On-the-fly adaptation of regression forests for online camera relocalisation
Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D cor...
| Egile Nagusiak: | , , , , , |
|---|---|
| Formatua: | Conference item |
| Argitaratua: |
Institute for Electrical and Electronics Engineers
2017
|
| _version_ | 1826306334685921280 |
|---|---|
| author | Cavallari, T Golodetz, S Lord, N Valentin, J Di Stefano, L Torr, P |
| author_facet | Cavallari, T Golodetz, S Lord, N Valentin, J Di Stefano, L Torr, P |
| author_sort | Cavallari, T |
| collection | OXFORD |
| description | Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the camera pose. Recently, regression forests have become a popular alternative to establish such correspondences. They achieve accurate results, but must be trained offline on the target scene, preventing relocalisation in new environments. In this paper, we show how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly. Our adapted forests achieve relocalisation performance that is on par with that of offline forests, and our approach runs in under 150ms, making it desirable for realtime systems that require online relocalisation. |
| first_indexed | 2024-03-07T06:46:23Z |
| format | Conference item |
| id | oxford-uuid:fafd9528-512e-4927-a1ad-dc104147fd92 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T06:46:23Z |
| publishDate | 2017 |
| publisher | Institute for Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:fafd9528-512e-4927-a1ad-dc104147fd922022-03-27T13:10:32ZOn-the-fly adaptation of regression forests for online camera relocalisationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:fafd9528-512e-4927-a1ad-dc104147fd92Symplectic Elements at OxfordInstitute for Electrical and Electronics Engineers2017Cavallari, TGolodetz, SLord, NValentin, JDi Stefano, LTorr, PCamera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the camera pose. Recently, regression forests have become a popular alternative to establish such correspondences. They achieve accurate results, but must be trained offline on the target scene, preventing relocalisation in new environments. In this paper, we show how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly. Our adapted forests achieve relocalisation performance that is on par with that of offline forests, and our approach runs in under 150ms, making it desirable for realtime systems that require online relocalisation. |
| spellingShingle | Cavallari, T Golodetz, S Lord, N Valentin, J Di Stefano, L Torr, P On-the-fly adaptation of regression forests for online camera relocalisation |
| title | On-the-fly adaptation of regression forests for online camera relocalisation |
| title_full | On-the-fly adaptation of regression forests for online camera relocalisation |
| title_fullStr | On-the-fly adaptation of regression forests for online camera relocalisation |
| title_full_unstemmed | On-the-fly adaptation of regression forests for online camera relocalisation |
| title_short | On-the-fly adaptation of regression forests for online camera relocalisation |
| title_sort | on the fly adaptation of regression forests for online camera relocalisation |
| work_keys_str_mv | AT cavallarit ontheflyadaptationofregressionforestsforonlinecamerarelocalisation AT golodetzs ontheflyadaptationofregressionforestsforonlinecamerarelocalisation AT lordn ontheflyadaptationofregressionforestsforonlinecamerarelocalisation AT valentinj ontheflyadaptationofregressionforestsforonlinecamerarelocalisation AT distefanol ontheflyadaptationofregressionforestsforonlinecamerarelocalisation AT torrp ontheflyadaptationofregressionforestsforonlinecamerarelocalisation |