Application of the gradient orientation for systems of automatic target detection
Borisova I.V., Legkiy V.N., Kravets S.A.


Novosibirsk State Technical University, Novosibirsk, Russia

Full text of article: Russian language.


In this paper, a problem of automatic target tracking in complex natural backgrounds is considered. Target detection is performed in each frame of a video sequence by the elementwise comparison with a reference image. The proposed method is based on the representation of every pixel as the orientation of the luminance gradient in the vicinity. The vicinities are divided into classes depending on their orientation. In addition to the classes of anisotropic vicinities, a class of vicinities with an isotropic structure is introduced. The classes are numbered and the number of the vicinity class is used as a feature of the point of interest. Thus, the original gray-scale image is transformed to a pseudo-image in which the detection procedure is carried out. The encoded image is then scanned using a reference image. The elementwise comparison of the reference image with the current fragment is performed in a feature space. As a result, a comparison matrix is formed, each element of which is the number of matching elements of the reference image and the current image fragment. The position of the reference image is determined by the maximum value of the comparison matrix. A special rule of reference image overwriting, the so-called dynamic proximity measure, is used to achieve stable tracking. The testing results have shown that with our approach the object tracking is more stable in comparison with the use of normalized correlation.

image processing, target detection, gradient orientation, reference image.

Borisova IV, Legkiy VN, Kravets SA. Application of the gradient orientation for systems of automatic target detection. Computer Optics. 2017; 41(6): 931-937. DOI: 10.18287/2412-6179-2017-41-6-931-937.


  1. Popov PG, Borisova IV. Practical use of the rebound effect in image processing. J Opt Technol 1999; 66(4): 360-366. DOI: 10.1364/JOT.66.000360.
  2. Haralick RM, Watson LT. A facet model for image data. Computer Graphics and Image Processing 1981; 15(2): 113-129. DOI: 10.1016/0146-664X(81)90073-3.
  3. Lowe DG. Object recognition from local scale-invariant features. Proc of the International Conference on Computer Vision 1999; 2: 1150-1157. DOI: 10.1109/ICCV.1999.790410.
  4. Dalal N, Triggs B. Histograms of oriented gradients for human detection. CVPR 2005; 1: 886-893. DOI: 10.1109/CVPR.2005.177.
  5. Miramontes-Jaramillo D, Diaz-Ramirez VH, Kober V, Karnaukhov V. A novel image matching algorithm based on sliding histograms of oriented gradients. Journal of Communications Technology and Electronics 2014; 59(12): 1446-1450. DOI: 10.1134/S1064226914120146.
  6. Lukashevich PV, Zalessky BA. Scale invariant algorithm for matching image regions [In Russian]. Informatics 2011; 3: 118-128.
  7. Haber E, Modersitzki J. Intensity gradient based registration and fusion of multi-modal images. MICCAI 2006; 9: 726-733. DOI: 10.1007/11866763_89.
  8. Blokhinov YuB, Chernyavskiy AS. The search for three-dimensional objects in images based on dynamically generated contour templates [In Russian]. Mechanics, Control and Informatics 2012; 2(8): 181-188.
  9. Baryskievic IA, Tsviatkou VYu. Adaptive covariance stabilization of video image [In Russian]. Doklady BGUIR 2015; 5(91): 60-66.
  10. Popov PG. Dynamical measure of the images relationship. Part II: Short-time memory and the control systems [In Russian]. Avtometriya 1994; 2: 47-54.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846)332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20