<title>Automatic 3D object pose estimation in IR image sequences for forward motion applications</title>

Abstract

The successful mission of autonomous airborne systems like unmanned aerial vehicles (UAV) strongly depends on the performance of automatic image processing used for navigation, target acquisition and terminal homing. In this paper we propose a method for automatic determination of missile position and orientation (pose) during target approach. The flight path is characterized by a forward motion, i.e. an approximately linear motion along the optical axis of the sensor system. Due to the lack of disparity, classical methods based on stereo triangulation are not suitable for 3D object recognition. To handle this we applied the SoftPOSIT algorithm, originally proposed by D. DeMenthon, and adapted it to fit our specific needs: The gathering of image points is done by multi-threshold segmentation, texture analysis, 2D tracking and edge detection. The reference points are updated in each loop and the calculated pose is smoothed using the quaternion representation of the model's orientation in order to stabilize the computations. We will show some results of image based determination of trajectories for airborne systems. Terminal homing is demonstrated by tracking the 3D pose of a vehicle in an image sequence taken in oblique view and gathered by an infrared sensor mounted to a helicopter.

Imaging sensor fusion and enhanced vision for helicopter landing operations

“…Beside the investigation of automatic target recognition and classification procedures for the output of single sensors like laser radar [1] or IR cameras [4], a lot of research work at the FOM is done in the field of multisensorial data fusion. Subject to analysis are mobile sensors on a common platform as well as distributed systems.…”

A Kalman Filtering Approach to 3-D IR Scene Prediction using Single-Camera Range Video

“…Aside from the consumer-end applications, indoor and outdoor navigation has been greatly influenced from imaging-science developments and newly introduced range measurement devices. To this end, many 3-D image-motion estimation and modeling problems have been widely investigated in various indoor and outdoor navigation settings [1], [2], [3], [6], [9], [10], [11], [15], [19]. Determining egomotion (i.e., finding the motion of the camera based on its output image in response to the scene in question) has also been studied in the research effort discussed in [4].…”