Unsupervised Conditional Diffusion Models in Video Anomaly Detection for Monitoring Dust Pollution
Video surveillance is widely used in monitoring environmental pollution, particularly harmful dust. Currently, manual video monitoring remains the predominant method for analyzing potential pollution, which is inefficient and prone to errors. In this paper, we introduce a new unsupervised method bas...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/5/1464 |
| _version_ | 1797263869161242624 |
|---|---|
| author | Limin Cai Mofei Li Dianpeng Wang |
| author_facet | Limin Cai Mofei Li Dianpeng Wang |
| author_sort | Limin Cai |
| collection | DOAJ |
| description | Video surveillance is widely used in monitoring environmental pollution, particularly harmful dust. Currently, manual video monitoring remains the predominant method for analyzing potential pollution, which is inefficient and prone to errors. In this paper, we introduce a new unsupervised method based on latent diffusion models. Specifically, we propose a spatio-temporal network structure, which better integrates the spatial and temporal features of videos. Our conditional guidance mechanism samples frames of input videos to guide high-quality generation and obtains frame-level anomaly scores, comparing generated videos with original ones. We also propose an efficient compression strategy to reduce computational costs, allowing the model to perform in a latent space. The superiority of our method was demonstrated by numerical experiments in three public benchmarks and practical application analysis in coal mining over previous SOTA methods with better AUC, of at most over 3%. Our method accurately detects abnormal patterns in multiple challenging environmental monitoring scenarios, illustrating the potential application possibilities in the environmental protection domain and beyond. |
| first_indexed | 2024-04-25T00:19:51Z |
| format | Article |
| id | doaj.art-3d1bd164279242b3bfa88636de389bac |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-25T00:19:51Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3d1bd164279242b3bfa88636de389bac2024-03-12T16:54:51ZengMDPI AGSensors1424-82202024-02-01245146410.3390/s24051464Unsupervised Conditional Diffusion Models in Video Anomaly Detection for Monitoring Dust PollutionLimin Cai0Mofei Li1Dianpeng Wang2School of Mathematics and Statistics, Beijing Institute of Technology, Beijing 100081, ChinaInner Mongolia Ecological Environment Big Data Co., Ltd., Hohhot 010070, ChinaSchool of Mathematics and Statistics, Beijing Institute of Technology, Beijing 100081, ChinaVideo surveillance is widely used in monitoring environmental pollution, particularly harmful dust. Currently, manual video monitoring remains the predominant method for analyzing potential pollution, which is inefficient and prone to errors. In this paper, we introduce a new unsupervised method based on latent diffusion models. Specifically, we propose a spatio-temporal network structure, which better integrates the spatial and temporal features of videos. Our conditional guidance mechanism samples frames of input videos to guide high-quality generation and obtains frame-level anomaly scores, comparing generated videos with original ones. We also propose an efficient compression strategy to reduce computational costs, allowing the model to perform in a latent space. The superiority of our method was demonstrated by numerical experiments in three public benchmarks and practical application analysis in coal mining over previous SOTA methods with better AUC, of at most over 3%. Our method accurately detects abnormal patterns in multiple challenging environmental monitoring scenarios, illustrating the potential application possibilities in the environmental protection domain and beyond.https://www.mdpi.com/1424-8220/24/5/1464conditional diffusion modelsdust pollutionlatent compressionvideo anomaly detection |
| spellingShingle | Limin Cai Mofei Li Dianpeng Wang Unsupervised Conditional Diffusion Models in Video Anomaly Detection for Monitoring Dust Pollution Sensors conditional diffusion models dust pollution latent compression video anomaly detection |
| title | Unsupervised Conditional Diffusion Models in Video Anomaly Detection for Monitoring Dust Pollution |
| title_full | Unsupervised Conditional Diffusion Models in Video Anomaly Detection for Monitoring Dust Pollution |
| title_fullStr | Unsupervised Conditional Diffusion Models in Video Anomaly Detection for Monitoring Dust Pollution |
| title_full_unstemmed | Unsupervised Conditional Diffusion Models in Video Anomaly Detection for Monitoring Dust Pollution |
| title_short | Unsupervised Conditional Diffusion Models in Video Anomaly Detection for Monitoring Dust Pollution |
| title_sort | unsupervised conditional diffusion models in video anomaly detection for monitoring dust pollution |
| topic | conditional diffusion models dust pollution latent compression video anomaly detection |
| url | https://www.mdpi.com/1424-8220/24/5/1464 |
| work_keys_str_mv | AT limincai unsupervisedconditionaldiffusionmodelsinvideoanomalydetectionformonitoringdustpollution AT mofeili unsupervisedconditionaldiffusionmodelsinvideoanomalydetectionformonitoringdustpollution AT dianpengwang unsupervisedconditionaldiffusionmodelsinvideoanomalydetectionformonitoringdustpollution |