文献类型：期刊文献

英文题名：Recognition of Design Fixation via Body Language Using Computer Vision

作者：Yang, Zhongliang[1];Chen, Yumiao[2];Zhang, Song[3]

机构：[1]Donghua Univ, Coll Mech Engn, Shanghai 201620, Peoples R China;[2]East China Univ Sci & Technol, Sch Art Design & Media, Shanghai 200237, Peoples R China;[3]Univ Manchester, Dept Mat, Manchester M13 9PL, Lancs, England

年份：2021

卷号：2021

外文期刊名：MATHEMATICAL PROBLEMS IN ENGINEERING

收录：;EI(收录号：20213710888906);WOS:【SSCI(收录号:WOS:000695545400009)，SCI-EXPANDED(收录号:WOS:000695545400009)】；

基金：+is study was partly supported by the National Natural Science Foundation of China (no. 51905175), Shanghai Pujiang Talent Program (no. 2019PJC021), the Cooperative Education Program of Ministry of Education (no. 202002SZ05), and the Shanghai Soft Science Key Project (no. 21692196800).

语种：英文

外文关键词：Design - Computer vision - Convolutional neural networks

摘要：The main objective of this study is to recognize design fixation accurately and effectively. First, we conducted an experiment to record the videos of design process and design sketches from 12 designers for 15 minutes. Then, we executed a video analysis of body language in designers, correlating body language to the presence of design fixation, as judged by a panel of six experts. We found that three body language types were significantly correlated to fixation. A two-step hybrid recognition model of design fixation based on body language was proposed. The first-step recognition model of body language using transfer learning based on a pretrained VGG-16 convolutional neural network was constructed. The average recognition rate achieved by the VGG-16 model was 92.03%. Then, the frames of recognized body language were used as input vectors to the second-step fixation classification model based on support vector machine (SVM). The average recognition rate for the fixation state achieved by the SVM model was 79.11%. The impact of the work could be that the fixation can be detected not only by the sketch outcomes but also by monitoring the movements, expressions, and gestures of designers, as it is happening by monitoring the movements, expressions, and gestures of designers.