A Target Recognition and Angle Coarse Estimation Algorithm Using Spatial Sparse Coding

Abstract

The present invention provides a target recognition and angle rough estimation algorithm using spatial sparse coding. Firstly, images of equally spaced angles (15°) of different targets are taken as training sets, and spatial fragments of each image are acquired and screened according to the standard deviation; then For the fragments in each independent image, preprocessing of whitening and PCA is performed; then the dictionary (sub-dictionary) of each target is trained separately using spatial fragmentation; after removing useless bases in each sub-dictionary, the sub-dictionary as a whole Merge into a large dictionary, use this large dictionary to retrieve the sparse coding coefficients of the training set image fragments, and count the number of times the fragments in each image use each base in the large dictionary, as the feature vector of each training image; finally By calculating the correlation coefficient between the base use count vector (feature vector) of the test target image in the large dictionary and the feature vector of each image in the training set, the target classification and rough estimation of the angle are realized.

Description

technical field [0001] The invention relates to a digital image processing technology, in particular to a target recognition and angle rough estimation algorithm using space sparse coding. Background technique [0002] When the human eye recognizes and classifies objects, there are several parameters: color, shape, position, attitude, lighting conditions, observation points, interference or noise distribution, etc. In the context of big data, how to effectively abstract these parameters has become the primary problem of object recognition and classification. Sparse representation is currently a more effective method to deal with this problem. [0003] For computer vision applications, traditional methods include DCT, wavelet, etc. The above methods aim to use a large number of images to train an over-complete dictionary and then perform sparse coding on the target image. The obtained dictionary is pre-set, and it is very difficult to manually set a good dictionary. In addit...

AI Technical Summary

Problems solved by technology

However, PCA has strict requirements on the "base" in the dictionary, which must be strictly orthogonal, which limits the flexibility of problem solving. Sparse expression comes from this, and sparse coding expresses the original signal as a linear combination of dictionary elements.

Images