Local convolutional features and metric learning for SAR image registration

Guo, Qiang; Xiao, Jin; Hu, Xin; Zhang, Baochang

doi:10.1007/s10586-018-1946-0

Cited by 5 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the true match error is within 3 pixels, the keypoint pair is deemed to be the right match. (5) if N kp > 1 then (6) Split child node (7) else then (8) Store child node (9) else then (10) Store child node (11) else then (12) if N store > N set then (13) Store the point which has the largest response in each node (14) Figure 3. Its basic principle is to use the mathematical characteristics between the number of feature points in the same area of various shapes of the image to measure the distribution of feature points.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Image registration plays an important role in computer vision. Image registration is widely used in many aspects such as image matching [1][2][3][4][5][6][7], change detection [8,9], 3D reconstruction [10][11][12], guidance [13][14][15], mapping sciences [16][17][18][19][20][21], and mobile robot [22,23]. In general, image registration methods can be mainly divided into two kinds: gray-scale matching methods and feature-based matching methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Homogenized ORB Algorithm Using Dynamic Threshold and Improved Quadtree

Xiao

2021

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

The Oriented FAST and Rotated BRIEF (ORB) algorithm has the problem that the extracted feature points are overconcentrated or even overlapped, leading to information loss of local image features. A homogenized ORB algorithm using dynamic thresholds and improved quadtree method is proposed in this paper, named Quadtree ORB (QTORB). In the feature point extraction stage, a new dynamic local threshold calculation method is proposed to enhance the algorithm’s ability to extract feature points at homogeneous regions. Then, a quadtree method is improved and adopted to manage and optimize feature points to eliminate those excessively concentrated and overlapping feature points. Meanwhile, in the feature points optimization process, different quadtree depths are set at different image pyramid levels to prevent excessive splitting of the quadtree and increase calculation speed. In the feature point description stage, local gray difference value information is introduced to enhance the saliency of the feature description. Finally, the Hamming distance is used to match points and RANSAC is used to avoid mismatches. Two datasets, namely, the optical image dataset and SAR image dataset, are used in the experiment. The experimental result shows that, considering accuracy and real-time efficiency, the QTORB can effectively improve the distribution uniformity of feature points.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Homogenized ORB Algorithm Using Dynamic Threshold and Improved Quadtree

Xiao

2021

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, in some applications, hybrid methods are considered as well [11, 12]. ABM methods are more appropriate for dense matching, while FBM methods are the most suitable for sparse matching [13]. In overlapping images, these methods are used in finding an optimal spatial transformation to match the feature point coordinates, one after the other.…”

Section: Introductionmentioning

confidence: 99%