Visual object recognition with 3D-aware features in the urban scenes of KITTI evaluation benchmark
Identificadores
Enlace permanente (URI): http://hdl.handle.net/10017/43131DOI: 10.3390/s150409228
ISSN: 1424-8220
Editor
MDPI
Fecha de publicación
2015-04-20Patrocinadores
Ministerio de Educación, Cultura y Deporte
Comunidad de Madrid
Ministerio de Economía y Competitividad
Cita bibliográfica
Yebes J.J, Bergasa L.M, & García-Garrido M.A. 2015, "Visual Object Recognition with 3D-Aware Features in KITTI Urban Scenes", Sensors. 2015, 15(4), 9228-9250
Palabras clave
3D-aware features
Object recognition
KITTI
DPM
Stereo-vision
Proyectos
info:eu-repo/grantAgreement/MECD//AP-2010-1472
info:eu-repo/grantAgreement/CAM//S2013%2FMIT-2748/ES/ROBOTICA APLICADA A LA MEJORA DE LA CALIDAD DE VIDA DE LOS CIUDADANOS, FASE III/RoboCity2030-III-CM
info:eu-repo/grantAgreement/MINECO//TEC2012-37104/ES/SMART DRIVING APPLICATIONS/
Tipo de documento
info:eu-repo/semantics/article
Versión
info:eu-repo/semantics/publishedVersion
Versión del editor
https://doi.org/10.3390/s150409228Derechos
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
Derechos de acceso
info:eu-repo/semantics/openAccess
Resumen
Driver assistance systems and autonomous robotics rely on the deployment of several sensors for environment perception. Compared to LiDAR systems, the inexpensive vision sensors can capture the 3D scene as perceived by a driver in terms of appearance and depth cues. Indeed, providing 3D image understanding capabilities to vehicles is an essential target in order to infer scene semantics in urban environments. One of the challenges that arises from the navigation task in naturalistic urban scenarios is the detection of road participants (e.g., cyclists, pedestrians and vehicles). In this regard, this paper tackles the detection and orientation estimation of cars, pedestrians and cyclists, employing the challenging and naturalistic KITTI images. This work proposes 3D-aware features computed from stereo color images in order to capture the appearance and depth peculiarities of the objects in road scenes. The successful part-based object detector, known as DPM, is extended to learn richer models from the 2.5D data (color and disparity), while also carrying out a detailed analysis of the training pipeline. A large set of experiments evaluate the proposals, and the best performing approach is ranked on the KITTI website. Indeed, this is the first work that reports results with stereo data for the KITTI object challenge, achieving increased detection ratios for the classes car and cyclist compared to a baseline DPM.
Ficheros en el ítem
Ficheros | Tamaño | Formato |
|
---|---|---|---|
Visual_Yebes_Sensors_2015.pdf | 5.208Mb |
|
Ficheros | Tamaño | Formato |
|
---|---|---|---|
Visual_Yebes_Sensors_2015.pdf | 5.208Mb |
|
Colecciones
- ELECTRON - Artículos [242]
- ROBESAFE - Artículos [37]