基于毫米波雷达的城市室外人群情绪识别模型构建方法  

A Millimetre-Wave Radar-Based Method for Developing an Emotion Recognition Model for Urban Outdoor Crowds

作　　者：崔鸿基 韩昀松[1] 庄典 张启惠 CUI Hongji;HAN Yunsong;ZHUANG Dian;ZHANG Qihui(Candidate,Harbin Institute of Technology;Southeast University)

机构地区：[1]哈尔滨工业大学 [2]东南大学

出　　处：《世界建筑》2025年第3期71-77,共7页World Architecture

基　　金：国家自然科学基金,项目批准号:52422801。

摘　　要：城市室外人群情绪识别是优化城市空间设计、改善室外人群心理健康的关键。本研究旨在融合毫米波雷达与深度学习技术,创新城市室外人群情绪识别模型构建方法,并以严寒地区典型城市公共空间为例展开实践验证。结果表明:所构建的情绪识别模型对愤怒、放松、兴奋、悲伤情绪识别的准确率分别为95.9%、98.2%、89.5%和98.9%,总体准确率达95.6%。Emotion recognition of urban outdoor crowds is key to optimising the design of urban spaces and improving the mental health of outdoor crowds.The study aims to integrate millimetre wave radar with deep learning technology to innovate the method of constructing an emotion recognition model for urban outdoor crowds,and to take typical urban public spaces in cold regions as examples for practical validation.The results show that the accuracy of the constructed emotion recognition model for anger,relaxation,excitement,and sadness is 95.9%,98.2%,89.5%,and 98.9%respectively,with an overall accuracy of 95.6%.

关 键 词：人群情绪识别 毫米波雷达 城市街区 空间具身感知 计算性设计 

分 类 号：TU984.12[建筑科学—城市规划与设计] TU984