.png){kind=icon}
Return
Learning Scene Context for Multiple Object Tracking
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2009.2019934.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose a framework for multitarget tracking with feedback that accounts for scene contextual information. We demonstrate the framework on two types of context-dependent events, namely target births (i.e., objects entering the scene or reappearing after occlusion) and spatially persistent clutter. The spatial distributions of birth and clutter events are incrementally learned based on mixtures of Gaussians. The corresponding models are used by a probability hypothesis density (PHD) filter that spatially modulates its strength based on the learned contextual information. Experimental results on a large video surveillance dataset using a standard evaluation protocol show that the feedback improves the tracking accuracy from 9% to 14% by reducing the number of false detections and false trajectories. This performance improvement is achieved without increasing the computational complexity of the tracker.
Keywords:
Adaptive filtering
clutter
context
GMM
PHD filter
tracking
video surveillance
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W
Organization
Cited Papers
ShareSaveBeyond activism/academia: militant research and the radical climate and climate justice movement(s).png)
Area
AreaIF0
PREAI
ShareSaveShareSaveShareSaveEfficacy of Lactic Acid and Modified Atmosphere Packaging against Campylobacter jejuni on Chicken during Refrigerated StorageFoods
OAAI
FoodsIF0
OAAIShareSave
View more