Low-textured regions detection for improving stereoscopy algorithms

Ibarra-Delgado, Salvador; Cózar, Julián Ramos; González-Linares, José María; Gómez-Luna, Juan; Guil, Nicolás

doi:10.1109/hpcsim.2014.6903753

Cited by 5 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presence of shadows in the dune face is determined by the steepness (slope) and orientation (aspect) of the topography in relation to the Sun light (for a given Sun altitude and azimuth). Optical remote sensing images from shadowed areas have low reflectance and texture, which alters the calculation of the disparity (which is later converted into elevation) of corresponding points in the stereo-pair and leads to less accurate elevations [27,28].…”

Section: D Beach Topography Comparisonsmentioning

confidence: 99%

Deriving High Spatial-Resolution Coastal Topography From Sub-meter Satellite Stereo Imagery

et al. 2019

View full text Add to dashboard Cite

High spatial resolution coastal Digital Elevation Models (DEMs) are crucial to assess coastal vulnerability and hazards such as beach erosion, sedimentation, or inundation due to storm surges and sea level rise. This paper explores the possibility to use high spatial-resolution Pleiades (pixel size = 0.7 m) stereoscopic satellite imagery to retrieve a DEM on sandy coastline. A 40-km coastal stretch in the Southwest of France was selected as a pilot-site to compare topographic measurements obtained from Pleiades satellite imagery, Real Time Kinematic GPS (RTK-GPS) and airborne Light Detection and Ranging System (LiDAR). The derived 2-m Pleiades DEM shows an overall good agreement with concurrent methods (RTK-GPS and LiDAR; correlation coefficient of 0.9), with a vertical Root Mean Squared Error (RMS error) that ranges from 0.35 to 0.48 m, after absolute coregistration to the LiDAR dataset. The largest errors (RMS error > 0.5 m) occurred in the steep dune faces, particularly at shadowed areas. This work shows that DEMs derived from sub-meter satellite imagery capture local morphological features (e.g., berm or dune shape) on a sandy beach, over a large spatial domain.Among topographic survey methods of suitable quality, those based on Global Navigation Satellite Systems (GPS), such as Real Time Kinematic GPS (RTK-GPS), have been used extensively to map and monitor coastal morphology [2]. Beach topographic surveys using RTK-GPS method can be performed either by walking and carrying a GPS receiver, or driving a mobile unit (e.g., quad bike). In both cases, the vertical precision is approximately 0.05 to 0.1 m, depending on the terrain relief [2]. This method typically requires an intense human effort, which normally is optimized by reducing the number of measurements to a limited number of cross-shore sections of the beach. Nevertheless, this limited spatial coverage results in an incomplete representation of topographic spatial patterns and evolving features, especially in the case of complex topographies such as steep and unconsolidated slopes. In such cases, interpolation methods are typically required, introducing additional uncertainty into the DEM [3].Remote sensing techniques, such as airborne LiDAR (Light Detection and Ranging) and Unmanned Aerial Vehicle (UAV), emerge in this context as a solution to overcome the limited spatial coverage of the RTK-GPS method [4][5][6][7][8][9]. The use of airborne LiDAR to measure geomorphological changes in coastal areas is relatively new. This instrumentation acquires millions of x, y, z points per hour, with a horizontal spacing of typically 1 to 3 m. This high spatial resolution, together with the capacity to survey over large areas (from 10 1 to 10 5 m), allows overcoming traditional survey limitations found with RTK-GPS [2]. The vertical accuracy of LiDAR ranges from 0.05 m to 0.15 m [5], which is in the same order as RTK-GPS and appropriate for studying beach morphology. Nonetheless, LiDAR-based DEMs are costly [5,6], which limits the frequent (e.g., monthly or-post-...

show abstract

Section: D Beach Topography Comparisonsmentioning

confidence: 99%

Deriving High Spatial-Resolution Coastal Topography From Sub-meter Satellite Stereo Imagery

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The -L‖ component of the lab color space closely matches for the easy human perception. There are many image processing algorithms applying the important transformations discussed in [1] [9]; we convert the left and right images from RGB to the Lab color space and retain only the L values of its pixels for further processing. The color space xyz conversion is also used for result comparison with the lab color space.…”

Section: A Preprocessingmentioning

confidence: 99%

An Evaluation and Improved Matching Cost of Stereo Matching Method

Raviya¹,

Vyas²

2016

IJIGSP

View full text Add to dashboard Cite

The main target of stereo matching algorithms is to find out the three dimensional (3D) distance, or depth of objects from a stereo pair of images. Depth information can be derived from images using disparity map of the same scene. There are many applications of computer vision like People tracking, Gesture recognition, Industrial automation and inspection, Security and Biometrics, Three-dimensional modeling, Web and Cloud, Aerial surveys etc. There are large categories of stereo algorithms which are used for finding the disparity or depth. This paper presents a proposed stereo matching algorithm to obtain depth map, enhance and measure. The hybrid mathematical process of the algorithm are color conversion, block matching, guided filtering, Minimum disparity assignment design, mathematical perimeter, zero depth assignment, combination of hole filling and permutation of morphological operator and last non linear spatial filtering. Our algorithm is produce noise less, reliable, smooth and efficient depth map. We obtained the results with ground truth image using Structural Similarity Index Map (SSIM) and Peak Signal to Noise Ratio (PSNR).

show abstract

“…In recent years, with the development of deep learning, studies based on image recognition algorithms and neural networks are developed for tackling the problems of color invariance and incomplete target tracking with lowresolution cameras [6,7]. For instance, Omer Akgul and others successfully completed the recognition of specific targets using Alexnet structure [8].…”

Section: Introductionmentioning

confidence: 99%

Geometry Consistency Of Augmented Reality Based On Semantics

Quan

Yao

Qian

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In augmented reality, for achieving geometric consistency in the perspective projection virtual-real, we propose a semantic consistency method to achieve the fusion between virtual and real objects with selected segmented objects in the real scene as references. The proposed framework maintains the three-dimensional structure of the scene by satisfying the global semantic map of the real scene. It takes the segmented objects in the scene as the basic unit, and executes the virtual and real fusion for ensuring the accuracy of the relative geometric position of the virtual objects. In addition, a multi-task network architecture is proposed to optimize the camera parameters based on the scene segmentation. The experiment results demonstrate the effectiveness of the proposed augmented reality geometric consistency framework, and confirm that our strategy has the capability of fusing the virtual and real geometric consistency.

show abstract

Low-textured regions detection for improving stereoscopy algorithms

Cited by 5 publications

References 16 publications

Deriving High Spatial-Resolution Coastal Topography From Sub-meter Satellite Stereo Imagery

Deriving High Spatial-Resolution Coastal Topography From Sub-meter Satellite Stereo Imagery

An Evaluation and Improved Matching Cost of Stereo Matching Method

Geometry Consistency Of Augmented Reality Based On Semantics

Contact Info

Product

Resources

About