Method to generate training samples for neural network used in target recognition

Training neural network to recognize targets needs a lot of samples.People usually get these samples in a non-systematic way,which can miss or overemphasize some target information.To improve this situation,a new method based on virtual model and invariant moments was proposed to generate training samples.The method was composed of the following steps:use computer and simulation software to build target object’s virtual model and then simulate the environment,light condition,camera parameter,etc.;rotate the model by spin and nutation of inclination to get the image sequence by virtual camera;preprocess each image and transfer them into binary image;calculate the invariant moments for each image and get a vectors’ sequence.The vectors’ sequence which was proved to be complete became the training samples together with the target outputs.The simulated results showed that the proposed method could be used to recognize the real targets and improve the accuracy of target recognition effectively when the sampling interval was short enough and the circumstance simulation was close enough.     

基于伪随机序列自相关性的新型超声波测距系统

针对传统超声波传感器存在受环境因素影响大、抗干扰能力差等缺陷,提出了一种新型超声波测距系统的设计方法.该超声波测距系统基于伪随机序列自相关性原理,采用模块化设计,可准确地测量出超声波的传播速度和渡越时间,进而计算出障碍物的距离.采用低功耗,高性能的TMS320VC5509A DSP作为信息处理器,采用基于快速傅里叶变换(FFT)的相关判别算法,有效地提高了实时性.改进了超声波接收电路,采用高速绝对值电路代替传统的检波电路,可高效地从接收到的超声波信号中解调出伪随机序列.根据所设计的超声波测距系统的工作原理,提出了适用于该系统的误差校正方法.在干扰存在的情况下,进行了性能测试实验,实验结果表明,该超声波测距系统的测距误差在1.8%以内,具有良好的抗干扰性.     

3D reconstruction method based on contour features

To guarantee the accuracy and real-time of the 3D reconstruction method for outdoor scene, an algorithm based on region segmentation and matching was proposed. Firstly, on the basis of morphological gradient information, obtained by comparing color weight gradient images and proposing a multi-threshold segmentation, scene contour features were extracted by a watershed algorithm and a fuzzy c-means clustering algorithm. Secondly, to reduce the search area, increase the correct matching ratio and accelerate the matching speed, the region constraint was established according to a region''s local position, area and gray characteristics, the edge pixel constraint was established according to the epipolar constraint and the continuity constraint. Finally, by using the stereo matching edge pixel pairs, their 3D coordinates were estimated according to the binocular stereo vision imaging model. Experimental results show that the proposed method can yield a high stereo matching ratio and reconstruct a 3D scene quickly and efficiently.     

机器人视觉目标数字图像实时处理及分割

机器人视觉目标图像信噪比低、背景噪声干扰大,目标识别处理通常利用目标的灰度信息进行预处理。文中设计一种基于数学形态学和遗传算法的灰度图像实时预处理和阈值处理技术图像分割方法。描述图像的基本结构和特征,用具有一定形态的结构元去度量和提取图像中的对应形态,以达到对图像分析和识别;经过预处理的原始图像,采用基于遗传算法的最大类间方差图像分割法,非线性快速地查找到最优的分割阈值,从噪声图中分割出可能目标。基于ARM嵌入式微处理器,以复杂可编程逻辑器件CPLD作为时序控制单元,进行图像处理、分割,实现了图像信息的采集、存储、传输及处理为一体。仿真实验表明,该方法实时性好,简捷、快速,对运动目标的图像识别有较好的实用价值。     

轮胎安全性能智能检测系统无线异步通讯程序的研究与设计

通过开展对汽车轮胎安全性能智能检测和隐患预警系统无线异步通讯协议的制定、适于PIC系列微控制器的CRC算法的分析以及无线异步通讯程序框图的设计,实现了系统子机与主机间有关轮胎温度和气压实时信息的准确传输     

新型锥蜗杆传动在饮料高速灌装机中的应用

分析了在国产新型饮料高速灌装机上采用锥蜗杆传动的先进性和可行性，并结合设计实例介绍了锥蜗杆传动的设计方法与步骤。     

新型汽车轮胎气压在线检测装置的研究与设计

轮胎的过压或欠压是引发轮胎安全事故的重要原因,了解并控制轮胎的气压状况将有利于提高轮胎的安全使用性能。 为此,研究了国外有关轮胎气压在线检测技术的最新动态,提出了汽车轮胎安全性能智能检测和隐患预警系统的技术构想, 组建了新型轮胎气压在线检测装置,实现了从轮胎上直接提取气压变化的实时信息,可完成对轮胎气压波动情况的在线检 测、智能分析和实时处理。进行了相应的系统软硬件仿真与调试工作。仿真实验和实际测试证明,该在线检测装置可帮助驾驶 员及时了解并准确掌握轮胎的安全性能和使用条件,从而有效提升了轮胎使用的安全性和可靠性。     

柔性成圆辊减振弹簧的优化设计

柔性成圆辊减振弹簧是实现金属罐体成国高速化和柔性化的关键零件。但按常规方法设计出来的减振弹簧，存在短期断裂的隐患。本文提出该减振弹簧优化设计的方法，并在工艺和结构上采取相应措施，从而解决了柔性成圆辊减振弹簧的短期断裂问题。     

一种四足机器人机体冲击力检测算法

四足机器人机体冲击力的有效检测能够为动态平衡控制提供决策依据,而与之相关的研究在现有文献中尚未见到,为此提出了一种新型的四足机器人机体冲击力检测算法;通过机器人的动力学分析和基于卡尔曼滤波器的姿态求解,获得腿部冲击力加速度和重力加速度在机体坐标系中的分量,并将其从加速度计输出信号中分离以获得机体冲击力加速度,完成对机体冲击力的检测;对四足机器人进行了动力学仿真。结果表明:所提出的算法能够有效地实现机体冲击力的检测。