Home » Technology » Capability

Information Sharing

Deep Vision's data abstraction technology delivers fast and efficient information sharing.

Deep Vision's novel concept of data abstraction quickly transforms abundant sensor data into a form that is easily classified and efficiently stored.

The abstractions created from the raw data are extremely compact. For instance, 64 abstractions (averaging 16 symbols each) requires 1 KB of storage capacity.

The compact nature, coupled with robust descriptive capabilities, makes the data abstractions ideal for real-time communication between members of a multi-modal, distributed sensor system.

For example, it would take 5.5 minutes to transmit 30 lossless compressed imagesα over a persistent 128 kbps communication link. While, it would only take 2 seconds to transmit the data abstractions β.

The transmission of the data abstractions not only promotes the sharing of information but also reduces transmission times thus potentially reducing the strain on the power supply by the transmitter.

α 30 grey-scale PNG images, 640x480, circa. 5,130 KB (177KB each).
β Typical results. 45 abstractions per image totaling 33 KB for 30 images.
Exploitation Value
 

  • Counter-mobility Systems
  • UAVs
  • Distributed self/group aware multi-modal sensor systems

Features

  • Communication of low volume/high value information.
  • Real-time situational awareness capability
  • Reduced transmission and reception times.
  • Increased effective communication payload capacity.
 Operating Facts

  • Operating System: Any (GNU/Linux recommended)
  • Hardware Requirements: None
  • Sensor Modalities: Visual, Thermal, Sonar
  • Timings†: 100+ FPS
  • Runtime Memory Requirements†: 300 KB
  • Storage Requirements‡: 1.1 KB

† Typical. Based on a 640 x 480 data set
‡ Typical. Based on 45 abstractions (avg. 25 symbols each)

Input Requirements

  • Archived and real-time acquisition from visual, thermal, or sonar sensors.