Name
Abstract | ||
|---|---|---|
This paper shows a concrete example of the use of graph mining for tracking objects in videos with moving cameras and without any contextual information on the objects to track. To make the mining algorithm efficient, we benefit from a video representation based on dynamic (evolving through time) planar graphs. We then define a number of constraints to efficiently find our so-called spatio-temporal graph patterns. Those patterns are linked through an occurrences graph to allow us to tackle occlusion or graph features instability problems in the video. Experiments on synthetic and real videos show that our method is effective and allows us to find relevant patterns for our tracking application. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-33460-3_31 | ECML/PKDD (1) |
Keywords | Field | DocType |
object tracking,real video,so-called spatio-temporal graph pattern,tracking application,mining algorithm,video representation,planar graph,occurrences graph,concrete example,contextual information,graph mining | Computer vision,Object detection,Graph,Contextual information,Graph patterns,Computer science,Image processing,Video tracking,Artificial intelligence,Data mining algorithm,Planar graph | Conference |
Citations | PageRank | References |
2 | 0.39 | 85 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fabien Diot | 1 | 8 | 0.83 |
| Élisa Fromont | 2 | 192 | 25.51 |
| baptiste jeudy | 3 | 98 | 8.44 |
| Emmanuel Marilly | 4 | 8 | 4.55 |
| Olivier Martinot | 5 | 12 | 5.95 |