立体视觉系统摄象机标定自动化

讨论了基于被动视觉的摄象机标定方法,并完全实现了自动控制,该方法在传统标定方法基础上,以激光探测手段获取场景点（激光斑点）的三维坐标（３Ｄ）;以三步优化查询算法得到该场景点图象坐标（２Ｄ）;采用线性最小二乘算法求解摄 同透视投影矩阵,同时介绍了实验系统,给出了实验结果和精度 。     

基于TMSS320C32的多路声信号实时采集与处理系统

介绍了反武装直升机被动声定位跟踪系统中直升噪声信号实时采集与处理系统的设计,该系统由双CPU并行式结构的两个子系统构成,基于单片机AT89C51的数据采集子系统完成对多路声信号的同步采集,并把数字信号保存到片外共享存储器中,基于TMS320C32DSP的声信号处理子系统从共享存储器中取出采集数据进行高速处理,得到定位跟踪结果,由于数据采集与信号处理分别由不同的微处理器完成,可以同时进行,不同于以往的采集一段数据,处理一段数据的串行工作模式,提高了系统的响应速度与整体性能。     

Hand Motion Tracking Using Simulated Annealing Method in a Discrete Space

Hand tracking is a challenging problem due to the complexity of searching in a 20 degrees of freedom (DOF) space for an optimal estimation of hand configuration. The feasible hand configurations are represented as a discrete space, which avoids learning to find parameters as general configuration space representations do. Then, an extended simulated annealing method with particle filtering to search for optimal hand configuration in the proposed discrete space, in which simplex search running in multi-processor is designed to predict the hand motion instead of initializing the simulated annealing randomly, and particle filtering is employed to represent the state of the tracker at each layer for searching in high dimensional configuration space. Experimental results show that the proposed method makes the hand tracking more efficient and robust.     

Structured scene modeling using micro stereo vision system with large field of view

0　ＩＮＴＲＯＤＵＣＴＩＯＮＴｏａｃｈｉｅｖｅａｕｔｏｎｏｍｏｕｓｎａｖｉｇａｔｉｏｎｉｎｄｉｆｆｅｒｅｎｔｅｎｖｉ ｒｏｎｍｅｎｔｓ ,ｍｏｂｉｌｅｒｏｂｏｔｓｍｕｓｔｂｅｅｎｄｏｗｅｄｗｉｔｈｔｈｅａｂｉｌｉ ｔｙｔｏｐｅｒｃｅｉｖｅｉｔｓｅｎｖｉｒｏｎｍｅｎｔｓｕｆｆｉｃｉｅｎｔｌｙａｎｄｅｆｆｉｃｉｅｎｔｌｙ .Ｒａｎｇｅｓｅｎｓｏｒｓ ,ｓｕｃｈａｓ,ｌａｓｅｒｒａｎｇｅｆｉｎｄｅｒ,ｓｔｒｕｃｔｕｒｅｄｌｉｇｈｔｓｃａｎｎｅｒ,ｓｏｎａｒｔｒａｎｓｄｕｃｅｒｓ,ａｎｄｓｔｅｒｅｏｖｉｓｉｏｎｈａ…     

New E-Commerce Model Based on Multi-Agent Automated Negotiation

A new multi-agent automated negotiation model is developed and evaluated, in which two competitive agents, such as the buyer and seller, have firm deadlines and incomplete information about each other. The negotiation is multi-dimensional in different cases. The model is discussed in 6 kinds of cases with different price strategies, warrantee strategies and time strategies. The model improves the model of Wooldridge and that of Sycara to a certain extent. In all possible situations, the optimal negotiation strategy is analyzed and presented,and an e-commerce model based on multi-agent automated negotiation model is also illustrated for the e-commerce application in the future.     

