Forest fires are an important problem for many countries. Prevention, surveillance and extinguishing tasks are costly and sometimes risky. This paper focuses on the surveillance of the fire embers once the fire is extinguished. This is a post-fire task which requires an important amount of terrestrial resources, especially if the weather conditions may provoke the re-ignition of the fire. We propose the use of an Unmanned Aerial System to support fire fighters' decisions. Our proposal is to develop an intelligent system which can make or suggest tactical decisions to firemen on hot-spot surveillance. The Unmanned Aerial System consists of a small unmanned aircraft, a ground control station and several personal devices for the firemen on ground. All system elements are wirelessly connected. On board data acquisition and fast processing, together with an intelligent transmission and interpretation are the targets of the system.

In this paper we present a new method for extracting the maximum parallelism or vector operations out of DO loops with tight recurrences using sequential programming languages. We have named the method Graph Traverse Scheduling (GTS). It is devised to produce code for shared memory multiprocessors or vector machines. When parallelizing, hardware support for fast synchronization is assumed.