Skip to Main Content Area
  • CPS-VO
    • Contact Support
  • Browse
    • Calendar
    • Announcements
    • Repositories
    • Groups
  • Search
    • Search for Content
    • Search for a Group
    • Search for People
    • Search for a Project
    • Tagcloud
      
 
Not a member?
Click here to register!
Forgot username or password?
 
Home
National Science Foundation

Cyber-Physical Systems Virtual Organization

Read-only archive of site from September 29, 2023.

CPS-VO

public domain surveillance data

biblio

Visible to the public A deep learning approach to trespassing detection using video surveillance data

Submitted by grigby1 on Fri, 07/03/2020 - 1:15pm
  • Railroad security
  • Deep Neural Network
  • dual-stage ARTS architecture
  • dual-stage deep learning architecture
  • early warning prediction techniques
  • high fidelity trespass classification stage
  • inexpensive pre-filtering stage
  • potential trespassing sites
  • public domain surveillance data
  • deep convolutional neural networks
  • railroad trespassing activity
  • safety risks
  • Subspace constraints
  • surveillance
  • Trespassing detection
  • video processing
  • video surveillance data
  • deep video
  • convolutional neural nets
  • computer architecture
  • machine learning
  • pubcrawl
  • Metrics
  • Resiliency
  • resilience
  • learning (artificial intelligence)
  • deep learning
  • Scalability
  • Neural networks
  • video surveillance
  • Detectors
  • activity detection
  • automated railroad trespassing detection system
  • background subtraction
  • CNN-based deep learning architecture
  • computer vision

Terms of Use  |  ©2023. CPS-VO