Name
Abstract | ||
|---|---|---|
We present an online data association algorithm for multi-object tracking using structured prediction. This problem is formulated as a bipartite matching and solved by a generalized classification, specifically, Structural Support Vector Machines (S-SVM). Our structural classifier is trained based on matching results given the similarities between all pairs of objects identified in two consecutive frames, where the similarity can be defined by various features such as appearance, location, motion, etc. With an appropriate joint feature map and loss function in the S-SVM, finding the most violated constraint in training and predicting structured labels in testing are modeled by the simple and efficient Kuhn-Munkres (Hungarian) algorithm in a bipartite graph. The proposed structural classifier can be generalized effectively for many sequences without re-training. Our algorithm also provides a method to handle entering/leaving objects, short-term occlusions, and misdetections by introducing virtual agents--additional nodes in a bipartite graph. We tested our algorithm on multiple datasets and obtained comparable results to the state-of-the-art methods with great efficiency and simplicity. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-37431-9_8 | ACCV (3) |
Keywords | Field | DocType |
structural support,generalized classification,online multi-target tracking,online data association algorithm,bipartite graph,proposed structural classifier,large margin,vector machines,structured prediction,structured label,structural classifier,bipartite matching | Computer vision,Feature vector,Pattern recognition,Computer science,Structured prediction,Support vector machine,Local binary patterns,Bipartite graph,Data association,Artificial intelligence,3-dimensional matching,Classifier (linguistics) | Conference |
Citations | PageRank | References |
28 | 1.13 | 24 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Suna Kim | 1 | 28 | 1.13 |
| Suha Kwak | 2 | 397 | 20.33 |
| Jan Feyereisl | 3 | 131 | 10.20 |
| Bohyung Han | 4 | 2203 | 94.45 |