Enhanced disparity estimation in stereo images

Kordelas, Georgios; Alexiadis, Dimitrios S.; Daras, Petros; Izquierdo, Ebroul

doi:10.1016/j.imavis.2014.12.001

Cited by 41 publications

(20 citation statements)

References 42 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The selection of these strict values ensures that the segmentation map will be of high reliability, meaning that most likely, a segment will be comprised of pixels belonging to surfaces with similar spectral behavior. The latter fact is verified also in [39,40]. An example for performing mean-shift segmentation to the blue, green and red bands of Sentinel-2 (S2) data acquired on 20 August 2017 is given in Figure 3.…”

Section: Segmentation Of the Satellite Imagementioning

confidence: 54%

Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data

et al. 2018

View full text Add to dashboard Cite

Satellite data offer the opportunity for monitoring the temporal flooding dynamics of seasonal wetlands, a parameter that is essential for the ecosystem services these areas provide. This study introduces an unsupervised approach to estimate the extent of flooded areas in a satellite image relying on the physics of light interaction with water, vegetation and their combination. The approach detects automatically thresholds on the Short-Wave Infrared (SWIR) band and on a Modified-Normalized Difference Vegetation Index (MNDVI), derived from radiometrically-corrected Sentinel-2 data. Then, it combines them in a meaningful way based on a knowledge base coming out of an iterative trial and error process. Classes of interest concern water and non-water areas. The water class is comprised of the open-water and water-vegetation subclasses. In parallel, a supervised approach is implemented mainly for performance comparison reasons. The latter approach performs a random forest classification on a set of bands and indices extracted from Sentinel-2 data. The approaches are able to discriminate the water class in different types of wetlands (marshland, rice-paddies and temporary ponds) existing in the Doñana Biosphere Reserve study area, located in southwest Spain. Both unsupervised and supervised approaches are examined against validation data derived from Landsat satellite inundation time series maps, generated by the local administration and offered as an online service since 1983. Accuracy assessment metrics show that both approaches have similarly high classification performance (e.g., the combined kappa coefficient of the unsupervised and the supervised approach is 0.8827 and 0.9477, and the combined overall accuracy is 97.71% and 98.95, respectively). The unsupervised approach can be used by non-trained personnel with a potential for transferability to sites of, at least, similar characteristics.

show abstract

Section: Segmentation Of the Satellite Imagementioning

confidence: 54%

Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data

et al. 2018

View full text Add to dashboard Cite

show abstract

“…As stated, disparity estimation is an extensively-studied problem, and the corresponding literature is long, e.g., [6,7,[18][19][20][21], just to name a few works. According to [7], many of them can be decomposed into a set of distinct generic steps: calculation of a pixel-wise matching-cost, cost aggregation and spatial regularization-optimization.…”

Section: Previous Relevant Workmentioning

confidence: 99%

Frequency-Domain Joint Motion and Disparity Estimation Using Steerable Filters

2018

View full text Add to dashboard Cite

Abstract:In this paper, the problem of joint disparity and motion estimation from stereo image sequences is formulated in the spatiotemporal frequency domain, and a novel steerable filter-based approach is proposed. Our rationale behind coupling the two problems is that according to experimental evidence in the literature, the biological visual mechanisms for depth and motion are not independent of each other. Furthermore, our motivation to study the problem in the frequency domain and search for a filter-based solution is based on the fact that, according to early experimental studies, the biological visual mechanisms can be modelled based on frequency-domain or filter-based considerations, for both the perception of depth and the perception of motion. The proposed framework constitutes the first attempt to solve the joint estimation problem through a filter-based solution, based on frequency-domain considerations. Thus, the presented ideas provide a new direction of work and could be the basis for further developments. From an algorithmic point of view, we additionally extend state-of-the-art ideas from the disparity estimation literature to handle the joint disparity-motion estimation problem and formulate an algorithm that is evaluated through a number of experimental results. Comparisons with state-of-the-art-methods demonstrate the accuracy of the proposed approach.

show abstract

“…For example, when the image radiometric condition is good, the absolute difference (AD), the insensitive measure of Birchfield and Tomasi (BT), or the gradient measure can achieve accurate matching results (Meiet et al, 2011). When the image radiation varies, zero-based normalized cross correlation (ZNCC) and normalized gradient (Zhou and Boulanger, 2012) are often used to compensate for linear radiation distortions between correspondences, while Census (Zabih and Woodfill, 2005;Jiao et al, 2014;Kordelas et al, 2015), mutual information (Paul et al, 1997), and image radiation correction (Jung et al, 2013) are insensitive to nonlinear radiation distortion. Hirschmuller evaluated the popular cost computation methods and concluded that Census and mutual information measures can achieve the best matching results under varying radiometric conditions (Hirschmueller and Scharstein, 2009).…”

Section: Review Of Previous Workmentioning

confidence: 99%

Image-Guided Non-Local Dense Matching With Three-Steps Optimization

Xu¹,

Zhang²,

Yue³

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This paper introduces a new image-guided non-local dense matching algorithm that focuses on how to solve the following problems: 1) mitigating the influence of vertical parallax to the cost computation in stereo pairs; 2) guaranteeing the performance of dense matching in homogeneous intensity regions with significant disparity changes; 3) limiting the inaccurate cost propagated from depth discontinuity regions; 4) guaranteeing that the path between two pixels in the same region is connected; and 5) defining the cost propagation function between the reliable pixel and the unreliable pixel during disparity interpolation. This paper combines the Census histogram and an improved histogram of oriented gradient (HOG) feature together as the cost metrics, which are then aggregated based on a new iterative non-local matching method and the semi-global matching method. Finally, new rules of cost propagation between the valid pixels and the invalid pixels are defined to improve the disparity interpolation results. The results of our experiments using the benchmarks and the Toronto aerial images from the International Society for Photogrammetry and Remote Sensing (ISPRS) show that the proposed new method can outperform most of the current state-of-the-art stereo dense matching methods.

show abstract

Enhanced disparity estimation in stereo images

Cited by 41 publications

References 42 publications

Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data

Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data

Frequency-Domain Joint Motion and Disparity Estimation Using Steerable Filters

Image-Guided Non-Local Dense Matching With Three-Steps Optimization

Contact Info

Product

Resources

About