Model identification method based on local characteristic aggregation descriptor

Abstract

The invention discloses a model identification method based on a local characteristic aggregation descriptor. First of all, SIFT characteristics of vehicle images in a model database are extracted; then Kmeans clustering is performed on the SIFT characteristics of all the vehicle images so as to form K cluster centers and obtain a dictionary with K visual words; then, each SIFT characteristic is endowed with a closest visual word for each model image; a residual error cumulant between SIFT characteristic vectors around each visual word and current visual words is counted, and the local characteristic agglomeration descriptor of a current vehicle picture is obtained; finally, an indexable coding image database of n model types is obtained through quantification coding from local characteristic agglomeration descriptors of n model images of a training module; and for a test vehicle image, the local characteristic agglomeration descriptor of the test vehicle image is extracted in the same way as a query vector for introduction into an image database for indexing, and the model of a test vehicle is identified through matching by use of an approximation nearest neighbor search method.

Description

technical field [0001] The invention belongs to the technical field of pattern classification, and in particular relates to a vehicle type recognition method based on local feature aggregation descriptors. Background of the invention [0002] With the rapid development of information technology, more and more intelligent transportation systems have entered people's lives, such as automatic road toll collection systems, vehicle identification technology, electronic police systems, global positioning systems, and vehicle navigation systems. These intelligent transportation management systems are built by integrating the most cutting-edge software and hardware technologies, including data communication transmission technology, electronic control technology, electronic sensing technology and information technology. The intelligent transportation system needs to play an overall role in a large area, manage traffic in real time and efficiently, and finally realize the intelligent ...

AI Technical Summary

Problems solved by technology

[0005] Bag of visual words model encoding and Fisher vector encoding are widely used in image retrieval and classification, but in the case of a large amount of data, due to the limitation of the dictionary size, the feature expression of the visual bag of words model encoding will become rougher and rougher. There is a lot of loss of feature information, which reduces the search accuracy. Although Fisher vector coding can describe the picture in more detail, it also loses a lot of features.

Images