.png){kind=icon}
.png){kind=icon}
Return
Trajectories as Topics: Multi-Object Tracking by Topic Discovery
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2018.2866955.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper proposes a new approach to multi-object tracking by semantic topic discovery. We dynamically cluster frame-by-frame detections and treat objects as topics, allowing the application of the Dirichlet process mixture model. The tracking problem is cast as a topic-discovery task, where the video sequence is treated analogously to a document. It addresses tracking issues such as object exclusivity constraints as well as tracking management without the need for heuristic thresholds. Variation of object appearance is modeled as the dynamics of word co-occurrence and handled by updating the cluster parameters across the sequence in the dynamical clustering procedure. We develop two kinds of visual representation based on super-pixel and deformable part model and integrate them into the model of automatic topic discovery for tracking rigid and non-rigid objects, respectively. In experiments on public data sets, we demonstrate the effectiveness of the proposed algorithm.
Keywords:
Multi-object tracking
topic model
DPMM
Gibbs sampling
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W
View more organizations