Distributed vision computing method based on open type Web Service framework

Abstract

The invention relates to a distributed vision computing method based on an open type Web Service framework. The method has the technical scheme of: collecting the video image of an identified target by adopting an embedded video collecting front end, and sending the video image back to a data center through network multicast; a computing server is controlled by a control server in the data centerto accomplish the computing task, and carrying out the uncompressing, target detecting, image preprocessing, feature extraction, identification, classification and result drawing of video data; and integrating the computing results. The method solves the defect of difficult compatibility with other systems. Under the uniform scheduling of the control server, the method avoids a great deal of unnecessary matching calculation, improves the performance of system operation, achieves the compatibility with most of databases and simply updated external systems, and realizes the identification and calculation of large-scale databases by adopting a packet mode.

Description

technical field [0001] The invention relates to a distributed computer vision computing method, in particular to a distributed visual computing method based on an open WebService architecture. Background technique [0002] Vision-based biometric recognition technology is one of the important contents in the field of public security. After a long period of development, all vision-based recognition systems can be realized according to a unified framework, that is, according to target detection, image preprocessing, and feature extraction. and target recognition in four steps. Target detection mainly completes the judgment of whether there is a target in the image and preliminary positioning; preprocessing usually includes precise positioning, normalization of scale and brightness, in order to extract effective features; feature extraction is based on the final recognition purpose to extract the most favorable for recognition information; target recognition is to select a suit...

AI Technical Summary

Problems solved by technology

However, since the completion of the calculation process is still carried out on a server machine, there is no essential difference from the single computer method

With the urgent need for large-scale data processing in practical applications, this computing model based on a single computer is difficult to meet the actual needs

Although there have been large-scale face recognition systems using distributed computing such as TH-ID Face, these recognition systems only use distributed computing to improve parallelism and system performance, and do not fully consider cross-platform applications and compatibility with other systems. Practical issues, still can not meet the actual application needs of public security

Images