Probabilistic Integration of Intensity and Depth Information for Part-Based Vehicle Detection

Alexandros Makris 1 Mathias Perrollaz 2, * Christian Laugier 2, *
* Corresponding author
1 MOISE - Modelling, Observations, Identification for Environmental Sciences
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 E-MOTION - Geometry and Probability for Motion and Action
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : In this paper, an object class recognition method is presented. The method uses local image features and follows the part-based detection approach. It fuses intensity and depth information in a probabilistic framework. The depth of each local feature is used to weigh the probability of finding the object at a given distance. To train the system for an object class, only a database of images annotated with bounding boxes is required, thus automatizing the extension of the system to different object classes. We apply our method to the problem of detecting vehicles from a moving platform. The experiments with a data set of stereo images in an urban environment show a significant improvement in performance when using both information modalities.
Document type :
Journal articles
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download
https://hal.inria.fr/hal-00905703
Contributor : Mathias Perrollaz <>
Submitted on : Wednesday, January 8, 2014 - 3:15:38 PM
Last modification on : Friday, February 22, 2019 - 3:20:27 PM
Long-term archiving on : Tuesday, April 8, 2014 - 10:10:54 PM

File

06575156.pdf
Publisher files allowed on an open archive

Identifiers

Collections

INRIA | LJK_MAD | LJK | LJK_MAD_MOISE | UGA | LIG_SIC_E-MOTION | LIG

Citation

Alexandros Makris, Mathias Perrollaz, Christian Laugier. Probabilistic Integration of Intensity and Depth Information for Part-Based Vehicle Detection. IEEE Transactions on Intelligent Transportation Systems, IEEE, 2013, 14 (4), pp.1896-1906. ⟨10.1109/TITS.2013.2271113⟩. ⟨hal-00905703⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

579

Files downloads

516

Contact


archive-ouverte@inria.fr