Tracking Highly Similar Rat Instances under Heavy Occlusions: An Unsupervised Deep Generative Pipeline.
Anna Gelencsér-HorváthLászló KopácsiViktor VargaDávid KellerÁrpád DobolyiKristóf KaracsAndrás LorinczPublished in: J. Imaging (2022)
Keyphrases
- highly similar
- robust tracking
- unsupervised learning
- occlusion reasoning
- data driven
- computer vision
- high similarity
- particle filter
- partially occluded
- partial occlusion
- visual tracking
- tracking multiple objects
- tracking objects
- cluttered background
- real time
- crowded scenes
- physically plausible
- kalman filter
- image sequences
- object tracking
- mean shift
- multiple moving objects
- deep architectures
- occlusion detection
- generative model
- particle filtering
- occlusion handling
- motion segmentation
- multi object tracking
- object appearance
- appearance variations
- behavior analysis