Proceedings of the 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE 2018)

Session: Artificial Intelligence and Recognition Technology

18 articles
Proceedings Article

The Application of Real-Time Object Detection on Aerial HD Videos Based on Deep CNN

Guanghui Xu, Shuai Xie, Jun Wang, Guodong Wu
Efficient real-time object detection in aerial HD videos is an urgent need, with the increasing use of UAV(unmanned aerial vehicles) in various fields. But it is still challenging to detect objects accurately and timely due to its large pixel size and relatively small objects. We use the popular SSD...
Proceedings Article

Design of the UAV Digital Actuator Automatic Test System Based on Dual-core Microcontroller TMS320F28377D

Tao Yang, Liren Chai, Gang Wang
For purpose of UAV digital actuator test, one of UAV's key components, whose static and dynamic performance impacts on the UAV maneuvering performance, this paper studies an automatic digital actuator test system, introduces its hardware and software design scheme, and demonstrates its application. The...
Proceedings Article

A Load Identification Technology for Wireless Smart Home Systems

Zhenchao Xie, Daohong Lin, Yufeng Chen, Xinshu Wan
Aiming at the applications in wireless smart homes, a wireless charging system based on LCL topology is designed. Moreover, the constant-current (CC) output of the system is realized according to the charging characteristics of lithium batteries. On this basis, a charging strategy is proposed, which...
Proceedings Article

A Feasible Control Method for Incomplete Symmetrical Marine Robot

Lei Zhang, Zaopeng Dong, Yongsuo Yan, Yuyin Cao
For the incomplete symmetrical underactuated USV (unmanned surface vehicle), this paper proposed a global asymptotic stabilization control method. The global diffeomorphism transformation for the USV model was performed twice in order to obtain the form of nonlinear cascade systems, so the stabilization...
Proceedings Article

Develop the AI Literacy of Infants by Deeply Integrated English Learning and Robot Education

Zhongyu Zhang
In this paper, a new learning model which integrate the English Learning and Robot Education for infants was proposed. According to this model, a textbook of using robot to teach English was designed. A corresponding course which matched with the textbook was developed. An experiment of using this course...
Proceedings Article

A Hybrid Fusion Algorithm for Integrated INS/UWB Navigation and Its Application in Vehicle Platoon Formation Control

Yingmao Lu, Jianjun Yi, Liang He, Xiaomin Zhu, Pengfei Liu
The vehicle positioning technology is playing an important role in Cooperative Vehicle Infrastructure System (CVIS). In those single positioning modes, the precision of wireless positioning is greatly affected by the environment. However, the accumulative errors of inertial navigation system (INS) and...
Proceedings Article

The Research of Internet Identity Authentication System Based on Fingerprint Information

Feng Xiao, Yue Zhang, Fei Zhang, Yongzhen Li
With the Internet stepping into thousands of households, human beings really come into in the age of the Internet, When people are cheering for their achievements, however, information security has gradually become our incubus. And how to ensure the security of information is the most urgent problem...
Proceedings Article

Multi-Network Fusion Based on CNN for Facial Expression Recognition

Chao Li, Ning Ma, Yalin Deng
We propose a method which is multi-network fusion (MNF) based on CNN to recognize facial expressions. Our experimental data adopts the ICML2013 facial expression recognition contest's dataset (FER-2013) and JAFFE dataset. Based on the classic Tang's network structure and Caffe-ImageNet structure, we...
Proceedings Article

Human Face Age Recognition Based on Convolutional Neural Networks

Zijiang Zhu, Yi Hu, Dong Liu, Xiaoguang Deng, Junshan Li
In the field of image recognition, the issue of face age recognition has attracted the attention of many scholars, and a lot of outstanding algorithms have been proposed, but the correctness rate of age recognition is not high. To improve the AGE identification accuracy, this paper proposes a face AGE...
Proceedings Article

Face Recognition Based on LBP(2D)2PCA+SVM

Yanmei Jiang, Wei Wei, Xue Liu, Ying Shi
In this work, we present a novel approach of face recognition which considers local binary pattern (LBP), principal component analysis (PCA) and support vector machine (SVM) algorithms, which is named as LBP(2D)2PCA+SVM. This method firstly extracts facial texture features, then uses (2D)2PCA algorithm...
Proceedings Article

The Colony Count Based on Image Processing Using Matlab and Photoshop

Xiaoming Chen, Shufang Li, Zhijun Zhang, Jun Gao
Using two conventional software programs to do a counting method on the colony image from a normal photograph, and the comparison between the methods.
Proceedings Article

CT Image Segmentation Algorithm Based on Merging of Similar Adjacent Components

Xueguang Sun, Weigen Qiu
CT is one of the most widely used medical imaging techniques. Image segmentation is of great significance to medical image aided clinical diagnosis. Due to the complexity of structure and shape of CT image, and the inhomogeneity of organization, the commonly used image segmentation algorithm can not...
Proceedings Article

BDS Common-View Method Based on CGGTTS V2E Standard

Xu Liu, Dangli Zhao, Junliang Liu
CCTF published CGGTTS for Common GNSS Generic Time Transfer Standard that is CGGTTS V2E. To support the standard in the BDS common-view, the paper refers to the standard and simulates corresponding algorithm in the standard realizing BDS common-view method based on CGGTTS V2E. The result show that the...
Proceedings Article

An Adaptive Bitrate Algorithm Based on Estimation and Video Adaptation for Improving QoE in DASH

Saba Qasim Jabbar, Dheyaa Jasim Kadhim, Yu Li
Dynamic Adaptive streaming over HTTP (DASH) is widely used by content providers for video delivery and dominates traffic on cellular networks. The variation in both video bitrate and network bandwidth badly impacts on the user Quality of Experience (QoE), so recent works is going to submitting better...
Proceedings Article

Vehicle Target Detection Based on Improved Mixed Gaussian Modeling

Caiyun Xie, Ruxia Hong, Jing Wang, Hong Yu
In the modern world, with the rapid development of science and technology, computer and related technologies have been used in many fields; of course, intelligent video surveillance system cannot do without computer technology. This system also cannot do without the core issue: the detection of the goal...
Proceedings Article

A Precision Evaluating Method of DEM Using Map Spots Generated by Contour Superposition

Zechun Huang, Zhu Xu, Qianning Zhang, Min Xiao, Zipu Liu, Yongyou Qian, Tianting He
Aiming at the shortcomings of traditional contour superposition analysis in quantitative evaluation of DEM error, the purpose of this paper is to propose a new method to measure the DEM accuracy by using the map spots of contour superposition. To begin with, the concepts of the difference rate and the...
Proceedings Article

Sight Spot Buffer Model Based on Tourists' Interests

Xiao Zhou, Shun He, Shixiang Zhang, Wei Chen, Yu Chen, Youwei Ma
Aim at the current problems that tourism GIS cannot provide individual service to meet the needs of tourists, this paper brings forward sight spot buffer model based on tourists' interests and needs. Firstly, sight spot classification model is set up and all the sight spots are coded. According to tourists'...
Proceedings Article

Research on Creation and Technology to Make Large-scale Production of Vertical Greening Wall

Wanlu Luo, Jianwu Ma
This paper introduces a kind of vertical greening wall system on which climbing plants could grow. It emphasizes on illustrating that this system could be manufactured in large scale in factories in advance, and climbing plants can grow on a nursery-land-based structure to become a landscape. It has...