激光与光电子学进展, 2019, 56 (16): 161503, 网络出版: 2019-08-05
基于特征密集计算与融合算法的教师课堂行为分析 下载: 769次
Analysis of Teachers' Actions Using Feature Dense Computation and Fusion Algorithm
机器视觉 卷积神经网络 时空金字塔池化 非局部计算 时空特征 行为分析 machine vision convolution neural network spatiotemporal pyramid pooling non-local computation spatiotemporal features analysis of actions
摘要
针对传统网络结构不能充分利用数据中时空信息的问题,提出了一种时空金字塔池化模型,并将该模型与非局部特征计算操作相结合,设计了一种基于时空信息密集计算与融合的三维密集连接卷积神经网络,从而可以更有效地提取视频的时空特征。将该算法应用于课堂场景下教师行为的分析,实验结果表明,所设计的网络结构在教师行为数据集上达到了较高的识别准确率。
Abstract
Considering the incapacity of the traditional network structure to fully extract spatiotemporal information in data, a spatiotemporal pyramid pooling model is proposed. A three-dimensional, densely connected convolutional neural network based on dense computation and fusion of spatiotemporal features is designed. The combination of this model with non-local computation operation of features improves the effectiveness of spatiotemporal-feature extraction from videos. The algorithm is applied to the analysis of teachers' actions in classroom scenes. The experimental results show that the designed network structure produces high recognition accuracy on the teachers' actions dataset.
张晓龙, 刘剑飞, 郝禄国. 基于特征密集计算与融合算法的教师课堂行为分析[J]. 激光与光电子学进展, 2019, 56(16): 161503. Xiaolong Zhang, Jianfei Liu, Luguo Hao. Analysis of Teachers' Actions Using Feature Dense Computation and Fusion Algorithm[J]. Laser & Optoelectronics Progress, 2019, 56(16): 161503.