A New Method for Feature Point Matching: Inner and Exterior Product

In this paper, a novel feature descriptor called gradient correlation descriptor (GCD) is proposed. The GCD descriptor uses the gradient correlation measure defined by the inner and exterior product to characterize the gradient distributions in neighborhoods of feature points, and it has the following advantages: Its construction is very simple because of only the inner and exterior product operations are used; Its distinctive performance is better than the region-based SIFT descriptors since the gradient correlation measure can effectively characterize the gradient distributions in neighborhoods of feature points; In the gradient correlation measure the use of gradient mean makes it is not sensitive to the estimate precision of main orientation of feature point, and thus can provide a better stabilization to image rotation; The gradient correlation measure makes it also has very good adaptability to image affine transform, image blur, JPEG compression as well as illumination change.

Download Full-text

Non-Uniform SURF Feature Point Detection and Matching

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.284-287.3184 ◽

2013 ◽

Vol 284-287 ◽

pp. 3184-3188

Author(s):

Yea Shuan Huang ◽

Zhi Hong Ou ◽

Hung Hsiu Yu ◽

Hsiang Wen Hsieh

Keyword(s):

Moving Objects ◽

Salient Feature ◽

Feature Point ◽

Feature Descriptor ◽

Feature Points ◽

Point Matching ◽

Point Mapping ◽

Feature Point Extraction ◽

Feature Point Matching ◽

Point Detection

This paper presents a method for detecting feature points from an image and locating their matching correspondence points across images. The proposed method leverages a novel rapid LBP feature point detection to filter out texture-less SURF feature points. The detected feature points, also known as Non-Uniform SURF feature points, are used to match corresponding feature points from other frame images to reliably locate positions of moving objects. The proposed method consists of two processing modules: Feature Point Extraction (FPE) and Feature Point Mapping (FPM). First, FPE extracts salient feature points with Feature Transform and Feature Point Detection. FPM is then applied to generate motion vectors of each feature point with Feature Descriptor and Feature Point Matching. Experiments are conducted on both artificial template patterns and real scenes captured from moving camera at different speed settings. Experimental results show that the proposed method outperforms the commonly-used SURF feature point detection and matching approach.

Download Full-text

Robust Wide Baseline Feature Point Matching Based on Scale Invariant Feature Descriptor

Lecture Notes in Computer Science - Advanced Intelligent Computing Theories and Applications. With Aspects of Theoretical and Methodological Issues ◽

10.1007/978-3-540-87442-3_42 ◽

2008 ◽

pp. 329-336 ◽

Cited By ~ 2

Author(s):

Sicong Yue ◽

Qing Wang ◽

Rongchun Zhao

Keyword(s):

Feature Point ◽

Feature Descriptor ◽

Scale Invariant ◽

Point Matching ◽

Invariant Feature ◽

Feature Point Matching ◽

Scale Invariant Feature

Download Full-text

Image Mosaics Algorithm Combined Feature Point Matching with Transformation Parameters

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.380-384.4136 ◽

2013 ◽

Vol 380-384 ◽

pp. 4136-4139

Author(s):

Peng Rui Qiu ◽

Ying Liang ◽

Hui Rong

Keyword(s):

Projective Transformation ◽

Feature Point ◽

Image Mosaic ◽

Feature Points ◽

Geometric Information ◽

Point Matching ◽

Feature Point Matching ◽

Transformation Parameters ◽

Relationship Of ◽

The Relationship

To solve the problem of the large amount of calculation, poor robustness and do not well in image mosaic of images who are in different scales in the traditional image mosaic method ,the article arise a mosaic algorithm of different scales images registration and adaptive. Through feature point matching and automatically recognizing of transform geometric parameters between images,It achieves the match and mosaic of different scale and rotated images. First, using SIFT to extract the feature points of the images and matching feature points according to the principal of mutual information maximum. Then based on the geometric information of the matching pairs, automatically recognize the relationship of transformation parameters. In the end, obtain the projective transformation and achieve the image stable mosaic.

Download Full-text

Unusual Event Detection using Mean Feature Point Matching Algorithm

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v6i4.10179 ◽

2016 ◽

Vol 6 (4) ◽

pp. 1595 ◽

Cited By ~ 1

Author(s):

Chitra Hegde ◽

Shakti Singh Chundawat ◽

Divya S N

Keyword(s):

Input Image ◽

Feature Point ◽

Experimental Result ◽

Feature Points ◽

Surveillance Video ◽

Point Matching ◽

Public And Private ◽

Unusual Event ◽

Speeded Up Robust Features ◽

Feature Point Matching

Analysis and detection of unusual events in public and private surveillance system is a complex task. Detecting unusual events in surveillance video requires the appropriate definition of similarity between events. The key goal of the proposed system is to detect behaviours or actions that can be considered as anomalies. Since suspicious events differ from domain to domain, it remains a challenge to detect those events in major domains such as airport, super malls, educational institutions etc. The proposed Mean Feature Point Matching (MFPM) algorithm is used for detecting unusual events. The Speeded-Up Robust Features (SURF) method is used for feature extraction. The MFPM algorithm compares the feature points of the input image with the mean feature points of trained dataset. The experimental result shows that the proposed system is efficient and accurate for wide variety of surveillance videos.

Download Full-text