Gesture recognition system based on FPGA and recognition method thereof

Abstract

The invention relates to a gesture recognition system realized based on an FPGA and a recognition method thereof. The gesture recognition system comprises a CMOS camera data acquisition module, an FPGA data processing module, a DDR3 storage module and a VGA display module. The CMOS camera is connected with the FPGA, and driving of a camera is completed in an FPGA chip. After video data collected by the camera enters the FPGA chip, the data is cached in a DDR3 storage module under the action of a data read-write control module and is read out under the action of the data read-write control module. And the character drive and video superposition module superposes the identification content with the gesture image in the form of characters in real time according to the identification results of the static gesture and the dynamic gesture and then sends the superposed identification content to the VGA display module for display. Compared with the prior art, the invention effectively solves the problem of unstable gesture recognition and the problem of real-time performance of gesture recognition in complex environments such as insufficient illumination and skin color-like interference.

Description

technical field [0001] The invention relates to the technical field of image processing and the field of human-computer interaction, in particular to an FPGA-based gesture recognition system and a recognition method thereof. Background technique [0002] Gesture recognition technology is one of the research hotspots in the field of human-computer interaction. With the support of gesture recognition technology, interactive devices such as computers and robots can be controlled more naturally and efficiently. [0003] Gesture recognition can be divided into two types: static gesture recognition and dynamic gesture recognition. Most existing solutions are designed for static gestures or dynamic gestures only. In gesture recognition, there are very few methods that can handle both static and dynamic gestures. The algorithm proposed by the invention solves the problem of gesture recognition in complex environments, and at the same time can freely switch between static gesture ...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the object of the present invention is to provide a gesture recognition system and recognition method thereof based on FPGA, realize static gesture recognition and dynamic gesture recognition simultaneously by using HOG feature and SVM classifier on the FPGA platform, and provide an effective The human-computer interaction method effectively solves the problem of unstable gesture recognition and the real-time problem of gesture recognition in complex environments such as insufficient lighting and skin-color interference

Images