Pedestrian mask and three-dimensional scene fusion display method, terminal and storage medium

Abstract

The invention discloses a pedestrian mask and three-dimensional scene fusion display method, a terminal and a storage medium, and the method comprises the steps: dividing a target through the sample features of a pre-obtained sample image, calculating a first classification loss, dividing a prediction frame framing the target, and calculating a first boundary frame loss; identifying the category of the target, calculating a second classification loss, adjusting the prediction box based on the category to obtain a detection box, and calculating a second bounding box loss; classifying each pixelin the detection frame and calculating mask loss; constructing a novel loss function by utilizing the first classification loss, the second classification loss, the mask loss, the first bounding boxloss and the second bounding box loss; when the pedestrian image and the three-dimensional scene are fused and displayed, segmenting a pedestrian mask from the image by using a novel loss function, and then fusing the pedestrian mask to the three-dimensional scene. Through the above mode, a novel loss function can be constructed to optimize the pedestrian mask and the bounding box, so that the final display effect is better.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a method, terminal and storage medium for fused display of a pedestrian mask and a 3D scene. Background technique [0002] Pedestrian detection is the focus of research in the field of target detection, and it is the basis for follow-up research such as pedestrian recognition and pedestrian analysis. Pedestrian detection plays a key role in judging whether there are abnormal pedestrian intrusions in areas such as regional security monitoring systems and intelligent transportation. Pedestrian segmentation is an end-to-end network that detects each pedestrian and performs semantic segmentation. It not only needs to distinguish the category of each pixel at the pixel level, but also distinguishes each individual pedestrian at a more spatial location. The existing pedestrian segmentation is mainly divided into two categories, one is based on detection, there i...

AI Technical Summary

Problems solved by technology

[0004] This application provides a method, terminal and storage medium for fusion display of a pedestrian mask and a 3D scene to solve the problem that the existing pedestrian detection optimization effect is poor and the 3D fusion display effect is not ideal

Images