Hierarchical human body analysis semantic segmentation method with edge constraint

Abstract

The invention discloses a hierarchical human body analysis semantic segmentation method with edge constraint, and mainly solves the problems of poor adaptability and insufficient acquisition of rich human body structure semantic context information in a complex analysis scene in the prior art. The method comprises the following steps: collecting and marking portrait data, and preprocessing training data in the portrait data; and constructing a hierarchical human body analysis semantic segmentation model with edge constraint, training and evaluating the model by using the preprocessed training data, and inputting a picture containing a human body into the trained hierarchical human body analysis semantic segmentation model with edge constraint and meeting the evaluation requirement to obtain a segmentation result picture. According to the method, the edge feature information of the human body analysis semantic segmentation task can be constrained, the phenomena of wrong division and missing division of the human body image by the human body analysis semantic segmentation model in a complex scene are improved, the effect of human body analysis semantic segmentation is effectively improved, and the method can be used for real-time early warning of an intelligent security and protection system and virtual reality reloading of electronic commerce.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a hierarchical human body analysis and semantic segmentation method, which can be used for real-time early warning of intelligent security systems and virtual reality dressing of e-commerce. Background technique [0002] With the rapid development of intelligent security and virtual reality industries, the business demand for human body analysis is also increasing. In recent years, with the intelligentization of security products, the security system with the human body as the monitoring entity, such as smart communities and smart streets, has played an important role in the process of cracking down on crimes and improving people's sense of security due to their independent judgment and real-time early warning. role. It mainly uses human body analysis technology to segment the portraits in key monitoring areas, which is used to assist in monitoring abnormal ...

AI Technical Summary

Problems solved by technology

Although these methods can improve the adaptability of the model through feature message transmission, they cannot obtain richer human body structure semantic information due to the single layer and insufficient use of human body structure information for transmission, and the segmentation effect is not good.

Images