Search

Based on the classification system of modern Chinese words classification system and characteristics of military documents field, the military document words are classified and descripted with morphology, syntax, complex feature, semantic and reference. And a military documents electronic lexicon prototype is designed. This lexicon can meet the requirement of military document intelligent processing well proved by application of military documents electronic lexicon.

Aiming at improving the identification and judgment on objectives of unmanned weapon system in the battlefield, this paper puts forward a new efficient method to infuse conflict evidence orienting towards shortcomings existing in the Dempster-Shafter (D-S) evidence theory when fusing conflict evidence. This paper is to improve the D-S Evidence Theory, by firstly conducting research on the influence of a certain operational environment on the sensors precision in the unmanned weapon system, and by secondly establishing sensors weight values based on fixed basic probability assignment by exploiting AHP. The improved approach can enhance the reliability of identification result, which has been proved via simulation experiments, and it improves the performance of target recognition system to a certain extent.

For the traditional machine vision, positioning algorithms are usually less efficient and more complex, the author proposes a relative threshold-based positioning algorithm for real-time machine vision. Firstly, the algorithm thresholds the template and sample images with a relative threshold. So it can not only effectively impact the influence of uniform illumination, but also reduce the volume of data. Then it uses the two-floor image pyramid method to greatly reduce the computation amount and uses the adaptive step method further to accelerate the matching speed. The algorithm nears to the object by the rough matching, and then navigates to the object center through a precise matching. While greatly improving the matching speed it ensures the accuracy. The experiments show that it can meet the real-time requirement.