Subventions et des contributions :

Titre :
Deep Learning for analyzing traffic camera video
Numéro de l’entente :
EGP
Valeur d'entente :
25 000,00 $
Date d'entente :
23 août 2017 -
Organisation :
Conseil de recherches en sciences naturelles et en génie du Canada
Location :
Québec, Autre, CA
Numéro de référence :
GC-2017-Q2-00504
Type d'entente :
subvention
Type de rapport :
Subventions et des contributions
Informations supplémentaires :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier (2017-2018 à 2018-2019).

Nom légal du bénéficiaire :
Clark, James (Université McGill)
Programme :
Subventions d'engagement partenarial pour les universités
But du programme :

The project involved improving the performance and enhancing the capabilities of the BriskVANTAGE trafficx000D
analysis software from the BriskSynergies company. Modern state-of-the-art machine learning technologyx000D
(deep convolutional neural networks) will be used to improve the detection and recognition of objects such asx000D
motorcycles, bicycles, trucks and buses, in addition to automobiles and pedestrians. The deep net algorithmsx000D
will be modified to include robust object tracking and data association (retaining the identity of which scenex000D
object is which when tracking) in situations where vehicles and pedestrians may become occluded by otherx000D
objects, or when tracking is momentarily lost. Benefits to Canada for the improved BriskVANTAGE softwarex000D
includes higher quality and higher reliability data analytics for urban planners engaged in traffic monitoring andx000D
analysis, leading to safer roads and improved traffic flow. Real-time systems can provide immediate signalingx000D
of significant traffic events as well as long-term monitoring of traffic and safety conditions and emergent trendsx000D
due to changes in demographics and road construction.