GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:
Learn how GPU computing and deep learning can be utilized for the detection of cracks, potholes and patches on road pavement surface. In recent years, the increasing number of vehicles on the road is driving the demand for automated pavement distress detection. To respond to this demand, we present a decentralized system for distress detection based on common passenger vehicles. By performing image pre-processing steps and calculating textural features and wavelet transform on GPUs, real-time pavement distress detection is enabled. Deep learning is employed to determine the type of the distress. The approach was tested on 38,000 images and an accuracy of 93% was achieved. To improve the reliability of the pavement distress detection methodology, an ensemble method for distress detection was developed by aggregating results obtained by different vehicles.
Learn how GPU computing and deep learning can be utilized for the detection of cracks, potholes and patches on road pavement surface. In recent years, the increasing number of vehicles on the road is driving the demand for automated pavement distress detection. To respond to this demand, we present a decentralized system for distress detection based on common passenger vehicles. By performing image pre-processing steps and calculating textural features and wavelet transform on GPUs, real-time pavement distress detection is enabled. Deep learning is employed to determine the type of the distress. The approach was tested on 38,000 images and an accuracy of 93% was achieved. To improve the reliability of the pavement distress detection methodology, an ensemble method for distress detection was developed by aggregating results obtained by different vehicles.  Back
 
Topics:
Intelligent Video Analytics, Artificial Intelligence and Deep Learning
Type:
Talk
Event:
GTC Europe
Year:
2018
Session ID:
E8174
Streaming:
Download:
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