warning: Creating default object from empty value in /home/ijkco/ijkco.com/modules/taxonomy/taxonomy.pages.inc on line 34.

Recognition & Tracking

We build computer vision algorithms and systems for:
  • Automatic target recognition
  • Object detection and identification
  • Automated threat assessment
Our extensive background in tracking includes:
  • Sensor pointing, line-of-sight control
  • Correlation trackers and feature-based trackers
  • Multiple target tracking
Below are some examples case studies.

Target tracking and state estimation

Target tracking and state estimation

An established communications company sought ways to improve performance of a laser-based gimbal-mounted communications on-the-move product line. The DARPA funded program was intended to push the performance of existing systems by an order of magnitude. In particular, the product’s tracking ability and the ability to recover quickly from periods of outages were major program focuses.

IJK Controls built a detailed simulation that modeled everything from stabilized gimbal and target dynamics, video tracker noise to motor saturation and possible atmospheric effects.

Road detection for ground vehicle

Road detection for ground vehicle

Unmanned ground vehicles face an overwhelming perception problem: identifying and tracking obstacles while finding the best part of the road. This is even more difficult in offroad conditions. LIDAR based obstacle detection algorithms are in use, but road finding requires using rich visual camera data.

Missile seeker gimbal feedforward testbed

Missile seeker gimbal feedforward testbed

The Feedforward Testbed program was a demonstration project to develop a mirror-stabilized beam-steering mechanism for use in small missiles. Missile seekers are generally a gyroscope stabilized gimbal mounted to the front of a missile that attempts to track the target.