Wind turbines can affect radar systems used for missions in defense, aviation safety, and weather forecasting. Both range and Doppler reflections from wind turbines can create clutter' reduce detection sensitivity, and obscure potential targets. An accurate and up-to-date database of wind turbine locations and status is needed in order to assess their impact on radar functionalities. Overhead and satellite images are important data sources to assess the status of wind turbines. To significantly reduce human workload in classifying the status of wind turbines through overhead imagery, we trained classifiers using convolutional neural networks (CNN) to automate the wind turbine status classification problem. We leveraged the existing AlexNet and GoogLeNet CNN frameworks, paired with overhead imagery from Google maps, to train a classifier to determine whether a turbine structure exists at a location where one has been registered. The automated classifier achieved an average accuracy of 97%. Our classifier can act as a highly efficient prefilter to select wind turbines for status verification by human operators.1

We develop a view-normalization approach to multi-view face and gait recognition. An image-based visual hull (IBVH) is computed from a set of monocular views and used to render virtual views for tracking and recognition. We determine canonical viewpoints by examining the 3D structure, appearance (texture), and motion of the moving person. For optimal face recognition, we place virtual cameras to capture frontal face appearance; for gait recognition we place virtual cameras to capture a side-view of the person. Multiple cameras can be rendered simultaneously, and camera position is dynamically updated as the person moves through the workspace. Image sequences from each canonical view are passed to an unmodified face or gait recognition algorithm. We show that our approach provides greater recognition accuracy than is obtained using the unnormalized input sequences, and that integrated face and gait recognition provides improved performance over either modality alone. Canonical view estimation, rendering, and recognition have been efficiently implemented and can run at near real-time speeds.

Monitoring of large sites requires coordination between multiple cameras, which in turn requires methods for relating events between distributed cameras. This paper tackles the problem of automatic external calibration of multiple cameras in an extended scene, that is, full recovery of their 3D relative positions and orientations. Because the cameras are placed far apart, brightness or proximity constraints cannot be used to match static features, so we instead apply planar geometric constraints to moving objects tracked throughout the scene. By robustly matching and fitting tracked objects to a planar model, we align the scene's ground plane across multiple views and decompose the planar alignment matrix to recover the 3D relative camera and ground plane positions. We demonstrate this technique in both a controlled lab setting where we test the effects of errors in the intrinsic camera parameters, and in an uncontrolled, outdoor setting. In the latter, we do not assume synchronized cameras and we show that enforcing geometric constraints enables us to align the tracking data in time. In spite of noise in the intrinsic camera parameters and in the image data, the system successfully transforms multiple views of the scene's ground plane to an overhead view and recovers the relative 3D camera and ground plane positions.