Deep Learning Architecture for Recognition of Abnormal Activities

机译：识别异常活动的深度学习架构

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

The video surveillance is one of the key areas in computer vision researches. The scientific challenge in this field involves the implementation of automatic systems to obtain detailed information about individuals and groups behaviors. In particular, the detection of abnormal movements of groups or individuals requires a fine analysis of frames in the video stream. In this article, we propose a new method to detect anomalies in crowded scenes. We try to categorize the video in a supervised mode accompanied by unsupervised learning using the principle of the autoencoder. In order to construct an informative concept for the recognition of these behaviors, we use a technique of representation based on the superposition of human silhouettes. The evaluation of the UMN dataset demonstrates the effectiveness of the proposed approach.

机译：视频监控是计算机视觉研究的关键领域之一。该领域的科学挑战涉及自动系统的实现，以获取有关个人和团体行为的详细信息。特别是，要检测组或个人的异常运动，需要对视频流中的帧进行精细分析。在本文中，我们提出了一种在拥挤的场景中检测异常的新方法。我们尝试使用自动编码器的原理，将视频分类为监督模式，并伴随无监督学习。为了构建用于识别这些行为的信息概念，我们使用了基于人体轮廓叠加的表示技术。对UMN数据集的评估证明了该方法的有效性。

著录项

来源
《International conference on machine vision》|2017年|106960F.1-106960F.7|共7页
会议地点
作者
Marwa Khatrouch; Mariem Gnouma; Ridha Ejbali; Mourad Zaied;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
abnormal human activity recognition; anomaly detection; silhouette extraction; history of binary motion image; deep learning;

机译：异常的人类活动识别;异常检测;轮廓提取;二进制运动图像的历史;深度学习;

相似文献

外文文献
中文文献
专利

1. Improving physical activity recognition using a new deep learning architecture and post-processing techniques [J] . Manuel Gil-Martin, Ruben San-Segundo, Fernando Fernandez-Martinez, Engineering Applications of Artificial Intelligence . 2020,第Juna期

机译：使用新的深度学习架构和后处理技术提高体力活动识别
2. Efficient deep feature selection for remote sensing image recognition with fused deep learning architectures [J] . Ozyurt Fatih Journal of supercomputing . 2020,第11期

机译：利用融合深度学习架构的遥感图像识别有效的深度特征选择
3. Deep learning architecture for iris recognition based on optimal Gabor filters and deep belief network [J] . He Fei, Han Ye, Wang Han, Journal of electronic imaging . 2017,第2期

机译：基于最佳Gabor滤波器和深度置信网络的虹膜识别深度学习架构
4. Deep Learning Architecture for Recognition of Abnormal Activities [C] . Marwa Khatrouch, Mariem Gnouma, Ridha Ejbali, International Conference on Machine Vision . 2018

机译：深度学习架构，用于识别异常活动
5. Deep Learning Architectures for Heterogeneous Face Recognition [D] . Iranmanesh, Seyed Mehdi. 2021

机译：非均质面部识别的深度学习架构
6. Efficient Deep Learning Architecture for Detection and Recognition of Thyroid Nodules [O] . Jingzhe Ma, Shaobo Duan, Ye Zhang, 2020

机译：用于检测和识别甲状腺结节的高效深度学习架构
7. Deep Learning Approach Combining Lightweight CNN Architecture with Transfer Learning: An Automatic Approach for the Detection and Recognition of Bangladeshi Banknotes [O] . Ali Hasan Md. Linkon, Md. Mahir Labib, Faisal Haque Bappy, 2020

机译：轻量级CNN架构与转移学习的深度学习方法：孟加拉国钞票检测与识别的自动方法

Deep Learning Architecture for Recognition of Abnormal Activities

摘要

著录项

相似文献

相关主题

期刊订阅