FPGA (Field Programmable Gate Array)-based SIFT (Scale Invariant Feature Transform) image feature extraction system

Abstract

The invention provides an FPGA (Field Programmable Gate Array)-based SIFT (Scale Invariant Feature Transform) image feature extraction system, which comprises a kilomega network module, a Gaussian filtering cascading and Gaussian difference module, a gradient computation module, an extreme point detection module and a principal direction and feature descriptor, wherein the kilomega network module is connected with the Gaussian filtering cascading and Gaussian difference module, the Gaussian filtering cascading and Gaussian difference module is simultaneously connected with the gradient computation module and the extreme point detection module, and the principal direction and feature descriptor is simultaneously connected with the gradient computation module and the extreme point detection module. The invention is an image rectification preprocessing system which can precisely extract target feature information in real time.

Description

technical field [0001] The invention belongs to the technical field of image registration, and in particular relates to an FPGA-based SIFT image feature extraction system. Background technique [0002] In the moving target detection and tracking system, the quality requirements for the extracted image feature points are relatively high. During the actual processing, if the captured video image changes on a certain scale, the feature point matching will be deviated. [0003] Using SIFT feature extraction algorithm can improve the accuracy of feature point extraction. For example: Document 1 (Yan Ke, Rahul Sukthankar. PCA-SIFT: a more distinctive representation for local image descriptors [C]. Proc Conf Computer Vision and Pattern Recognition, 2004: 511-517) proposed an improved method based on the SIFT algorithm, This method uses PCA (Principal Component Analysis) to reduce the dimensionality of feature descriptors, and uses block filtering (Boxlet) and integral images to r...

AI Technical Summary

Problems solved by technology

For example: Document 1 (Yan Ke, Rahul Sukthankar. PCA-SIFT: a more distinctive representation for local image descriptors [C]. Proc Conf Computer Vision and Pattern Recognition, 2004: 511-517) proposed an improved method based on the SIFT algorithm, This method uses PCA (Principal Component Analysis) to reduce the dimensionality of feature descriptors, and uses block filtering (Boxlet) and integral images to replace the computationally complex Gaussian filtering in the original method, which reduces the complexity of the method, but the method is It is implemented on a software platform, so the real-time performance is poor; Document 2 (Xu Fei, Liu Wei. Algorithm optimization under multi-core [J]. Information Communication, 2012, 121(5): 42-46) proposed a multi-core based on TI The method of implementing SITF algorithm on C6000DSP chip, using multi-core DSP can improve the operation accuracy of SIFT algorithm, and has strong portability, but this method takes up a lot of memory resources, and the real-time performance has not been completely improved

Images