旋轉不變梯度直方圖目標描述方法

諶德榮; 王文斌; 劉丙太; 姜威; 俞達; 宮久路

doi:10.11999/JEIT150546

旋轉不變梯度直方圖目標描述方法

doi: 10.11999/JEIT150546

1.
(北京理工大學機電工程與控制國家重點實驗室北京 100081) ②(北京宇航系統(tǒng)工程研究所北京 100076)

基金項目:

國家部委基金，北京理工大學基礎研究基金

計量
- 文章訪問數: 1694
- HTML全文瀏覽量: 221
- PDF下載量: 1078
- 被引次數: 0
出版歷程
- 收稿日期: 2015-05-11
- 修回日期: 2015-09-16
- 刊出日期: 2016-01-19

Rotation-invariant Histogram of Oriented Gradients for Target Description

1.
(National Laboratory for Mechatronic and Control, Beijing Institute of Technology, Beijing 100081, China)
2.
(Beijing Institute of Astronautical Systems Engineering, Beijing 100076, China)

Funds:

The Foundations of General Armament Department, Funds of Beijing Institute of Technology

摘要

摘要: 論文為解決旋轉目標圖像匹配問題，提出旋轉不變梯度直方圖(RI-HOG)目標描述方法。RI-HOG描述方法首先將目標區(qū)域等間隔劃分為多個同心圓環(huán)并統(tǒng)計每個圓環(huán)的梯度直方圖(HoG)，各圓環(huán)HoG累加的結果作為目標區(qū)域的主方向，再將各圓環(huán)HoG根據主方向旋轉相應角度作主方向歸一化處理，最后把旋轉后的各圓環(huán)HoG按空間順序連接后即生成RI-HOG。對實際采集圖像的仿真結果表明，基于RI-HOG的目標匹配算法在目標旋轉任意角度時依然能夠準確檢測到目標。RI-HOG具有很好的旋轉不變性。
- 自動目標識別 /
- 特征描述方法 /
- 梯度直方圖 /
- 旋轉不變性
Abstract: A rotation-invariant feature descripts method called Rotation Invariant Histogram of Oriented Gradients (RI-HOG) is proposed for automatic target recognition. RI-HOG calculates gradient of image first, then the image window is divided into a set of un-overlapped annular regions, called sells, and the Histogram of Gradient (HoG) is used to calculate a feature vector for each cells. After that the HoG of each circle is accumulated to get the main angle of the target area, and then it is rotated due to the main angle to make a normalization of the main angle. At last, the HoG of each circle after rotating is linked to generate the rotation-invariant target feature vector. Experiment results show that target detection method using RI-HOG can find the target under arbitrary rotations. RI-HOG is a rotation-invariant target feature descriptor.
- Automatic target recognition /
- Feature description method /
- Histogram of Gradient (HoG) /
- Rotation invariant

HTML全文

參考文獻(17)

顏雪軍, 趙春霞, 袁夏. 一種魯棒的基于圖像對比度的局部特征描述方法[J]. 電子與信息學報, 2014, 36(4): 882-887. doi: 10.3724/SP.J.1146.2013.00846.

YAN Xuejun, ZHAO Chunxia, and YUAN Xia. A robust local feature descriptor based on image contrast[J]. Journal of Electronics Information Technology, 2014, 36(4): 882-887. doi: 10.3724/SP.J.1146.2013.00846.

TUYTELAARS T and MIKOLAJCZYK K. Local invariant feature detectors: a survey[J]. Foundations and Trends? in Computer Graphics and Vision, 2008, 3(3): 177-280.　

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

BAYA H, ESSA A, TUYTELAARS T, et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

DALAL N and TRIGGS B. Histograms of oriented gradients for human detection[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, 2005: 886-893.

FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.

SADEGHI M A and FORSYTH D. 30 Hz object detection with DPM V5[C]. European Conference on Computer Vision, Zurich, Switzerland, 2014: 65-79.

HARIHARAN B, ZITNICK C L, and DOLL?AR P. Detecting objects using deformation dictionaries[C]. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, 2014: 1995-2002.

AHMED E, SHAKHNAROVICH G, and MAJI S. Knowing a good HOG filter when you see it: efficient selection of filters for detection[C]. European Conference on Computer Vision, Zurich, Switzerland, 2014: 80-94.

PONCE C and SINGER A. Computing steerable principal components of a large set of images and their rotations[J]. IEEE Transactions on Image Processing, 2011, 20(11): 3051-3062.

SCHMIDT U and ROTH S. Learning rotation-aware features: from invariant priors to equivariant descriptors[C]. IEEE Conference on Computer Vision and, Pattern Recognition, Providence, RJ, USA, 2012: 2050-2057.

TAKACS G, CHANDRASEKHAR V, TSAI S, et al. Unified real-time tracking and recognition with rotation-invariant fast features [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, 2010: 934-941.

TAKACS G, CHANDRASEKHAR V, TSAI S S, et al. Fast computation of rotation-invariant image features by an approximate radial gradient transform[J]. IEEE Transactions on Image Processing, 2013, 22(8): 2970-2982.

謝志江, 呂波, 劉琴, 等. 旋轉不變性圖像模板匹配快速算法[J]. 吉林大學學報(工學版), 2013, 43(3): 711-717.

XIE Zhijiang, LU Bo, LIU Qin, et al. Rotation-invariant and fast image template matching algorithm[J]. Journal of Jilin University (Engineering and Technology Edition), 2013, 43(3): 711-717.

GAUGLITZ S, TURK M, and HLLERER T. Improving keypoint orientation assignment[C]. British Machine Vision Conference, Dundee, Scotland, 2011: 93.1-93.11.

施引文獻

資源附件(0)

訪問統(tǒng)計