| Presentation | 2005-02-24 Pedestrian Detection by Boosting Soft-Margin SVM with Feature Selection Kenji NISHIDA, Takio KURITA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We present an example-based algorithm for detecting objects in images by integrating component-based classifiers, which automaticaly select the best feature for each classifier and are combined according to AdaBoost algorithm. The system employs soft-margin SVM for base learner, which is trained for all features and the optimal feature is selected at each stage of boosting. We employed two features such as Histogram-equalization feature and Edge feature for our experiment. The proposed method is applied to the MIT CBCL pedestrian image database, and 100 sub-regions are extracted from each image as local-features. The experimental result shows fairly good classification ratio with single feature, while the improvement on classification ratio with the combination of two feature is small. However, the combination of features effects to select good local-features for base learners. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | AdaBoost / Support Vector Machine (SVM) / Feature Selsction / Pedestrian Detetion |
| Paper # | NLC2004-105,PRMU2004-187 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2005/2/17(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Natural Language Understanding and Models of Communication (NLC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Pedestrian Detection by Boosting Soft-Margin SVM with Feature Selection |
| Sub Title (in English) | |
| Keyword(1) | AdaBoost |
| Keyword(2) | Support Vector Machine (SVM) |
| Keyword(3) | Feature Selsction |
| Keyword(4) | Pedestrian Detetion |
| 1st Author's Name | Kenji NISHIDA |
| 1st Author's Affiliation | Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology (AIST)() |
| 2nd Author's Name | Takio KURITA |
| 2nd Author's Affiliation | Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology (AIST) |
| Date | 2005-02-24 |
| Paper # | NLC2004-105,PRMU2004-187 |
| Volume (vol) | vol.104 |
| Number (no) | 667 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |