A Rapid and Efficient Feature Point Detection and Matching Algorithm

2014 ◽  
Vol 607 ◽  
pp. 641-646
Author(s):  
Xiao Ling Ding ◽  
Qiang Zhao ◽  
Yi Bin Li ◽  
Xin Ma
Keyword(s):  
Computer Vision ◽  
Vision Research ◽  
Feature Detection ◽  
Feature Point ◽  
Sift Algorithm ◽  
Matching Algorithm ◽  
Object Feature ◽  
Point Detection ◽  
Real Time Application ◽  
Fast Detector

In the field of computer vision research, object feature detection and matching algorithm become a hot. Aiming at SIFT algorithm and SURF algorithm cannot meet the needs of real-time application, a feature point detection and matching algorithm based on orient FAST detector and rotation BRIEF descriptor is used. The experiments demonstrate that, this method not only remains the advantages of SURF but also improves the detection speed, and it can fully applicable to the field of computer vision to detect moving targets.

Analysis and Research of Stereo Correspondence Algorithms

2014 ◽  
Vol 568-570 ◽  
pp. 768-772
Author(s):  
Yan Yun Li ◽  
Zhao Hui Liu ◽  
Liang Zhou
Keyword(s):  
Computer Vision ◽  
Vision Research ◽  
Stereo Matching ◽  
Technology Development ◽  
Stereo Correspondence ◽  
Matching Algorithm ◽  
Binocular Stereo ◽  
Key Techniques

Stereo matching has been the focus of computer vision research. Some current researches on stereo matching algorithms were summarized, the stereo matching key techniques were analyzed; View of the current major challenges on binocular stereo matching, elaborated matching algorithm possible solutions and modification approaches; Finally, the field of technology development are prospected.

Study on Infrared Thermography Mosaic Algorithm Based on the Feature Point Detection and Registration

2012 ◽  
Vol 594-597 ◽  
pp. 1138-1142
Author(s):  
Ji Tong Jiang ◽  
Chao Song ◽  
Jun An
Keyword(s):  
Image Fusion ◽  
Infrared Thermography ◽  
Feature Detection ◽  
Feature Point ◽  
Thermal Method ◽  
Image Mosaic ◽  
Image Transformation ◽  
Feature Registration ◽  
Infrared Thermograph ◽  
Point Detection

When detecting the large objects by infrared thermal method, it is difficult to get a whole panoramic picture. So it needs to stitch some infrared thermography. Image mosaic includes 4 steps, feature detection, feature registration, image transformation and image fusion. This paper studies about an infrared thermograph mosaic algorithm based on the feature point detection and registration, and realizes it in MATLAB.

scholarly journals Tri-SIFT: A Triangulation-Based Detection and Matching Algorithm for Fish-Eye Images

Information ◽  
2018 ◽  
Vol 9 (12) ◽  
pp. 299
Author(s):  
Ende Wang ◽  
Jinlei Jiao ◽  
Jingchao Yang ◽  
Dongyi Liang ◽  
Jiandong Tian
Keyword(s):  
Computer Vision ◽  
Camera Model ◽  
Scale Invariant ◽  
Keypoint Matching ◽  
Sift Algorithm ◽  
Matching Algorithm ◽  
Orientation Histogram ◽  
Angle Of View ◽  
Scale Invariant Feature ◽  
Fish Eye

Keypoint matching is of fundamental importance in computer vision applications. Fish-eye lenses are convenient in such applications that involve a very wide angle of view. However, their use has been limited by the lack of an effective matching algorithm. The Scale Invariant Feature Transform (SIFT) algorithm is an important technique in computer vision to detect and describe local features in images. Thus, we present a Tri-SIFT algorithm, which has a set of modifications to the SIFT algorithm that improve the descriptor accuracy and matching performance for fish-eye images, while preserving its original robustness to scale and rotation. After the keypoint detection of the SIFT algorithm is completed, the points in and around the keypoints are back-projected to a unit sphere following a fish-eye camera model. To simplify the calculation in which the image is on the sphere, the form of descriptor is based on the modification of the Gradient Location and Orientation Histogram (GLOH). In addition, to improve the invariance to the scale and the rotation in fish-eye images, the gradient magnitudes are replaced by the area of the surface, and the orientation is calculated on the sphere. Extensive experiments demonstrate that the performance of our modified algorithms outweigh that of SIFT and other related algorithms for fish-eye images.

