基于哈希算法的图像拷贝检测

在局部保持投影算法（LPP）及最大熵模型的基础上提出了一种基于哈希算法的图像拷贝检测算法。该算法通过对LPP进行优化,可以对已有的图像特征进行快速降维处理,并避免过拟合现象的出现。同时,将低维度特征映射为紧凑的二进制哈希码,大大减少了存储和计算开销,能在千万级图像数据库上实现高效拷贝检测。通过实验确定了使拷贝检测质量最优的哈希码长度和汉明码。实验结果表明,该算法能够获得很好的拷贝检测效果。     

流函数法在 UUV 航路规划中的应用及改进

UUV相关技术的发展越来越多地受到广泛重视,其航路规划算法研究日益成为相关研究领域的重要课题。论文介绍了一种起源于流体力学的算法———流函数法,可有效应用于UUV的局部航路规划。针对UUV在实际应用中由于自身机动性、探测性能约束而产生的问题,提出了改进流函数法,能够更有效地规划航路。     

沥青路面压实度实时监测系统

针对传统压实度检测方法存在滞后性、偶然性等问题,提出沥青路面压实度实时监测系统实时监测和控制沥青路面的压实度。通过刚度与压实度的理论关系推导,验证此系统的理论可行性。根据压路机的特性,选择合适的激振器模拟碾压过程中振动轮的振动信号。实验室的静态试验（车辙板成型试验）表明,该沥青路面压实度实时监测系统能有效提高沥青面层压实质量。     

铁路桥梁非接触检测技术发展

针对铁路桥梁非接触检测的迫切需求,对桥梁非接触检测技术进行了探讨,介绍了基于全球导航卫星系统(GNSS)和合成孔径雷达干涉技术(InSAR)的星载遥感测试技术,以及基于光电图像、地基干涉雷达和激光多普勒测振技术的测站式测试技术的原理、方法与精度.对比分析发现星载遥感测试技术不适用于铁路常用跨度桥跨结构的测试.从测试信号...     

RFID技术在高速公路行车管理中的应用

RFID技术是采用射频通信的非接触式自动识别技术,可以广泛应用到各个行业当中。例如,利用RFID技术可以获得高速公路区间车辆的行驶速度,从而判断车辆是否超速行驶。因此高速公路管理采用RFID技术可以有效降低超速行为,提升行车安全性。     

Wavelet Transform Modulus Maxima-Based Robust Digital Image Watermarking in Wavelet Domain

A new robust watermarking approach was proposed in 2D continuous wavelet domain (CWT).The watermark is embedded into the large coefficients in the middle band of wavelet transform modulus maxima (WTMM) of the host image.After possible attacks,the watermark is then detected and extracted by correlation analysis.Compared with other wavelet domain watermarking approaches,the WTMM approach can endow the image with both rotation and shift invariant properties.On the other hand,scale invariance is achieved with the geometric normalization during watermark detection.Case studies involve various attacks such as shifting,lossy compression,scaling,rotation and median filtering on the watermarked image,and the result shows that the approach is robust to these attacks.     

Outlier mining based abnormal machine detection in intelligent maintenance

Assessing machine’s performance through comparing the same or similar machines is important to implement intelligent maintenance for swarm machine. In this paper, an outlier mining based abnormal machine detection algorithm is proposed for this purpose. Firstly, the outlier mining based on clustering is introduced and the definition of cluster-based global outlier factor (CBGOF) is presented. Then the modified swarm intelligence clustering(MSIC) algorithm is suggested and the outlier mining algorithm based on MSIC is proposed. The algorithm can not only cluster machines according to their performance but also detect possible abnormal machines. Finally, a comparison of mobile soccer robots’ performance proves the algorithm is feasible and effective.     

A novel approach to design robust fault detection filter for networked control systems

In this paper, an approach for designing robust fault detection filter (RFDF) of networked control systems (NCSs) with unknown inputs is studied. The design aims at implementing the optimal trade-off between robustness of unknown inputs (including the item produced by networked-induced delay) and sensitivity of fault. The key design issue is to introduce an optimal fault detection filter based on NCSs with the control law compensation as the reference residual model of NCSs and to formulate the RFDF design as a model-matching problem. By applying H _∞ optimization technique, linear matrix inequality (LMI) approach is given to solve the model-matching problem. The validity of the proposed approach is shown by a numerical example.      

基于序列图像运动分割的车辆边界轮廓提取算法

为了准确获得图像感兴趣区中运动车辆的形状特征,提出了一种新的车辆边界轮廓提取算法.利用连续3帧图像,对包含同一运动车辆的图像感兴趣区进行光流场分割,以获取目标运动区域,通过平移运动区域的左、右边界获得正确的车辆区域及其封闭边界轮廓,通过放大运动矢量计算公式的阈值来提高其运行效率.试验结果表明:该算法可从具有复杂自然场景的图像序列中检测出完整的运动车辆边界轮廓,检测正确率在95%以上.