Data Searching

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

The descriptive nature of the abstractions permit the rapid location and retrieval of relevant content buried deep within mountains of archived data. This also enables the determination, evaluation, and interpretation of anomalous patterns within multi-variate data sets.

The abstractions, created from the data, describe the data's content. Therefore the data is effectively self-descriptive, eliminating the need to manual indexing.

The data can probed from patterns by analysing the evolution of the abstractions through time and space.

Additionally, Deep Vision's data abstraction technology operates with a throughput of 100+ frames per second.

• Find patterns and objects hidden within vast and complex data sets.
• Predictive learning through hindsight
• Data fusion

Features

• Content-based information retrieval.
• Assessment of multi-variate data patterns and relationships.
• Automatic data annotation, segmentation, and aggregation.
• Fast searching for specific forms.

• 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 video and images from visual, thermal, or sonar sensors.