Nyc3Dcars

Description en une ligne: A vehicle detection database for vision tasks set in the real world.

Description:

Use of <a href="http://www.postgresql.org/" style="color: rgb(4, 136, 205);">PostgreSQL</a> with the <a href="http://postgis.net/" style="color: rgb(4, 136, 205);">PostGIS</a> package is recommended for working with any of the spatial or geographic data and is required for the use of many of the analysis tools. JPEG images are distributed separately per reconstruction due to the large size. We provide a link below to our preprocessed geodatabase as well as links to original sources.

Files labeled as PGSQL can be imported into a PostgreSQL database using the following command:

zcat filename.dump.gz > | pg_restore --dbname=nyc3dcars

Alternatively, we provide a <a href="https://raw.github.com/kmatzen/nyc3dcars-toolkit/master/nyc3dcars_bootstrap.py" style="color: rgb(4, 136, 205);">script</a> to help download and import all necessary assets.

To enable the reproduction of our detection results, we have included the deformable part models that we trained using a combination of our dataset, the <a href="http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/" style="color: rgb(4, 136, 205);">PASCAL Visual Object Classes Challenge 2007</a> dataset, and the <a href="http://www.cvlibs.net/datasets/kitti/" style="color: rgb(4, 136, 205);">KITTI Vision Benchmark Suite</a> dataset. In addition, we provide links to our open source detection software, pydro (a python reimplementation of Pedro Felzenszwalb and Ross Girshick's <a href="http://www.cs.berkeley.edu/~rbg/latent/" style="color: rgb(4, 136, 205);">voc-release5</a> MATLAB package), our nyc3dcars-toolkit analysis scripts, and the source code for our annotation website.

Image:

{{#if:fabmobimage.11.jpg|Fichier:Fabmobimage.11.jpg|Fichier:No-image-yet.jpg}}

Site internet: http://nyc3d.cs.cornell.edu/

Organisations intéressées pour contribuer ou qui contribuent déjà:

Organisations utilisatrice ou intéressée par utiliser la ressource

Contributeurs:

Tags: opendata, autonomous, commun, database, vision, fabmob

Catégories:

Thème:

Référent:

Défi auquel répond la ressource:

Personnes clés à solliciter

Autre commun proche:

Type:

Dans le cadre de l'OpenChallenge ?

Niveau de développement

Espace d'échange synchrone (de type chat): [1]

Espace d'échange asynchrone (de type mail):

Lien vers l'outil de gestion des actions:

Lien vers l'outil de partage de fichiers:

Besoins:

Complément:

Prochaine Etape:

Autres informations: