The paper focuses on the development and evaluation of an autonomous payload tracking capability for determining time, state and attitude information (TSPI) of all types of airdrop loads. This automated capability of accurately acquiring TSPI data, will reduce the labor time and eliminate man-in-the-loop errors. The paper analyses the problem and then proceeds with the description of the PerceptiVU Target Tracking System (TTS) software adopted for obtaining the TSPI. The key features of this software include a choice of three basic tracking algorithms (dynamic centroid, hottest spot thresholding, dynamic correlation), capability of capturing from both standard analog video sources (such as NTSC and/or RS170) and digital video sources, control of the entire system with an off-the-shelf joystick controller. The paper further describes algorithms to be used in conjunction with the data provided by the TTS to determine system's state variables. A position estimation solution is based on tracking a payload's center (or any other predetermined point) by several cameras with known positions. A pose (position and orientation) estimation solution is based on tracking of four distinctive non-coplanar points. Pre-selected and artificially marked points on the moving target cooperatively serve as beacons, therefore providing precise measurements of the line of sign toward these points. This allows unique position and attitude estimation and no need for additional pattern recognition. In conclusion, the paper provides examples of video data processing and parameters estimation.

The paper discloses a current status of the development and evaluation of an autonomous payload tracking capability for determining time, state and attitude information (TSPI) for all types of airdrop loads. This automated capability of accurately acquiring TSPI data is supposed to radically reduce the labor time and eliminate man-in-the-loop errors. The paper starts with the problem formulation and then reviews the developed software. The algorithms rely on commercial off-the-shelf feature-based video-data processing software adopted for obtaining TSPI. Having the frame coordinates of the centroid of a tracking item available from no less than three ground stationary surveyed cameras at each instant during a descent together with these cameras azimuth and elevation information allows solving the position estimation problem. If more known-geometry features of the airdrop load can reliably be extracted, the pose (position and attitude) estimation would also be possible. The paper primarily addresses the status of the payload's position estimation portion providing examples of processing video data from up to six cameras. Yet, it also discusses the applicability of more recent computer-vision algorithm, based on establishing and tracking multiple scale-invariant keypoints. The paper ends with conclusions and suggestions for the further development.

No abstract

No abstract

No abstract