GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:
Well discuss the challenge of toll vehicle classification and our solution. Vinci Autoroutes, the company owning the most French motorways, classifies millions of vehicles in real-time every year. Because a small delay in classification time can have major business consequences, accuracy and speed are mandatory for toll collection systems. Well show how Volta architecture has helped us solve this problem by predicting more than eight million transactions per day.
Well discuss the challenge of toll vehicle classification and our solution. Vinci Autoroutes, the company owning the most French motorways, classifies millions of vehicles in real-time every year. Because a small delay in classification time can have major business consequences, accuracy and speed are mandatory for toll collection systems. Well show how Volta architecture has helped us solve this problem by predicting more than eight million transactions per day.  Back
 
Topics:
AI Application, Deployment & Inference, Computer Vision
Type:
Talk
Event:
GTC Washington D.C.
Year:
2019
Session ID:
DC91316
Download:
Share:
 
Abstract:
We'll present a novel real-time framework based on NVIDIA Volta architecture for real-time automatic incident detection, which plays an important role in transportation systems. This framework is mandatory in every tunnel in Europe and is being deployed to the more than 80 tunnels we manage in France and elsewhere in Europe. We'll describe our real-time automatic incident detection solution and discuss how it outperforms traditional systems based on classical image processing techniques, which are inefficient and produce many false positives. We'll also detail the challenges we faced, including the need to minimize hardware cost, provide highly precise detection, and keep computation time very low. The complexity of this problem increases with the number of the cameras, which range from 50-380 per tunnel.
We'll present a novel real-time framework based on NVIDIA Volta architecture for real-time automatic incident detection, which plays an important role in transportation systems. This framework is mandatory in every tunnel in Europe and is being deployed to the more than 80 tunnels we manage in France and elsewhere in Europe. We'll describe our real-time automatic incident detection solution and discuss how it outperforms traditional systems based on classical image processing techniques, which are inefficient and produce many false positives. We'll also detail the challenges we faced, including the need to minimize hardware cost, provide highly precise detection, and keep computation time very low. The complexity of this problem increases with the number of the cameras, which range from 50-380 per tunnel.  Back
 
Topics:
Intelligent Video Analytics, Autonomous Vehicles, AI Application, Deployment & Inference
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9868
Streaming:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next