Home » Technology » Capability

Object Tracking

Deep Vision's data abstraction technology delivers real-time object tracking.

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

The abstractions created from the raw data, coupled with their position on the sensor and relative positions over time, provide the foundation for real-time object tracking.

The abstractions do not have any dependencies to the sensing platform, sensor or other objects within the sensor's data. Therefore, the abstractions, and by extension the objects, can be tracked independent of both sensor and object motion.

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

With prior knowledge of the target objects, or their characteristics, Deep Vision's object tracking technology delivers a highly robust, real-time target locking solution.
Exploitation Value

  • Operator Assistance
  • Target locking
  • Motion Analysis and Prediction

Features

  • Real-time object tracking
  • Simultaneous tracking of multiple objects
  • Operates in complex and cluttered environments
  • Context-based motion analysis
  • Sensor and object independent
  • Moving platform and moving target
 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 video and images
  • Real-time acquisition from visual, thermal, or sonar sensors.
Examples - Dynamic Knowledge Base

These videos illustrate the use of Deep Vision's sensor exploitation technology with a dynamic knowledge base. The user selects and labels an object from within the scene. The description and label pair is added to the knowledge base. The memory requirements of the expression (e.g. to transmit and store) are appended to the label for clarity. The overall size of the knowledge base is indicated at the top-right corner along with the memory requirements of all recognised objects.

The demonstration software operates within the 33 ms imposed by the attached camera, resulting in fluid object recognition and tracking. The current frame rate, which includes both processing and rendering, is displayed in the bottom-right corner.

It should be noted that multiple occurrences of these objects of interest could have been placed throughout the environment. Each one would have been found and recognised. However, for clarity, only one instance of each object of interest is presented.

1. The user selects two objects: a cross and the letter H. Each object is given a meaningful label: First Aid and Hospital respectively. These objects are then placed in the environment and the camera is moved within it. Each object presented on the sensor and found in the knowledge base is highlighted and labelled accordingly. 2. The users selects three objects: the letter H, an airplane and a cross. Each object is given a meaningful label: Hospital, Airport and First Aid respectively. These objects are then moved throughout the environment.
Examples - Motion Analysis

These videos illustrate the use of Deep Vision's sensor exploitation technology with low-level motion analysis.

1. Simultaneous tracking of two people in motion (delineated by bounding box).
 2. Tracking of an intermittently moving person. The person remains locked even when motionless (indicated by the constant colour of the bounding box). Note that the pickup truck near the end of the sequence (top right corner) is ignored, demonstrating the ability to differentiate between items of interest in any scene.
3. Preferential tracking of a moving person. The moving vehicle is ignored in favour of the person even after the person has left the scene.