coding algorithm that adaptively utilizes the texture and depth map correlation. Based on the correlation, we propose four efficient techniques, including depth information based fast mode size decision, adaptive disparity estimation in texture coding, motion vector sharing based on the texture image similarity correlation and the SKIP mode decision in depth coding. Experimental results show that the proposed algorithm can significantly reduce the computational complexity of MVD coding while improve the coding performance and achieve better rendering quality <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> .

A Real-time Multiview Video Coding System using Fast Disparity Estimation

In this paper, a real-time multiview video coding system using fast disparity estimation is proposed, In the multiview encoder, adaptive disparity-motion estimation (DME) for an effective 3-dimensional (3D) processing are proposed, That is, by adaptively predicting the mutual correlation between stereo images in the key-frame using the proposed algorithm, the bandwidth of stereo input images can be compressed to the level of a conventional 2D image and a predicted image also can be effectively reconstructed using a reference image and adaptive disparity vectors. Also, in multiview decoder, intermediate view reconstruction (IVR) using adaptive disparity search algorithm (DSA) for real-time multiview video processing is proposed, The proposed IVR can reduce a processing time of disparity estimation by selecting adaptively disparity search range. Accordingly, the proposed multiview video coding system is able to increase the efficiency of the coding rate and improve the resolution.

Trinocular disparity estimation with adaptive support weight and disparity calibration

A new trinocular stereo matching algorithm is proposed. The collinear trinocular stereo, which is an almost occlusion-free system, is adopted, and the classical binocular stereo algorithm, adaptive support weight, is used for window selection. A novel camera selection technique is presented to utilize the information of different target images more efficiently. Moreover, a trinocular disparity calibration algorithm is introduced, so the initial disparity can be refined and a precise result can be produced. Some image sequences of real scenes are used to evaluate our algorithm. The result shows that the proposed method can extract an accurate disparity map. It is concise and efficient.

三目自适应权值立体匹配和视差校准算法

三目自适应权值立体匹配和视差校准算法

Computer-Based Integral Imaging Using Adaptive Disparity Estimation Based Intermediate View Reconstruction

In this paper, computer-based integral imaging (II) using adaptive disparity estimation (ADE) based intermediate-view reconstruction (IVR) technique is proposed. In the proposed methodology, a number of intermediate elemental images can be synthesized, as many as required, from the limited number of pickup elemental images using the ADE based IVR technique. In the proposed ADE, for the region having larger feature values, a smaller matching window is selected, whereas, for the opposite case, a larger matching window is selected by comparing predetermined threshold values. In addition, intermediate-view elemental image (IEI) is synthesized using an IVR technique that is an interpolation method with a weighted mean value for the images. With sufficient overlapping of the increased number of elemental images in the reconstruction image plane, resolution-enhanced three-dimensional (3-D) II can be carried out. Also, in this study, some experiments were performed and their results are presented.

Stereo image reconstruction using regularized adaptive disparity estimation

In this paper, stereo image reconstruction using regularized adaptive disparity estimation is proposed. That is, by adaptively predicting the mutual correlation between stereo images pair using the proposed algorithm, the bandwidth of stereo input images pair can be compressed to the level of a conventional 2D image and a predicted image also can be effectively reconstructed using a reference image and disparity vectors. Especially, in the proposed algorithm, the first feature values are extracted from the input stereo images pair. Then, a matching window for stereo matching is adaptively selected depending on the magnitude of these feature values. That is, for the region having larger feature values, a smaller matching window is selected, while, for the opposite case, a larger matching window is selected by comparing predetermined threshold values. This approach is not only able to reduce a mismatching of disparity vectors, which occurs in the conventional dense disparity estimation with a small matching window, but is also able to reduce blocking effects that occur in the coarse disparity estimation with a large matching window. In addition, in this paper, a new regularized adaptive disparity estimation technique is proposed. That is, by regularizing the estimated disparity vector with the neighboring disparity vectors, problems of the conventional adaptive disparity estimation scheme might be solved, and the predicted stereo image can be more effectively reconstructed. From experiments using stereo sequences of “Man”, “Fichier”, “Manege”, and “Tunnel”, it is shown that the proposed algorithm improves the PSNRs of a reconstructed image to about 6.90 dB on average at ±30 search ranges as compared to those of conventional algorithms. Also, it is found that there is almost no difference between an original image and a reconstructed image through the proposed algorithm by comparison to that of conventional algorithms.