基于scSE非局部双流ResNet网络的行为识别OA北大核心CSTPCD
ACTION RECOGNITION ALGORITHM FOR NON-LOCAL TWO-STREAM RESNET NETWORK BASED ON SCSE FUSION
针对双流网络对包含冗余信息的视频帧存在识别率低的问题,在双流网络的基础上引入scSE(Spatial and Channel Squeeze & Excitation Block)和非局部操作,构建SC_NLResNet行为识别框架.该框架将视频划分为等分不重叠的时序段并在每段上稀疏采样,提取RGB帧以及光流图作为scSE模块的输入;将经过scSE处理的特征输入非局部双流ResNet网络中,融合各分段得到最终的预测结果.在UCF101以及Hmdb51数据集上实验准确率分别达到96.9%和76.2%,结果表明,非局部操作与scSE模块结合可以增强特征时空上以及通道间的信息提高准确率,验证了 SC_NLResNet网络的有效性.
Aimed at the problem of low recognition rate of video frames containing redundant information in dual-stream network,scSE(Spatial and Channel Squeeze & Excitation Block)and non-local operation are introduced based on two-stream network to construct SC_NLResNet behavior recognition framework.In this framework,the framework divided the video into equal and non-overlapping temporal segments and sparsely sampled each segment,extracting RGB frames and optical flow graphs as the input of the scSE module.The features processed by scSE were inputted into the non-local two-stream ResNet network,and the segmentations were merged to obtain the final prediction results.The experimental accuracy on UCF101 and Hmdb51 dataset reaches 96.9%and 76.2%,respectively.The results show that the combination of non-local operation and scSE module can enhance the information of feature space-time and between the channels to improve the accuracy,which verifies the effectiveness of SC_NLResNet network.
李占利;王佳莹;靳红梅;李洪安
西安科技大学计算机科学与技术学院 陕西西安 710600
计算机与自动化
双流卷积神经网络scSE模块残差网络非局部操作行为识别
Two-stream convolutional neural networkScSE moduleResidual neural networkNon-local operationAction recognition
《计算机应用与软件》 2024 (008)
319-325 / 7
陕西省自然科学基础研究计划项目(2019JM-348,2019JLM-10).
评论