Image processing and fusion to detect navigation obstacles

Abstract

Helicopters flying at low altitude in the visual flight rules often crash against obstacles such as a power transmission line. This paper describes the image sensors to detect obstacles and the several image processing techniques to derive and enhance the targets in the images. The images including obstacles were collected both on the ground and by air using an infrared (IR) camera and a color video camera in different backgrounds, distances, and weather conditions. Collected results revealed that JR images have an advantage over color images to detect obstacles in many environments. Several image processing techniques have been evaluated to improve the qualities of collected images. For example, fusion of JR and color images, several filters, such as the Median filter or the adaptive filter have been tested. Jnformation that the target is thin and long, which characterizes the shape of power lines, has been introduced to derive power lines. It has been shown that these processes can greatly reduce the noise and enhance the contrast, no matter how the background is. It has also been demonstrated that there is a good prospect that these processes will help develop the algorithm for automatic obstacle detection and warning.

Investigation of image fusion methods for helicopter day, night and all weather operation

“…Lallier and Farooq [13] propose an adaptive weight averaging method for the fusion of thermal and visual images. Yamamoto and Yamanda [14] investigate the use of image superposition for the fusion of visible light and infrared images for airborne 978-1-4244-3504-3/09/$25.00 ©2009 IEEE where (m, n) defmes an m x n window centered around the current coefficient. The coefficient with the largest saliency is then selected as follows.…”

Improvements of image fusion methods

“…1 Hence, there is a need for combining the streams of information into one coherent representation in order to cope with the data overload. 10 For example, heavy fog would block a pilot's vision, but by fusion of a laser imaging sensor image to the pilot's image, we could dramatically improve the pilot's vision. 10 For example, heavy fog would block a pilot's vision, but by fusion of a laser imaging sensor image to the pilot's image, we could dramatically improve the pilot's vision.…”