Extraction of visual landmarks using improved feature matching technique for stereo vision applications

Sharma, Kajal; Moon, Inkyu; Kim, Sung Gaun

doi:10.4103/0256-4602.105002

Cited by 15 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. Feature extraction and matching [25]: SIFT algorithm was used to extract the image features, and image matching was carried out. The basic matrix was calculated by the RANSAC algorithm, and the wrong matching pairs were eliminated; 2.…”

Section: Image Datamentioning

confidence: 99%

A Novel Method for Density Analysis of Repaired Point Cloud with Holes Based on Image Data

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Repairing point cloud holes has become an important problem in the research of 3D laser point cloud data, which ensures the integrity and improves the precision of point cloud data. However, for the point cloud data with non-characteristic holes, the boundary data of point cloud holes cannot be used for repairing. Therefore, this paper introduces photogrammetry technology and analyzes the density of the image point cloud data with the highest precision. The 3D laser point cloud data are first formed into hole data with sharp features. The image data are calculated into six density image point cloud data. Next, the barycenterization Bursa model is used to fine-register the two types of data and to delete the overlapping regions. Then, the cross-section is used to evaluate the precision of the combined point cloud data to get the optimal density. A three-dimensional model is constructed for this data and the original point cloud data, respectively and the surface area method and the deviation method are used to compare them. The experimental results show that the ratio of the areas is less than 0.5%, and the maximum standard deviation is 0.0036 m and the minimum is 0.0015 m.

show abstract

Section: Image Datamentioning

confidence: 99%

A Novel Method for Density Analysis of Repaired Point Cloud with Holes Based on Image Data

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Numerous algorithms have been proposed in the field of path finding, navigation, and simultaneous localization and mapping (SLAM) [1][2][3][4]. Most of the techniques rely on laser or sonar sensors, while others are based on recently developed vision sensors [5][6][7].…”

Section: Related Workmentioning

confidence: 99%

Mobile Robot Path Finding Using Invariant Landmarks

Sharma¹

2016

IEIE Transactions on Smart Processing and Computing

Self Cite

View full text Add to dashboard Cite

This paper proposes a new path-finding scheme using viewpoint-invariant landmarks. The scheme introduces the concept of landmark detection in images captured with a vision sensor attached to a mobile robot, and provides landmark clues to determine a path. Experiment results show that the scheme efficiently detects landmarks with changes in scenes due to the robot's movement. The scheme accurately detects landmarks and reduces the overall landmark computation cost. The robot moves in the room to capture different images. It can efficiently detect landmarks in the room from different viewpoints of each scene. The outcome of the proposed scheme results in accurate and obstacle-free path estimation.

show abstract

“…For stereo matching approaches based on features, the common features are Scale Invariant Feature Transform (SIFT) features and geometric features. In order to improve the efficiency of the stereo matching of high-speed automobile navigation, Sharma et al combined SIFT features with maps before being stored in the database [4,5]. Joglekar, et al reported relevant parameters of neural networks based on rigorous SIFT matching, and achieved denser stereo matching with the neural networks based on Bayesian decision [6].…”

Section: Introductionmentioning

confidence: 99%

A study of stereo microscope measurements based on interpolated feature matching

Wang

Jiang

et al. 2015

BME

View full text Add to dashboard Cite

Abstract. Recently, digital stereo microscopes have been becoming increasingly popular in fields such as biomedicine and biotechnology. As such, being able to precisely match left/right feature pairs is critical, which is an important step in stereo matching. We hereby propose a dynamic interpolation method that combines two dimensional calibration and depth information to achieve stereo matching. In this experiment, we obtained the original scale-invariant feature transform feature point pairs and selected a pair of matching units. Based on the selected pair of matching elements and interpolated feature points shown in the left view of stereo microscope image, the dynamically interpolated feature points in the right view were developed to perform stereo measurements. The experimental results revealed that the proposed method can realize stereo microscopic measurements; results with high reliability can be achieved with a large quantity of matching elements.

show abstract

Extraction of visual landmarks using improved feature matching technique for stereo vision applications

Cited by 15 publications

References 17 publications

A Novel Method for Density Analysis of Repaired Point Cloud with Holes Based on Image Data

A Novel Method for Density Analysis of Repaired Point Cloud with Holes Based on Image Data

Mobile Robot Path Finding Using Invariant Landmarks

A study of stereo microscope measurements based on interpolated feature matching

Contact Info

Product

Resources

About