多尺度特征融合的二维编码图像识别

为实现二维编码同时适合机器和人的识读,提出了一种二维编码图像结合的新型二维图像编码技术,并针对该二维编码图像无定位标识的特点,采用目标识别的算法进行识别,同时改进了SSD(Single Shot Multibox Detector)算法使其适用于此类目标识别。该算法针对小目标的识别特点,去掉了原有的空洞卷积层以及选择了浅层的图层进行特征融合,达到了准确识别二维编码图像的效果。此外搭建了基于GTX1080型号的GPU、Ubantu Linux和TensorFlow的深度学习平台,提出了一种网络学习和验证方法,该方法通过电脑生成相应的数据集来训练网络,并采用合成的数据集和真实图片分别对网络进行验证和测试。测试结果表明,该方法训练的网络对具有良好拍照条件的真实图片的编码识别准确率达到100%。

Direct solution for fixed source location using well-posed TDOA and FDOA measurements

Based on the time differences of arrival(TDOA) and frequency differences of arrival(FDOA) measurements of the given planar stationary radiation source, the joint TDOA/FDOA location algorithm which solves the location of the target directly is proposed. Compared with weighted least squares(WLS) methods,the proposed algorithm is also suitable for well-posed conditions,and gets rid of the dependence on the constraints of Earth's surface. First of all, the solution formulas are expressed by the radial range. Then substitute it into the equation of the radial range to figure out the radial range between the target and the reference station. Finally use the solution expression of the target location to estimate the location of the target accurately. The proposed algorithm solves the problem that WLS methods have a large positioning error when the number of observation stations is not over-determined. Simulation results show the effectiveness of the proposed algorithm, including effectively increasing the positioning accuracy and reducing the number of observatories.

COMPARISON OF TDOA LOCATION ALGORITHMS WITH DIRECT SOLUTION METHOD

For Time Difference Of Arrival(TDOA) location based on multi-ground stations scene,two direct solution methods are proposed to solve the target position in TDOA location.Therein,the solving methods are realized in the rectangular and polar coordinates.On the condition of rectangular coordinates,first of all,it solves the radial range between the target and reference station,then cal-culates the location of the target.In the case of polar coordinates,the azimuth between the target and reference station is solved first,then the radial range between the target and reference station is figured out,finally the location of the target is obtained.Simultaneously,the simulation and comparison analysis are given in detail,and show that the polar solving method has the better fuzzy performance than that of rectangular coordinate.

CoN-Ⅰ高模量改性沥青制备及性能研究

高模量沥青是解决路面车辙问题的有效途径之一,对成品SBS沥青添加CoN-I高模量改性剂研制高模量沥青,对其三大指标及布氏黏度性能进行分析研究,研究结果表明:改性剂的加入使沥青的软化点升高、针入度减小、低温延性降低,黏度增大;当改性剂掺量为17%时,调制的CoN-I高模量沥青性能指标满足高模量沥青技术指标标准;结合沥青气动回弹试验进一步分析验证沥青性能变化,沥青蠕变变形与针入度具有较好的相关性。