You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data.
Michal BalaziaPetr SojkaPublished in: CoRR (2017)
Keyphrases
- noisy data
- video surveillance
- motion capture
- background subtraction
- surveillance system
- person identification
- moving objects
- motion detection
- computer vision
- human identification
- multiple cameras
- traffic monitoring
- missing values
- moving object detection
- gait recognition
- object tracking
- surveillance videos
- smoke detection
- missing data
- high dimensional
- input data
- gait analysis
- event detection
- pedestrian tracking
- high dimensionality
- detection of moving objects
- training data
- knn
- dimensionality reduction
- human body
- learning algorithm
- shadow detection