MATLAB Code For Object Detection in Image of a Cluttered Scene

Introduction:

The code uses the SURF local feature detector function to find the corresponding points between two images that are rotated and scaled with respect to each other and then extracts feature vectors (descriptors), and their corresponding locations, from a given binary or intensity image. The descriptors from pixels surrounding an interest point. The pixels represent and match features specified by a single-point location. Each single-point specifies the center location of a neighborhood. And finally, it finds corresponding interest points between a pair of images using the local SURF algorithm.

Code Input:

The code input is two images. The first contains plenty of objects and the second contains one object that we interested to find and match it with that in the first one. For example a lost book.

Code Output:

The code presents six images as an output. The first two images are the input themselves the code just presents them. The third image presents the descriptors on the interested image. the fourth and fifth images show matched lines between the given images. the final image shows a rectangular box around the matched object in the first image.

See The Video:

Click here.

Recommended Codes:

References:

[1] Lowe, David G. “Distinctive Image Features from Scale-Invariant Keypoints.” International Journal of Computer Vision. Volume 60, Number 2, pp. 91–110.

[2] Muja, M., and D. G. Lowe. “Fast Matching of Binary Features. “Conference on Computer and Robot Vision. CRV, 2012.

[3] Muja, M., and D. G. Lowe. “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration.” International Conference on Computer Vision Theory and Applications.VISAPP, 2009.

[4] Rublee, E., V. Rabaud, K. Konolige and G. Bradski. “ORB: An efficient alternative to SIFT or SURF.” In Proceedings of the 2011 International Conference on Computer Vision, 2564–2571. Barcelona, Spain, 2011.

[5] Bay, H., A. Ess, T. Tuytelaars, and L. Van Gool. “SURF:Speeded Up Robust Features.” Computer Vision and Image Understanding (CVIU).Vol. 110, No. 3, pp. 346–359, 2008.