Feature Detection by Color Tensor-Based Photometric Invariants

2011 ◽  
Vol 341-342 ◽  
pp. 540-545
Author(s):  
Xing Sheng Yuan ◽  
Zheng Zhi Wang
Keyword(s):  
Computer Vision ◽  
Real World ◽  
Vision Research ◽  
Feature Detection ◽  
Invariant Features ◽  
Photometric Invariance ◽  
Invariance Theory ◽  
Photometric Invariants

Although the majority of images are recorded in color format nowadays, computer vision research is still mostly restricted to luminance-based feature detection. In this paper, we combine the features based on the color tensor with photometric invariant derivatives to arrive at photometric invariant features. The combination of the photometric invariance theory and tensor based features allows for detection of a variety of features such as photometric invariant edges, corners. Experiments show that the proposed features are robust to scene incidental events and perform well in real-world scene.

scholarly journals Illumination-Invariant Feature Point Detection Based on Neighborhood Information

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6630
Author(s):  
Ruiping Wang ◽  
Liangcai Zeng ◽  
Shiqian Wu ◽  
Wei Cao ◽  
Kelvin Wong
Keyword(s):  
Feature Detection ◽  
Detection Method ◽  
Experimental Results ◽  
Feature Point ◽  
Detection Methods ◽  
Feature Points ◽  
Illumination Invariant ◽  
Neighborhood Information ◽  
Invariant Feature ◽  
Point Detection

Feature point detection is the basis of computer vision, and the detection methods with geometric invariance and illumination invariance are the key and difficult problem in the field of feature detection. This paper proposes an illumination-invariant feature point detection method based on neighborhood information. The method can be summarized into two steps. Firstly, the feature points are divided into eight types according to the number of connected neighbors. Secondly, each type of feature points is classified again according to the position distribution of neighboring pixels. The theoretical deduction proves that the proposed method has lower computational complexity than other methods. The experimental results indicate that, when the photometric variation of the two images is very large, the feature-based detection methods are usually inferior, while the learning-based detection methods performs better. However, our method performs better than the learning-based detection method in terms of the number of feature points, the number of matching points, and the repeatability rate stability. The experimental results demonstrate that the proposed method has the best illumination robustness among state-of-the-art feature detection methods.

Research on the SIFT Algorithm in Image Matching

2011 ◽  
Vol 121-126 ◽  
pp. 4656-4660 ◽  
Author(s):  
Yuan Cong ◽  
Xiao Rong Chen ◽  
Yi Ting Li
Keyword(s):  
Image Matching ◽  
Feature Matching ◽  
Scale Space ◽  
Feature Point ◽  
Image Feature ◽  
Sift Algorithm ◽  
Matching Algorithm ◽  
Key Points ◽  
Point Neighborhood ◽  
Accurate Matching

SIFT feature matching algorithm is hot in the field of the currently feature matching research, its matching with the strong ability can deal with the translation, rotation, affine transformation occurring between images , and it also have a stable image feature matching ability to the images filmed at any angle. SIFT algorithm is adopted in this paper, matching feature point through the scale space , calculating the histogram of detecting feature point neighborhood of gradient direction characteristic vector and generation to SIFT eigenvector and the key points similarity measure. From different setting threshold, scale scaling, rotating, noise on the experiment, the experiment result proves this algorithm in the above aspects has good robustness, suitable for mass characteristic database of rapid, accurate matching.

scholarly journals Feature Extraction of Real-Time Image Using SIFT Algorithm

2020 ◽  
Vol 4 (3) ◽  
Author(s):  
Nellutla Sasikala ◽  
V. Swathipriya ◽  
M. Ashwini ◽  
V. Preethi ◽  
A. Pranavi ◽  
...  
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Feature Extraction ◽  
Stereo Matching ◽  
Vital Role ◽  
Sift Algorithm ◽  
Real Time Image ◽  
Point Detection ◽  
Performance Of Algorithm ◽  
Time Image

This paper deals with image processing and feature extraction. Feature extraction plays a vital role in the field of image processing. There exist different image pre-processing approaches for feature extraction such as binarization, thresholding, resizing, normalisation so on...Then after these techniques are applied to obtain high clarity images. In Feature extraction object recognition and stereo matching are at the base of many computer vision problems. The descriptor generator module is changed for increasing the performance of algorithm. SIFT algorithm consist of two modules such as key point detection module and descriptor generation module. When compared to recent solution, the descriptor generation module speed is fifteen times faster and the time for feature extraction is also reduced.

Sign in / Sign up

Export Citation Format

Share Document