Cera Self-Calibration in Computer Vision with Precise Estimation of Initial Pareters

A key problem that plagues cera self-calibration, nely that the classical self-calibration algorithms are very sensitive to the initial values of the cera intrinsic pareters, is analyzed and a practical solution is provided. The effect of the cera intrinsic pareters, mainly the principal point and the skew factor is first discussed. Then a practical method via a controlled motion of the cera is introduced so as to obtain an accurate estimation of these pareters. Feasibility of this approach is illustrated by carrying out comprehensive experiments using synthetic data as well as real image sequences. Unreasonable initial values can often make self-calibration impossible, yet a precise initialization guarantees a better and successful reconstruction. Trying to obtain a more reasonable initialization is worthwhile the effort in cera self-calibration.     

一种心脏核磁共振图像左室壁内、外膜分割方法

为了充分利用心脏核磁共振图像(magnetic resonance image,简称MRI)中关于左心室的解剖和功能信息,必须先分割左室壁内、外膜.提出一种基于Snake模型的左室壁内、外膜分割方法.首先提出了Snake模型的卷积虚拟静电场外力模型CONVEF(convolutional virtual electric field),该外力场捕捉范围大、抗噪能力强、在C形凹陷区域等问题上性能突出,而且基于卷积运算,采用快速Fourier变换可以实时计算.就左室壁内膜的分割而言,考虑到左室壁的形状近似为圆形,引入基于圆形约束的能量项.对于左室壁外膜的分割,充分挖掘了左室壁内、外膜形状上的相似性和位置上的相关性,构造了形状相似性内能和一个新的边缘图,该边缘图用来计算新的外力场.基于所有这些策略并采用内膜的分割结果初始化,可以自动、准确地分割外膜.通过对一套活体心脏MR(magnetic resonance)图像进行分割并和手工分割结果和GGVF(generalized gradient vector flow) Snake模型的分割结果进行比较,结果表明该方法是有效的.     

Audio-visual emotion recognition with multilayer boosted HMM

Emotion recognition has become an important task of modern human-computer interaction. A multilayer boosted HMM ( MBHMM) classifier for automatic audio-visual emotion recognition is presented in this paper. A modified Baum-Welch algorithm is proposed for component HMM learning and adaptive boosting ( AdaBoost) is used to train ensemble classifiers for different layers ( cues) . Except for the first layer,the initial weights of training samples in current layer are decided by recognition results of the ensemble classifier in the upper layer. Thus the training procedure using current cue can focus more on the difficult samples according to the previous cue. Our MBHMM classifier is combined by these ensemble classifiers and takes advantage of the complementary information from multiple cues and modalities. Experimental results on audio-visual emotion data collected in Wizard of Oz scenarios and labeled under two types of emotion category sets demonstrate that our approach is effective and promising.     

微型实时多目立体视觉机设计与实现

本文给出一种实时计算场景稠密深度图的多目立体视觉机设计与实现方法.立体视觉机使用多个微型摄像机同步获取场景图像,采用图像修正、LoG滤波、多立体图像对匹配和稠密深度图等并行算法,利用FPGA的大规模并行处理能力和各算法间的多级流水线关系,在一片FPGA芯片上实现了立体视觉信息的实时处理.设计的立体视觉机体积小,运行速度快.当图像分辨率为320×240像素,深度搜索范围为64级,深度图精度为8位,时钟频率为60MHz时,恢复稠密深度图的速度大于30帧/秒.     

一种鱼眼镜头成像立体视觉系统的标定方法

鱼眼镜头成像立体视觉系统在微小型机器人视觉导航和近距离大视场物体识别与定位中有着广泛的应用 .尽管鱼眼镜头摄像机具有很大的视场角 (接近 180°) ,但同时也引入严重的图像变形 ,常规的摄像机标定方法无法使用 .该文提出一种标定鱼眼镜头摄像机立体视觉系统的方法 .在鱼眼镜头变形模型的基础上 ,通过考虑鱼眼镜头成像的径向变形、偏心变形和薄棱镜变形 ,建立了鱼眼镜头成像的精确成像模型 ;然后 ,利用非线性迭代算法 ,精确求解摄像机外部参数、内部参数 .实验表明 ,使用该方法得到的立体视觉系统参数满足精确恢复大场景稠密深度图的要求 .