A survey on image mosaicing techniques

Ghosh, Debabrata; Kaabouch, Naima

doi:10.1016/j.jvcir.2015.10.014

Cited by 168 publications

(93 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this paper, a modified version of the integer-coded genetic algorithm, originally proposed by [50] is applied to stochastically search for a sample set of correspondences that minimizes Equation (5). In GA terminology, each candidate sample set of correspondences is called an individual.…”

Section: Robust Estimation Via the Genetic Algorithmmentioning

confidence: 99%

“…In contrast to dense image matching, where image correspondences are established at nearly each pixel, sparse matching establishes the correspondences at salient image points only. Recent research works apply sparse matching to address a variety of problems including simultaneous localization and mapping [1,2], feature tracking [3] and real-time mosaicking [4,5]. The results of sparse matching are usually contaminated with false correspondences.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary Optimization for Robust Epipolar-Geometry Estimation and Outlier Detection

2017

View full text Add to dashboard Cite

Abstract:In this paper, a robust technique based on a genetic algorithm is proposed for estimating two-view epipolar-geometry of uncalibrated perspective stereo images from putative correspondences containing a high percentage of outliers. The advantages of this technique are three-fold: (i) replacing random search with evolutionary search applying new strategies of encoding and guided sampling; (ii) robust and fast estimation of the epipolar geometry via detecting a more-than-enough set of inliers without making any assumptions about the probability distribution of the residuals; (iii) determining the inlier-outlier threshold based on the uncertainty of the estimated model. The proposed method was evaluated both on synthetic data and real images. The results were compared with the most popular techniques from the state-of-the-art, including RANSAC (random sample consensus), MSAC, MLESAC, Cov-RANSAC, LO-RANSAC, StaRSAC, Multi-GS RANSAC and least median of squares (LMedS). Experimental results showed that the proposed approach performed better than other methods regarding the accuracy of inlier detection and epipolar-geometry estimation, as well as the computational efficiency for datasets majorly contaminated by outliers and noise.

show abstract

Section: Robust Estimation Via the Genetic Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evolutionary Optimization for Robust Epipolar-Geometry Estimation and Outlier Detection

2017

View full text Add to dashboard Cite

show abstract

“…Interest points can be edges, corners or blobs. There are several edge and corner detection methods to identify the interest points [14,15]. In this paper, interest points are extracted by Difference of Gaussian (DoG) method which is a blob detection method.…”

Section: Image Mosaicingmentioning

confidence: 99%

Adaptive Vision Based Condition Monitoring and Fault Detection Method for Multi Robots at Production Lines in Industrial Systems

Yetiş¹,

Karaköse²

2016

International Journal of Applied Mathematics, Electronics and Computers

View full text Add to dashboard Cite

Continuity of production is a highly important in the days that manufacturing is becoming bigger and serial. The mistakes done while producing process cause fail on products and it may bring about even big losses for the facility. Furthermore, hitches on robots at production line may also cause crucial damages that may give rise to high repair costs and discontinuance of production. In this study, it is aimed to obtain alive bird's eye view map of production lines, which are big and impossible to be monitored with only one camera, by using multi cameras and stitching algorithms. Finding the similar scenes of input images, estimation of homography, warping and blending operations, which are the steps used in feature based image-stitching algorithms, are applied respectively on images that are taken by cameras. The assignment of second nearest neighbor distance rate adaptively makes the results more qualified. After obtaining single stitched image movement detection is actualized by using the difference of sequential frames, and anomaly movements are determined. As a result, the robots at the long production lines can be monitored in one screen, and with processing the obtained image, faults on robots that may cause damage at non-cheap machines can be handled before time.

show abstract

“…In this configuration, stitching individual projector images is nontrivial. Most existing image stitching algorithms are based on feature recognition, which is computationally extensive and unsuitable for real‐time rendering . Furthermore, these algorithms suffer from boundary inconsistency of the source images .…”

Section: Introductionmentioning

confidence: 99%

Development of a parameterization image stitching algorithm for ultrashort throw laser MEMS projectors

Cui

Gao

2019

J Soc Info Display

View full text Add to dashboard Cite

We present a novel design of a parameterization image stitching algorithm for ultrashort throw laser MEMS projectors. The resultant method allows the use of projectors with short or even long throw ratios to achieve ultrashort throw projection through a parameterized algorithm to stitch multiple images into one single frame, alleviating the trade‐off between the resolution and frame rate in conventional laser MEMS displays. To evaluate the effectiveness, we construct a test system that consists of three off‐the‐shelf projectors with a throw ratio of 1.3 and three planar reflective mirrors. Using our method, the integrated system yields an ultrashort throw ratio of 0.26, greatly reducing the projection distance from 12 to 2.6 ft for the 120‐in. screen in diagonal. Moreover, our algorithm can be fine‐tuned to correct for image distortion, intensity variation, and edge mismatch induced by two‐axis light beam steering, thereby further improving the image quality.

show abstract

A survey on image mosaicing techniques

Cited by 168 publications

References 48 publications

Evolutionary Optimization for Robust Epipolar-Geometry Estimation and Outlier Detection

Evolutionary Optimization for Robust Epipolar-Geometry Estimation and Outlier Detection

Adaptive Vision Based Condition Monitoring and Fault Detection Method for Multi Robots at Production Lines in Industrial Systems

Development of a parameterization image stitching algorithm for ultrashort throw laser MEMS projectors

Contact Info

Product

Resources

About