Deep Convolutional Feature Fusion Model for Multispectral Maritime Imagery Ship Recognition

Combining both visible and infrared object information, multispectral data is a promising source data for automatic maritime ship recognition. In this paper, in order to take advantage of deep convolutional neural network and multispectral data, we model multispectral ship recognition task into a convolutional feature fusion problem, and propose a feature fusion architecture called Hybrid Fusion. We fine-tune the VGG-16 model pre-trained on ImageNet through three channels single spectral image and four channels multispectral images, and use existing regularization techniques to avoid over-fitting problem. Hybrid Fusion as well as the other three feature fusion architectures is investigated. Each fusion architecture consists of visible image and infrared image feature extraction branches, in which the pre-trained and fine-tuned VGG-16 models are taken as feature extractor. In each fusion architecture, image features of two branches are firstly extracted from the same layer or different layers of VGG-16 model. Subsequently, the features extracted from the two branches are flattened and concatenated to produce a multispectral feature vector, which is finally fed into a classifier to achieve ship recognition task. Furthermore, based on these fusion architectures, we also evaluate recognition performance of a feature vector normalization method and three combinations of feature extractors. Experimental results on the visible and infrared ship (VAIS) dataset show that the best Hybrid Fusion achieves 89.6% mean per-class recognition accuracy on daytime paired images and 64.9% on nighttime infrared images, and outperforms the state-of-the-art method by 1.4% and 3.9%, respectively.

Study of grain alignment efficiency and a distance estimate for small globule CB4

We study the polarization efficiency（defined as the ratio of polarization to extinction） of stars in the background of the small, nearly spherical and isolated Bok globule CB4 to understand the grain alignment process. A decrease in polarization efficiency with an increase in visual extinction is noticed. This suggests that the observed polarization in lines of sight which intercept a Bok globule tends to show dominance of dust grains in the outer layers of the globule. This finding is consistent with the results obtained for other clouds in the past. We determined the distance to the cloud CB4 using near-infrared photometry（2MASS J H KScolors） of moderately obscured stars located at the periphery of the cloud. From the extinction-distance plot,the distance to this cloud is estimated to be（459 ± 85） pc.

Scientific Basis of System Programming

Theoretical foundations of programming systems from modules, objects, components, services are given. Identified relevant theory of programming proposed by the author with the participation of students and postgraduates: graph modular programming theory with graph representation as an adjacency matrix for mathematical achievability of graph vertices;theory of generating programming and theory of software factories;theory of graph object and component modeling (OCM) by means of logic and algebra-mathematical theory of determining individual elements of complex systems;theory of system programming based on ontological and service-component models (SOA, SCA) with security and quality systems. The Internet Smart and Nanotechnology are given for perspective transition of computer technology to nanotechnology.