Jincheol Ha

Real-Time Vision-Based Relative Aircraft Navigation

Received 22 February 2006; revision received 11 September 2006; accepted for publication 11 September 2006. Copyright

Visual search automation for unmanned aerial vehicles

The design, development, and testing of an unmanned aerial vehicle (UAV) with automated capabilities is described: searching a prescribed area, identifying a specific building within that area based on a small sign located on one wall, and then identifying an opening into that building. This includes a description of the automated search system along with simulation and flight test results. Results include successful evaluation at the McKenna Military Operations in Urban Terrain flight test site.

Development and Test of Highly Autonomous Unmanned Aerial Vehicles

Published in Journal of Aerospace Computing, Information, and Communication, Vol. 1, Issue 12, December 2004.

Real-Time Vision-Based Relative Navigation

This paper describes two vision-based techniques for the navigation of an aircraft relative to an airborne target using only information from a single camera fixed to the aircraft. By applying an Extended Kalman Filter (EKF) for relative state estimation, both the velocity and position of the aircraft relative to the target can be estimated. While relative states such as bearing can be estimated fairly easily, estimating the range to the target is more difficult because it requires achieving valid depth perception with a single camera. The two techniques presented here offer distinct solutions to this problem. The first technique, Center Only Relative State Estimation (CORSE), uses optimal control to generate an optimal (sinusoidal) trajectory to a desired location relative to the target that results in accurate range-to-target estimates while making minimal demands on the image processing system. The second technique, Subtended Angle Relative State Estimation (SARSE), uses more rigorous image processing to arrive at a valid range estimate without requiring the aircraft to follow a prescribed path. Simulation results indicate that both methods yield range estimates of comparable accuracy while placing different demands on the aircraft and its systems.

Vision-based Target Tracking with Adaptive Target State Estimator

This paper presents an approach to vision-based target tracking with a neural network (NN) augmented Kalman filter as the adaptive target state estimator. The vision sensor onboard the follower (tracker) aircraft is a single camera. Real-time image processing implemented in the onboard flight computer is used to derive measurements of relative bearing (azimuth and elevation angles) and the maximum angle subtended by the target aircraft on the image plane. These measurements are used to update the NN augmented Kalman filter. This filter generates estimates of the target aircraft position, velocity and acceleration in inertial 3D space that are used in the guidance and flight control law to guide the follower aircraft relative to the target aircraft. Applications of the presented approach include vision-based autonomous formation flight, pursuit and autonomous aerial refueling. The NN augmenting the Kalman filter estimates the target acceleration and hence provides for robust state estimation in the presence of unmodeled target maneuvers. Vision-in-theloop simulation results obtained in a 6DOF real-time simulation of vision-based autonomous formation flight are presented to illustrate the efficacy of the adaptive target state estimator design.

Real-time Visual Tracking Using Geometric Active Contours for the Navigation and Control of UAVs

Visual tracking is an important component in the navigation and control of unmanned aerial vehicles (UAVs). This paper is concerned with the visual tracking problem for the navigation and control of UAVs and focuses on real-time image processing methods. We review previous research based on geometric active contours which are automatic processes to track object boundaries in an image. Test results and some limitations of the previous tracking system are discussed. Then, a fast and robust implementation of the Chan-Vese active contour model is proposed to overcome these limitations.

Real-time Visual Tracking Using Geometric Active Contours and Particle Filters

Image processing and flltering are essential elements for the visual tracking system in an unmanned aerial vehicle. This paper presents visual tracking methodology based on particle flltering in the framework of a fast implementation of the Chan-Vese active contour model. The fast implementation greatly improves the computational time of the segmentation process. We have tested particle flltering using this fast active contour model, and the flltering algorithm has shown the ability to robustly track an aerial target under varied conditions. The computational speed of the algorithm has allowed us to employ it for formation ∞ight among UAVs. We have also demonstrated the utility of the flltering algorithm for multiple target tracking in the presence of occlusions.

Recent flight test results of active-vision control systems

This tutorial session covers recent results using methods that utilize 2D and 3D imagery (e.g., from LADAR, visual, FLIR, acoustic-location) to enable aerial vehicles to autonomously detect and prosecute targets in uncertain 3D environments. This includes segmentation approaches, active contours, adaptive control, estimation theory, and optical flow. Recent flight test results utilizing a small glider and a small helicopter as well as a high-fidelity simulation of multiple airplanes are discussed.