Iterative Corner Extraction and Matching for Mosaic Construction

Alkaabi, Sultan; Deravi, Farzin

doi:10.1109/crv.2005.50

Cited by 9 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In each of the images of Figure 1, the brightness of the images is artificially reduced, motion blur (horizontal and vertical) is added, Gaussian noise is introduced and small rotation and translation is applied. In order to explain the improvement of the proposed algorithm, the comparison is preformed over two standard algorithms for corner matching proposed by Alkaabi and Deravi [10] and Laurakis et al [14] with respect to two performance measures, precision and recall, discussed in section IIC under different conditions. The results are shown in Figure 2 (Figure 2 and 3), it is observed that when the comparison is performed normal lighting conditions, the performance of the proposed algorithm is almost similar (slightly better) compared to two other algorithms.…”

Section: Resultsmentioning

confidence: 99%

“…Lourakis et al [9] proposed a fully automatic method for matching image features between two stereo pairs which exploited geometric constraints arising from the structure of a scene. Alkaabi and Deravi [10] proposed a rapid and automatic iterative corner extraction and matching for 2D mosaic construction. The algorithm combined corner extraction, matching, and transformation parameters estimation into an iterative scheme.…”

Section: ____________________________________________________________mentioning

confidence: 99%

See 1 more Smart Citation

Efficient Fuzzy Set Theoretic Approach to Image Corner Matching

Dutta

2015

IJRITCC

View full text Add to dashboard Cite

Abstract-Corner matching in digital images is a key step in several applications in computer vision such as motion estimation, object recognition and localization, 3D reconstruction etc. Accuracy and reliability of corner matching algorithms are two important criteria. In this paper, corner correspondence between two images is established in the presence of intensity variations, inherent noise and motion blur using a fuzzy set theoretic similarity measure. The proposed matching algorithm needs to extract set of corner points as candidates from both the frames. Fuzzy set theoretic similarity measure is used here as fuzzy logic is a powerful tool which is able to deal with ambiguous data. Experimental results conducted with the help of various test images show that the proposed approach is superior compared existing corner matching algorithms (conventional and recent) considered in this paper under non-ideal conditions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: ____________________________________________________________mentioning

confidence: 99%

Efficient Fuzzy Set Theoretic Approach to Image Corner Matching

Dutta

2015

IJRITCC

View full text Add to dashboard Cite

show abstract

“…al. [1] present an iterative corner extraction and matching method for aligning images in two-dimensional mosaics. Peleg et.…”

Section: Related Workmentioning

confidence: 99%

“…Recent image mosaicing techniques attempt to deal with parallax by 1) restricting the camera motion [1], 2) using adaptive manifolds [16], 3) dividing the scene into planar sub-scenes [6], or 4) recovering dense depth maps [4,12,30,9]. Image mosaicing is especially relevant within the context of aerial imagery, where one is oftentimes faced with the challenge of visualizing and understanding the image data captured over vast areas by one or more aerial vehicles.…”

Section: Introductionmentioning

confidence: 99%

Constructing image mosaics using focus based depth analysis

Helala

Qureshi

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Image alignment techniques have gained popularity for constructing image mosaics from video sequences. These image alignment techniques, however, have a hard time dealing with motion parallax, which limits their applicability. This paper studies image mosaicing in the presence of motion parallax and develops a new algorithm for generating view dependent image mosaics from low-flying aerial video sequences exhibiting strong parallax effects. Specifically we develop an energy minimization framework that computes a dense depth map of the scene from a sequence of images (captured by an uncalibrated camera following an unknown trajectory), which in turn can be used to generate a panoramic mosaic through view interpolation. We evaluate our algorithm on real and synthetic aerial video sequences and show that the proposed algorithm can construct high quality image mosaics even in the presence of strong parallax.

show abstract

“…Authors compared the performance of normalized mutual information (NMI) as a window similarity measure to that of two other measures, namely normalized crosscorrelation (NCC) and sum of squared differences (SSD). Alkaabi and Deravi (2005) presented a rapid and automatic iterative corner extraction and matching for 2D mosaic construction. The algorithm combined corner extraction, matching, and transformation parameters estimation into an iterative scheme.…”

Section: Related Workmentioning

confidence: 99%