Abstract
The problem of detecting a vehicle of a certain type in an outdoor scene is investigated. A shared weight neural network is applied in correlation fashion to images of outdoor scenes. Two sets of images are considered. The first set consists of forward looking infrared images of tanks. The second set consists of visible images of cars in a parking lot. The goal in the first set of images is to detect the tanks. The goal in the second set of images is to detect the Chevrolet Blazers. The second problem is much more difficult than the first. The networks are compared to a minimum average correlation energy (MACE) matched filter approach. The shared weight network was found to be better at generalizing. Problems were found in trying to suppress spurious outputs on the background. As a result, an improved training algorithm was developed.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call