Multi-stage infrared stationary human detection

Detecting stationary human targets is crucial in ensuring safe operation of unmanned ground vehicles. In this paper, a multi-stage detection algorithm for stationary humans in infrared imagery is proposed. This algorithm first applies an efficient feature-based anomalies detection algorithm to search the entire input image, which is followed by an eigen-neural-based clutter rejecter that examines only the portions of the input image identified by the first algorithm, and culminates with a simple evidence integrator that combines the results from the two previous stages. The proposed algorithm was evaluated using a challenging set of infrared images, and the results support the usefulness of this multi-stage human detection architecture.