A gesture recognition method based on address event flow characteristics

Abstract

The invention discloses a gesture recognition method based on address event flow characteristics. The gesture recognition method is mainly used for solving the gesture recognition problem under a complex background. The implementation scheme comprises the following steps of (1) collecting the address event flow data; (2) de-noising each address event flow sequence; (3) confirming a peak address event flow sequence; (4) detecting a characteristic event of the peak address event flow sequence; (5) extracting local invariant features of the feature event; (6) screening local invariant features ofthe effective gesture; (7) training a support vector machine SVM classifier; (8) classifying;. According to the method, the asynchronous characteristic of the address event is reserved, non-effectivegesture characteristic calculation is reduced, and only the characteristic event is subjected to characteristic extraction. The method has the advantages of high accuracy and strong applicability.

Description

technical field [0001] The invention belongs to the technical field of physics, and further relates to a gesture recognition method based on address event flow characteristics in the technical field of signal processing. The present invention pre-sets gesture types with meanings of different motion modes, and recognizes the set gesture types under different complex background environments of virtual reality and human-computer interaction. Background technique [0002] Human-computer interaction mainly relies on mechanical devices such as keyboards, mice, and touch screens. Although this traditional computer-centered touch method is widely and proficiently used in daily life, a new human-centered interaction method that is natural, intuitive, and more in line with people's daily habits has gradually become the mainstream trend. One of the mainstream trends is gesture recognition technology. [0003] Vision-based gesture recognition can enable operators to interact with huma...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that since the method does not perform data screening and calculates all data, there is a problem of huge amount of calculation and heavy processing burden.

However, the disadvantage of this method is that in order to use the existing processing mode to convert the event stream into an image frame and extract the features in the image frame for recognition, the asynchronous characteristics of the address event are not really preserved.

Although the method is simple to operate, the disadvantage of this method is that it is easily affected by skin-like objects, resulting in a high recognition error rate. It is only suitable for specific gestures in simple environments, and its applicability is not strong.

Images