A video can be seen as a sequence formed by continuous video frames of images, and the colorization process of video actually is the colorization of images. If the existing image colorization method is directly applied to video colorization, it tends to cause flutter or twinkle because of long-term sequentiality of videos. For this problem, a method based on Long Short Term Memory (LSTM) cells and Convolutional Neural Network (CNN) was proposed to colorize the grayscale video. In the method, the semantic features of video frames were extracted with CNN and the time sequence information of video was learned by LSTM cells to keep the time-space consistency of video, then local semantic features and time sequence features were fused to generate the final colorized video frames. The quantitative assessment and user study of the experimental results show that this method achieves good performance in video colorization.

The semi-automatic road extraction method needs more artificial participation and is time-consuming, and its accuracy of road extraction is low. In order to solve the problems, a new method of road extraction from multi-source high resolution remote sensing image based on Fully Convolutional neural Network (FCN) was proposed. Firstly, the GF-2 and World View high resolution remote sensing images were divided into small pieces, the images containing roads were classified by Convolutional Neural Network (CNN). Then, the Canny operator was used to extract the edge feature information of road. Finally, RGB, Gray and ground truth were combined and put into the FCN model for training, and the existing FCN model was extended to a new FCN model with multi-satellite source input and multi-feature source input. The Shigatse region of Tibet was chosen as the research area. The experimental results show that, the proposed method can achieve the extraction precision of 99.2% in the road extraction from high resolution remote sensing images, and effectively reduce the time needed for extraction.

An AdaBoost.M2-NFS model was presented to improve the recognition rate of traditional Neural Fuzzy System (NFS) towards similar plants. The traditional NFS was improved for fusion, and then the new NFS was combined with AdaBoost.M2 to get a new AdaBoost.M2-NFS model. Experimental results show that the new model increases the recognition rate by 3.33 percentage points compared with the single NFS; compared with the linear Support Vector Machine (SVM), its recognition rate increases by 1.11 percentage points; compared with Softmax, its recognition rate increases by 3.33 percentage points. Based on sensitivity and specificity analysis, the non-linear data can get better classification result than the linear data by the proposed algorithm. At the same time, due to the improvement of AdaBoost.M2, the new algorithm has the advantages of modeling quickly and high generalization ability in the field of plant recognition.

In the background of geological data, in order to more accurately and objectively assess the susceptibility of debris flow, a model of regional debris flow susceptibility assessment based on neural network was proposed, and the accuracy of the model was improved by using Mean Impact Value (MIV) algorithm, Genetic Algorithm (GA) and Borderline-SMOTE (Synthetic Minority Oversampling TEchnique) algorithm. Borderline-SMOTE algorithm was used to deal with the classification problem of imbalanced dataset in the preprocessing phase. Afterwards, a neural network was used to fit the non-linear relationship between the main indicators and the degree of proneness, and genetic algorithm was used to improve the fitting speed. Finally, MIV algorithm was combined to quantify the correlation between indicators and proneness. The middle and upper reaches of the Yarlung Zangbo River was selected as the study area. The experimental results show that the model can effectively reduce the overfitting of imbalanced datasets, optimize the original input dimension, and greatly improve the fitting speed. Using AUC (Area Under the Curve) metric to test the evaluation results, the classification accuracy of test set reached 97.95%, indicated that the model can provide reference for assessing the degree of debris flow proneness in the study area under imbalanced datasets.

Aiming at the poor flexibility of Automated Guided Vehicle (AGV) localization method in industrial working field, an Ultra WideBand (UWB) indoor localization system by using DW1000 Radio Frequency (RF) chip was designed and implemented. Firstly, to solve the problem of conflicts and networking of tags, the efficient mechanisms for multi-station ranging and multi-tag scheduling were proposed. Secondly, concerning the low accuracy and poor stability of the triangle centroid localization algorithm caused by maximal ranging errors, a concept of credibility was introduced and the inner triangle centroid algorithm was proposed, which could weaken the influence of maximal ranging errors through credibility coefficient to improve the algorithm performance. Finally, the proposed system was applied to the industrial workshop with 20 tags. For a single tag, the average frequency of coordinate updating reached 24 Hz and its standard deviation was 3 Hz; the static average localization error was 11.7 cm and its standard deviation was 2.5 cm; the dynamic maximum error was within 30 cm. The experimental results show that the proposed localization system has the characteristics of high real-time performance, high precision and high stability.

To meet the needs of ground simulation equipment used for spacecraft, a design of 1553B bus communication terminal Intellectual Property (IP) core based on Field Programmable Gate Array (FPGA) was proposed. On the premise of reliability, the bus system was designed with top-down approach and "two-process" coding method to generate object code with Very-High-Speed Integrated Circuit Hardware Description Language (VHDL), and then was simulated with ModelSim software, and finally, got verified and applied on actual device. The working mode of IP core can be configured with bus controller, remote terminal and bus monitor respectively. In addition, the IP core is easy to be integrated into System on Chip (SoC), and provides more choices for the further application of 1553B bus.

Most existing cloud storage systems are based on the model, which leads to a full dataset scan for multi-dimensional queries and low query efficiency. A KD-tree and R-tree based multi-dimensional cloud data index named KD-R index was proposed. KD-R index adopted two-layer architecture: a KD-tree based global index was built in the global server and R-tree based local indexes were built in local server. A cost model was used to adaptively select appropriate R-tree nodes to publish into global KD-tree index. The experimental results show that, compared with R-tree based global index, KD-R index is efficient for multi-dimensional range queries, and it has high availability in the case of server failure.

Most of Support Vector Data Description (SVDD) methods have blindness and bias issues when working on two-class problems. The authors proposed a new SVDD method based on information entropy. In this algorithm, firstly, the entropy values were resolved respectively of the two classes of samples. Secondly, according to the size of the value, one class was placed inside the ball. Finally, the penalty was given based on the information provided by the sizes of the two sample data and their entropy values. The efficiency of this algorithm was verified by using artificial data and UCI datasets for the data imbalanced classification problem. The experimental results on artificial data sets and UCI data sets show the feasibility and effectiveness of the proposed method.