智能系统学报2024，Vol.19Issue(6)：1407-1418,12.DOI:10.11992/tis.202309021
基于时空-动作自适应融合网络的油田作业行为识别
Oilfield operation behavior recognition based on spatio-temporal and action adaptive fusion network
摘要
Abstract
A spatiotemporal and action adaptive fusion network is proposed for personnel behavior recognition in oil-field operation sites to address the problems of false positives and negatives caused by the complex environment of oil-field operations interfering with behavior recognition algorithms.First,the videos are processed on the constructed net-work using a sparse sampling strategy,and features on the feature extraction network are then extracted.The core mod-ules of the network include spatiotemporal attention,action reinforcement,and adaptive feature fusion modules.The spatiotemporal attention module redistributes the spatiotemporal importance of features,establishing temporal correla-tions between different frames.The action reinforcement module weakens the background and enhances human body movements,allowing the model to focus on human actions.The feature fusion module adaptively combines the parallel features after reinforcement.Finally,behavior classification is achieved through fully connected layers and a SoftMax layer.The model is compared with classic networks on public and self-built oilfield datasets to verify the effectiveness of the proposed network.The Top-1 accuracy on the UCF101 dataset shows a 3.33%improvement over SlowOnly,the Slow branch of the SlowFast model,and a 1.61%improvement over the temporal shift module(TSM).On the HMDB51 dataset,the Top-1 accuracy improves by 8.56%and 1.83%compared to SlowOnly and TSM,respectively.Additionally,when evaluated on the self-built oilfield dataset,the proposed model shows a notable improvement in accuracy over the temporal segment network,TSM,and SlowOnly.This result validates the effectiveness of the spatiotemporal and action adaptive fusion network in oilfield operations and confirms its suitability for behavior recognition tasks in such environ-ments.关键词
行为识别/ResNet50/注意力机制/油田作业/特征融合/时空注意力/动作注意力/复杂场景Key words
behavior recognition/ResNet50/attention mechanism/oilfield operation/feature fusion/spatio-temporal at-tention/action attention/complex scenes分类
信息技术与安全科学引用本文复制引用
田枫,卫宁彬,刘芳,韩玉祥,赵玲,张思睿,马贵宝..基于时空-动作自适应融合网络的油田作业行为识别[J].智能系统学报,2024,19(6):1407-1418,12.基金项目
黑龙江省自然科学基金项目(LH2021F004). （LH2021F004）
