Feature Correspondence and Semi-Automatic Ground Truthing for Airborne Data Collection

摘要

A significant amount of airborne data has been collected in the past and more is expected to be collected in the future to support airborne landmine detection research and evaluation under various programs. In order to evaluate mine and minefield detection performance for sensor and detection algorithms, it is essential to generate reliable and accurate ground truth for the location of the mine targets and fiducials present in raw imagery. The current ground truthing operation is primarily manual, which makes the ground truthing a time consuming and expensive exercise in the overall data collection effort. In this paper, a semi-automatic ground-truthing technique is presented which reduces the role of the operator to a few high-level input and validation actions. A correspondence is established between the high-contrast targets in the airborne imagery called the image features, and the known GPS locations of the targets on the ground called the map features by imposing various position and geometric constraints. These image and map features may include individual fiducial targets, rows of fiducial targets and triplets of non-collinear fiducials. The targets in the imagery are established using the RX anomaly detector. An affine or linear conformal transformation from map features to image features is calculated based on feature correspondence. This map-to-image transformation is used to generate ground-truth for mine targets. Since accurate and reliable flight-log data is currently not available, one-time specification of a few parameters like flight speed, flight direction, camera resolution and specification of the location of the initial frame on the map is required from the operator. These parameters are updated and corrected for subsequent frames based on the processing of previous frames. Image registration is used to ground-truth images which do not have enough high-contrast fiducials for reliable correspondence. A GUI called SemiAutoGT developed in MATLAB for the ground truthing process is briefly discussed. Results are presented for ground-truthing of the data collected under the Lightweight Airborne Multispectral Minefield Detection (LAMD) program.