基于SE-U-Net预测网络的视频异常事件检测方法
VIDEO ABNORMAL EVENT DETECTION BASED ON SE-U-NET PREDICTIVE NETWORK
王伟胜 1王来花 1贾晴 1赵月1
作者信息
- 1. 曲阜师范大学网络空间安全学院 山东 曲阜 273165
- 折叠
摘要
针对视频异常检测中存在的数据不平衡问题,提出一种基于SE-U-Net预测网络的视频异常检测方法.该方法提取视频帧的显著性图,并将其制作成掩膜对数据进行预处理;利用预处理后的数据对预测模型进行训练,为了使预测模型更关注前景区域的优化,结合注意力机制设计一组新的损失函数用于约束模型的训练.在测试阶段设计一个新的异常评价分数计算方法,通过仅计算视频中显著性区域的预测误差来进行异常检测,缓解数据不平衡问题.利用公共数据集进行相关对比实验以及消融实验验证该方法的有效性.
Abstract
Aimed at the problem of data imbalance in video anomaly detection,an anomaly video detection method based on SE-U-Net predictive network is proposed.We extracted the saliency map of the video frame and made it into a mask to preprocess the data.We used the preprocessed data to train the prediction model.In order to make the prediction model pay more attention to the optimization of the foreground area,this paper combined the attention mechanism,and a new set of loss functions were designed to constrain the training of the model.In addition,in the testing phase,this paper designed a new anomaly evaluation score calculation method,and anomaly detection was performed only by calculating the prediction error of the saliency region in the video,which alleviated the problem of data imbalance.Public datasets for comparative experiments and ablation experiments were used to verify the effectiveness of the proposed method for abnormal event detection.
关键词
视频异常检测/显著性提取/未来帧预测/U-Net/异常评价分数Key words
Video anomaly detection/Saliency extraction/Prediction of future frames/U-Net/Anomaly evaluation score引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据