A boundary-fragment-model for object detection
<p>The objective of this work is the detection of object classes, such as airplanes or horses. Instead of using a model based on salient image fragments, we show that object class detection is also possible using only the object’s boundary. To this end, we develop a novel learning technique to...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
2006
|
| _version_ | 1824458916559323136 |
|---|---|
| author | Opelt, A Pinz, A Zisserman, A |
| author_facet | Opelt, A Pinz, A Zisserman, A |
| author_sort | Opelt, A |
| collection | OXFORD |
| description | <p>The objective of this work is the detection of object classes, such as airplanes or horses. Instead of using a model based on salient image fragments, we show that object class detection is also possible using only the object’s boundary. To this end, we develop a novel learning technique to extract class-discriminative boundary fragments. In addition to their shape, these “codebook” entries also determine the object’s centroid (in the manner of Leibe <em>et al.</em> [19]). Boosting is used to select discriminative combinations of boundary fragments (weak detectors) to form a strong “Boundary-Fragment-Model” (BFM) detector. The generative aspect of the model is used to determine an approximate segmentation.</p>
<p>We demonstrate the following results: (i) the BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance; and (ii) in comparison with other published results on several object classes (airplanes, cars-rear, cows) the BFM detector is able to exceed previous performances, and to achieve this with less supervision (such as the number of training images).</p> |
| first_indexed | 2025-02-19T04:33:30Z |
| format | Conference item |
| id | oxford-uuid:9f98d587-bd9d-4370-b474-ad6ab86f9062 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:33:30Z |
| publishDate | 2006 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:9f98d587-bd9d-4370-b474-ad6ab86f90622025-01-21T10:24:35ZA boundary-fragment-model for object detectionConference itemhttp://purl.org/coar/resource_type/c_5794uuid:9f98d587-bd9d-4370-b474-ad6ab86f9062EnglishSymplectic ElementsSpringer2006Opelt, APinz, AZisserman, A<p>The objective of this work is the detection of object classes, such as airplanes or horses. Instead of using a model based on salient image fragments, we show that object class detection is also possible using only the object’s boundary. To this end, we develop a novel learning technique to extract class-discriminative boundary fragments. In addition to their shape, these “codebook” entries also determine the object’s centroid (in the manner of Leibe <em>et al.</em> [19]). Boosting is used to select discriminative combinations of boundary fragments (weak detectors) to form a strong “Boundary-Fragment-Model” (BFM) detector. The generative aspect of the model is used to determine an approximate segmentation.</p> <p>We demonstrate the following results: (i) the BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance; and (ii) in comparison with other published results on several object classes (airplanes, cars-rear, cows) the BFM detector is able to exceed previous performances, and to achieve this with less supervision (such as the number of training images).</p> |
| spellingShingle | Opelt, A Pinz, A Zisserman, A A boundary-fragment-model for object detection |
| title | A boundary-fragment-model for object detection |
| title_full | A boundary-fragment-model for object detection |
| title_fullStr | A boundary-fragment-model for object detection |
| title_full_unstemmed | A boundary-fragment-model for object detection |
| title_short | A boundary-fragment-model for object detection |
| title_sort | boundary fragment model for object detection |
| work_keys_str_mv | AT opelta aboundaryfragmentmodelforobjectdetection AT pinza aboundaryfragmentmodelforobjectdetection AT zissermana aboundaryfragmentmodelforobjectdetection AT opelta boundaryfragmentmodelforobjectdetection AT pinza boundaryfragmentmodelforobjectdetection AT zissermana boundaryfragmentmodelforobjectdetection |