Pedestrian attribute identification method and system, computer equipment and storage medium

Abstract

The invention relates to a pedestrian attribute recognition method and system, computer equipment and a storage medium, and the method comprises the steps: extracting an image frame from a real-time video, inputting the image frame into a trained target detection model, and obtaining a pedestrian image outputted by the trained target detection model; inputting the pedestrian image into a trained pedestrian recognition model, and obtaining a classification result output by the trained pedestrian recognition model according to preset pedestrian attributes, wherein the preset pedestrian attributes comprise a gender attribute and an age attribute; and obtaining the number and proportion of pedestrians with different gender attributes and different age attributes according to the classificationresult. According to the invention, the pedestrian images can be extracted from the real-time video, the data of the pedestrian images are classified and counted to obtain pedestrian flow informationwith different attributes, and the popularity degree and popular groups of the sightseeing scenic spot are indirectly displayed by monitoring the pedestrian flow information with different attributes, and the traffic smoothness and the commercial service range can be reasonably planned.

Description

technical field [0001] The present application relates to the field of target detection, in particular to a method, system, computer equipment and storage medium for identifying attributes of pedestrians. Background technique [0002] Image target detection algorithm is an important research direction of deep learning. Before deep learning, traditional target detection mainly used manually marked features to generate candidate boxes through selective search, followed by classification and regression. Such algorithms include Viola-Jones face detection algorithm, support vector machine (SVM) and extended DPM (Deformable Parts Model) algorithm of HOG (Histograms of Oriented Gradients), etc. [0003] Object detection algorithms for static images based on deep learning are mainly developed from R-CNN detectors, which are developed from object candidate boxes generated by unsupervised algorithms and classified using convolutional neural networks. The model is scale-invariant, but...

AI Technical Summary

Problems solved by technology

[0010] The embodiment of the present application provides a pedestrian attribute identification method, system, computer equipment and storage medium, so as to at least solve the problems in the related art that pedestrians with different attributes in scenic spots cannot be effectively identified and the flow of pedestrians with various attributes cannot be effectively monitored. question

Images