Crater detection via genetic search methods to reduce image features

Recent approaches to crater detection have been inspired by face detection’s use of gray-scale texture features. Using gray-scale texture features for supervised machine learning crater detection algorithms provides better classification of craters in planetary images than previous methods. When using Haar features it is typical to generate thousands of numerical values from each candidate crater image. This magnitude of image features to extract and consider can spell disaster when the application is an entire planetary surface. One solution is to reduce the number of features extracted and considered in order to increase accuracy as well as speed. Feature subset selection provides the operational classifiers with a concise and denoised set of features by reducing irrelevant and redundant features. Feature subset selection is known to be NP-hard. To provide an efficient suboptimal solution, four genetic algorithms are proposed to use greedy selection, weighted random selection, and simulated annealing to distinguish discriminate features from indiscriminate features. Inspired by analysis regarding the relationship between subset size and accuracy, a squeezing algorithm is presented to shrink the genetic algorithm’s chromosome cardinality during the genetic iterations. A significant increase in the classification performance of a Bayesian classifier in crater detection using image texture features is observed.     

先进机身结构和材料设计

由于大型商用飞机机身结构的复杂性,其碳纤维复合材料部件的设计、制造和取证都不能借用现有的制造维修基本经验.碳纤维复合材料机身壁板超越了现代化金属技术,对应力应变的保守限制要求必须保证将具有损伤容限的机身结构交付到航空公司.这样,碳纤维复合材料壁板技术的应用至少限制了新飞机家族第一代成员的重量.     

Ambiguity Removal When Using Burst Waveforms. Part II: Nonlinear Processing

An effective technique for removing range ambiguities (detections at ranges other than the true range of the object) arising when using a burst waveform is to transmit two bursts with different pulse repetition frequencies nearly simultaneously and then to process their outputs nonlinearly. This correspondence introduces two nonlinear processors which combine coincidence detection with either noncoherent multiplication or integration. It is shown that the combined false alarm and ambiguity removal performance of these nonlinear processors is superior to the performance of coincidence detection, noncoherent multiplication, or noncoherent integration when used separately.