Effective Crowd Anomaly Detection Through Spatio-temporal Texture Analysis
- Submitting institution
-
The University of Huddersfield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 21
- Type
- D - Journal article
- DOI
-
10.1007/s11633-018-1141-z
- Title of journal
- International Journal of Automation and Computing
- Article number
- -
- First page
- 27
- Volume
- 16
- Issue
- 1
- ISSN
- 1476-8186
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presented a novel video sectioning and human behaviour representation model, capable of texture-based, time-series, non-stationary video event analysis, which significantly enhanced individual behaviour understanding and responding processes. It has since found extensive use in real-world tasks such as tracking for the visually impaired population (2 Patents on KrVision Augment Reality i-Glasses https://helios.hud.ac.uk/sengdg2/Patent%20Search%20and%20Analysis%20-%20Zhijie%20Xu%20with%20ZJU.pdf), semantic segmentation and vSLAM (Collaborative Research Evaluation Report: https://helios.hud.ac.uk/sengdg2/Collaborative%20Research%20Evaluation%20Report%20-%20KrVision.pdf), and CCTV-based smart factory monitoring (Instrumentation Monthly : https://www.instrumentation.co.uk/switch-to-new-smart-factory-technology-ticks-greener-manufacturing-box-for-bicycle-production-giant/). This research enabled the development and commercialisation of wearables and headsets for KrVision Co.Ltd and has helped 80,000 users worldwide to overcome their life difficulties (http://www.krvision.cn/).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
