The Feature Extraction and Matching Algorithm Based on the Fire Video Image Orientation

Abstract:

Because the SIFT (scale invariant feature transform) algorithm can not accurately locate the flame shape features and computationally intensive, this article proposed a stereo video image fire flame matching method which is a combination of Harris corner and SIFT algorithm. Firstly, the algorithm extracts image feature points using Harris operator in Gaussian scale space and defines the main directions for each feature point, and then calculates the 32-dimensional feature vectors of each feature point descriptor and the Euclidean distance to match two images. Experimental results of image matching demonstrate that the new algorithm improves the significance of the shape of the extracted feature points and keep a better match rate of 96%. At the same time the time complexity is reduced by 27.8%. This algorithm has a certain practicality.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 3986-3989
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.3986
• Online since: August 2013
• Authors: Ying Lu, Hui Qin Wang, Fei Xu, Wei Guang Liu
• Keywords: Different of Gaussian, Feature Descriptor, Harris Corners, SIFT Feature Point, Stereo Matching

References

[1] Yin-an Feng, Ying- xian Li, Rui-ling Hou. image-type fire space positioning [J]. System simulation technology, 2009, 5 (03): 182-186.

[2] LOWE D G. Distinctive image features from scale invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

DOI: 10.1023/b:visi.0000029664.99615.94

[3] LOWE D G. Object recognition from local scale-invariant features[C]/ Proceedings of the International Conference on Computer Vision . Corfu, Greece: [s. n. ], 1999, 3(1): 150- 1157.

DOI: 10.1109/iccv.1999.790410

[4] Hao Meng, Kang Cheng. Binocular vision based on SIFT feature point positioning [J]. Harbin Engineering University, 2009, 30 (6): 649-652.

[5] Mikajczyk K，Schmid C. Scale ＆ affine invariant interest point detectors [J]. International Journal of Computer Vision(S0920-5691)，2004，60(1)：63-86.

DOI: 10.1023/b:visi.0000027790.02288.f2

[6] Qin-jun Zhao, Dong-biao Zhao, Hu Wei. Harris-SIFT algorithm and its binocular stereo vision [J]. University of Electronic Technology, 2010, 39 (4) : 546-550.

[7] Wen-ming Zhang, Bin Liu , Wei Lin , Hai-bin Li , based on three-dimensional reconstruction of the binocular visual feature point extraction and matching algorithms [J]. Optical Technology 2008 . 34 (02): 181-185.

[8] Ting RUI, Sheng-mi Zhang, You Zhou and so on. Has the SIFT described Harris corner multi-source image registration [J] Optical Engineering, 2012 . 39 (08): 26-31.

[9] Pedram Azad, Tamim Asfour, Rudiger Dillmann. Combining Harris Interest Points and the SIFT Descriptor for Fast Scale-Invariant Object Recognition. in IEEE International Conference on Intelligent Robots and Systems. St. Louis, USA, 2009, p.4275.

DOI: 10.1109/iros.2009.5354611