A method for generating and utilizing structure from motion (SfM) uncertainty estimates within image-based pose estimation is presented. The method is applied to a class of problems in which SfM algorithms are utilized to form a geo-registered reference model of a particular ground area using imagery gathered during flight by a small unmanned aircraft. The model is then used to form camera pose estimates in near real-time from imagery gathered later. The resulting pose estimates can be utilized by any of the other onboard systems (e.g. as a replacement for GPS data) or downstream exploitation systems, e.g., image-based object trackers. However, many of the consumers of pose estimates require an assessment of the pose accuracy. The method for generating the accuracy assessment is presented. First, the uncertainty in the reference model is estimated. Bundle Adjustment (BA) is utilized for model generation. While the high-level approach for generating a covariance matrix of the BA parameters is straightforward, typical computing hardware is not able to support the required operations due to the scale of the optimization problem within BA. Therefore, a series of sparse matrix operations is utilized to form an exact covariance matrix for only the parameters that are needed at a particular moment. Once the uncertainty in the model has been determined, it is used to augment Perspective-n-Point pose estimation algorithms to improve the pose accuracy and to estimate the resulting pose uncertainty. The implementation of the described method is presented along with results including results gathered from flight test data.
We describe a comprehensive system for learning to identify suspicious vehicle tracks from wide-area motion
(WAMI) video. First, since the road network for the scene of interest is assumed unknown, agglomerative
hierarchical clustering is applied to all spatial vehicle measurements, resulting in spatial cells that largely capture
individual road segments. Next, for each track, both at the cell (speed, acceleration, azimuth) and track (range,
total distance, duration) levels, extreme value feature statistics are both computed and aggregated, to form
summary (p-value based) anomaly statistics for each track. Here, to fairly evaluate tracks that travel across
different numbers of spatial cells, for each cell-level feature type, a single (most extreme) statistic is chosen, over
all cells traveled. Finally, a novel active learning paradigm, applied to a (logistic regression) track classifier, is
invoked to learn to distinguish suspicious from merely anomalous tracks, starting from anomaly-ranked track
prioritization, with ground-truth labeling by a human operator. This system has been applied to WAMI video
data (ARGUS), with the tracks automatically extracted by a system developed in-house at Toyon Research
Corporation. Our system gives promising preliminary results in highly ranking as suspicious aerial vehicles,
dismounts, and traffic violators, and in learning which features are most indicative of suspicious tracks.
In this paper, we discuss algorithmic approaches for exploiting wide-area persistent EO/IR motion imagery for multisensor
geo-registration and automated information extraction, including moving target detection. We first present
enabling capabilities, including sensor auto-calibration and automated high-resolution 3D reconstruction using passive
2D motion imagery. We then present algorithmic approaches for 3D-based geo-registration, and demonstrate and
quantify performance achieved using public release data from AFRL's Columbus Large Image Format (CLIF) 2006 data
collection and the Ohio Geographically Referenced Information Program (OGRIP). Finally, we discuss algorithmic
approaches for 3D-based moving target detection with near-optimal parallax mitigation, and demonstrate automated
detection of dismount and vehicle targets in coarse-resolution CLIF 2006 imagery.