TB-places
| Autor: | Nicolai Petkov, Radim Tylecek, Michael Blaich, Nicola Strisciuglio, Manuel Lopez Antequera, Maria Leyva-Vallina |
|---|---|
| Přispěvatelé: | Intelligent Systems, [Leyva-Vallina, Maria] Univ Groningen, Bernoulli Inst Math Comp Sci & Artificial Intelli, NL-9700 Groningen, Netherlands, [Strisciuglio, Nicola] Univ Groningen, Bernoulli Inst Math Comp Sci & Artificial Intelli, NL-9700 Groningen, Netherlands, [Lopez-Antequera, Manuel] Univ Groningen, Bernoulli Inst Math Comp Sci & Artificial Intelli, NL-9700 Groningen, Netherlands, [Petkov, Nicola] Univ Groningen, Bernoulli Inst Math Comp Sci & Artificial Intelli, NL-9700 Groningen, Netherlands, [Lopez-Antequera, Manuel] Univ Malaga, Inst Invest Biomed Malaga, MAPIR Grp, Malaga 29010, Spain, [Tylecek, Radim] Univ Edinburgh, Sch Informat, Edinburgh EH8 9AB, Midlothian, Scotland, [Blaich, Michael] Robert Bosch GmbH, Robot Syst & Power Tools CR AER, D-71272 Renningen, Germany, TrimBot2020 Project through the European Horizon 2020 Program |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
General Computer Science
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION data set 02 engineering and technology Benchmark 01 natural sciences computer vision Image (mathematics) Component (UML) holistic image descriptor 0202 electrical engineering electronic engineering information engineering General Materials Science Computer vision visual place recognition Ground truth business.industry 020208 electrical & electronic engineering 010401 analytical chemistry General Engineering 0104 chemical sciences Data set Closure (mathematics) Benchmark (computing) Robot Artificial intelligence lcsh:Electrical engineering. Electronics. Nuclear engineering business lcsh:TK1-9971 |
| Zdroj: | IEEE Access, Vol 7, Pp 52277-52287 (2019) IEEE Access, 7:8698240, 52277-52287. IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| ISSN: | 2169-3536 |
| Popis: | Place recognition can be achieved by identifying whether a pair of images (a labeled reference image and a query image) depict the same place, regardless of appearance changes due to different viewpoints or lighting conditions. It is an important component of systems for camera localization and for loop closure detection and a widely studied problem for indoor or urban environments. Recently, the use of robots in agriculture and automatic gardening has created new challenges due to the highly repetitive appearance with prevalent green color and repetitive texture of garden-like scenes. The lack of available data recorded in gardens or plant fields makes difficult to improve localization algorithms for such environments. In this paper, we propose a new data set of garden images for testing algorithms for visual place recognition. It contains images with ground truth camera pose recorded in real gardens at different times, with varying light conditions. We also provide ground truth for all possible pairs of images, indicating whether they depict the same place or not. We also performed a thorough benchmark of several holistic (whole-image) descriptors, and provide the results on the proposed data set. We observed that existing descriptors have difficulties with scenes with repetitive textures and large changes of camera viewpoint. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|