Copy Move Forgery Detection based on double matching

Copy Move is a technique widespreadly used in digital image tampering, meaning Copy Move Forgery Detection (CMFD) is still a significant research. In this paper, a novel CMFD method is proposed, including double matching process and region localizing process. In double matching process, the first matching is conducted on Delaunay triangles consisting of Local Intensity Order Pattern (LIOP) keypoints, to find the approximate location of suspicious regions. In order to find sufficient keypoint pairs, the existing set of matching triangles is expanded by adding their neighbors iteratively, covering the whole tampered regions, and the second matching with a looser threshold is conducted on the vertices. In the region localizing process, considering the case of multiple copies, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is used to classify the keypoint pairs described in a new model. Experimental results indicate that the proposed method, with good robustness, outperforms some state-of-the-art methods.     

混凝土结构的压电声波检测分析

本文介绍了混凝土结构的压电体波和表面波检测的主要进展,对两种压电声波检测的优缺点进行了总结。体波检测设备一般埋入混凝土内部,需要选择合理的检测部位,检测结果较为精确;声表面波检测无需选择特定的部位,但是检测深度有限。在实际检测工作过程中,可以联合两种方法相互验证。     

A Tradeoff Between Accuracy and Speed for K-Means Seed Determination

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster’s inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed.     

A robust locating multi-optima approach for damage identification of plate-like structures

This paper proposes a robust optimization approach for multiple damage identification of plate-like structures. Different from traditional particle swarm optimizations (PSOs), a combined PSO and niche technique (NPSO) is proposed to solve multimodal optimization problems, with the full consideration of subswarm creation, merging and absorbing mechanism. As a hypersensitive parameter to damage, the curvature mode shape is adopted to construct the objective function. Case studies are conducted to investigate the effectiveness and robustness of the algorithm on multi-damage identification. Simulation results show that the proposed algorithm exhibits robust search performance on identifying damage locations accurately with good convergence behavior. It is hoped that this study can provide guidance on robust damage detection, especially when the structure is subject to multiple damages and external disturbances.     

DCNN深度特征与交替方向乘子的相关滤波跟踪

针对采用相关滤波的判别式目标跟踪遇到的瓶颈问题：由于目标快速移动引起边界效应，使得相关滤波器在学习与更新过程中可能会引入错误，最终错误的累积将导致跟踪失败。在采集深度学习特征与样本相似性度量的基础上，提出一种引入交替方向乘子方法的改进相关滤波目标跟踪算法，选择DCNN深度特征有效地表征待跟踪目标的初始状态，通过在线分类过程中样本相似性比对与半监督学习，辅助解决相关滤波器在学习过程中存在的自学习问题。所提目标跟踪算法特别适合训练样本为持续获得的、同时存储空间较小的机器学习过程，提高目标在快速运动与部分遮挡等复杂情况下的跟踪成功率，针对VOT2016标准测试视频的实验表明：当目标面临快速运动时，对比CN、SAMF、STC算法，所提DA-CFT跟踪算法将跟踪成功率分别由60.4%～73.4%、67.2%～82.9%、80.9%～88.1%提升至85.6%～91.0%。     

基于概要数据结构的全网络持续流检测方法

持续流是隐蔽的网络攻击过程中显现的一种重要特征，它不产生大量流量且在较长周期内有规律地发生，给传统的检测方法带来极大挑战。针对网络攻击的隐蔽性、单监测点的重负荷和信息有限的问题，提出全网络持续流检测方法。首先，设计一种概要数据结构，并将其部署在每个监测点；其次，当网络流到达监测点时，提取流的概要信息并更新概要数据结构的一位；然后，在测量周期结束时，主监测点将来自其他监测点的概要信息进行综合；最后，提出流持续性的近似估计，通过一些简单计算为每个流构建一个位向量，利用概率统计方法估计流持续性，使用修正后的持续性估计检测持续流。通过真实的网络流量进行实验，结果表明，与长持续时间流检测算法（TLF）相比，所提方法的准确性提高了50%，误报率和漏报率分别降低了22%和20%，说明全网络持续流检测方法能够有效监测高速网络流量。     

An integrated approach for aircraft turbofan engine fault detection based on data mining techniques

The present study proposes an algorithm for fault detection in terms of condition‐based maintenance with data mining techniques. The proposed algorithm is applied on an aircraft turbofan engine using flight data and consists of two main sections. In the first section, the relationship between engine exhaust gas temperature (EGT) as the main engine health monitoring criterion and other operational and environmental parameters of the engine was modelled using the data‐driven models. In the second section, a data set including EGT residuals, that is, the difference between the actual EGT of the system and the EGT estimated by the developed model in the health conditions of the engine, was created. Finally, faults occurring in each flight were detected based on the identification of abnormal events by a one‐class support vector machine trained by the health condition EGT residual data set. The results indicated that the proposed algorithm was an effective approach for inspecting aircraft engine conditions and detecting faults, with no need for technical knowledge on the interior characteristics of the aircraft engine.     

基于深度学习的四旋翼无人机单目视觉避障方法

针对无人机避障问题，提出一种基于深度学习的四旋翼无人机单目视觉避障方法。首先通过目标检测框选出目标在图像中的位置，并通过计算目标选框上下边距的长度，以此来估量出障碍物到无人机之间的距离；然后通过协同计算机判断是否执行避障动作；最后使用基于Pixhawk搭建的飞行实验平台进行实验。实验结果表明，该方法可用于无人机低速飞行条件下避障。该方法所用到的传感器只有一块单目摄像头，而且相对于传统的主动式传感器避障方法，所占用无人机的体积大幅减小。该方法鲁棒性较好，能够准确识别不同姿态的人，实现对人避障。     

基于张量分解融合RGB-D图像的物体识别

为了充分利用RGB-D图像的深度图像信息，提出了基于张量分解的物体识别方法。首先将RGB-D图像构造成一个四阶张量，然后将该四阶张量分解为一个核心张量和四个因子矩阵，再利用相应的因子矩阵将原张量进行投影，获得融合后的RGB-D数据，最后输入到卷积神经网络中进行识别。RGB-D数据集中三组相似物体的识别结果表明，利用张量分解融合RGB-D图像的物体识别准确率高于未采用张量分解的物体识别准确率，并且单一错分实例的准确率最高可提升99%。