Name
Abstract | ||
|---|---|---|
We present a method to detect the seat and head-rest of the by-passenger, as a part of a smart airbag system. The recognition of the seat and head-rest is useful for the purpose of background subtraction, as well as for assisting head-tracking and occupant classification. We use a multi-resolution probabilistic generalized Hough transform (GHT). We present experimental results for the detection, as well as an error analysis. Our experiments were performed using an imperfect set of models on close-range images with low dynamic range and under sever occlusions. Nevertheless, we have found that one needs to consider only the best 11 hypotheses of the GHT to ensure recognition. Moreover, when at least 25% of the seat contour is not occluded, only two hypotheses are needed on the average. The results show that the head-rest is a more robust clue than the seat. Finally, we discuss how to extend our work and possible uses in the context of occupant detection and classification. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1016/j.patrec.2006.10.007 | Pattern Recognition Letters |
Keywords | Field | DocType |
low dynamic range,imperfect set,background subtraction,articulated objects,occupant classification,close-range image,smart airbag,error analysis,smart airbag application,multi-resolution probabilistic,generalized hough transform,occupant detection and classification,seat contour,occupant detection,free-form objects,3d object recognition,seat detection | Background subtraction,Object detection,Computer vision,Pattern recognition,Low dynamic range,Multiresolution analysis,Hough transform,Artificial intelligence,Probabilistic logic,Airbag,Mathematics,Cognitive neuroscience of visual object recognition | Journal |
Volume | Issue | ISSN |
28 | 4 | Pattern Recognition Letters |
Citations | PageRank | References |
0 | 0.34 | 17 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| David Schreiber | 1 | 51 | 5.78 |
| Yun Luo | 2 | 0 | 0.34 |