3D human pose estimation in motion based on multi-stage regression

3D human pose estimation in motion is a hot research direction in the field of computer vision. However, the performance of the algorithm is affected by the complexity of 3D spatial information, self-occlusion of human body, mapping uncertainty and other problems. In this paper, we propose a 3D human joint localization method based on multi-stage regression depth network and 2D to 3D point mapping algorithm. First of all, we use a single RGB image as the input, through the introduction of heatmap and multi-stage regression to constantly optimize the coordinates of human joint points. Then we input the 2D joint points into the mapping network for calculation, and get the coordinates of 3D human body joint points, and then to complete the 3D human body pose estimation task. The MPJPE of the algorithm in Human3.6 M dataset is 40.7. The evaluation of dataset shows that our method has obvious advantages.     

The Bivariate Transmuted Family of Distributions: Theory and Applications

The bivariate distributions are useful in simultaneous modeling of two random variables. These distributions provide a way to model models. The bivariate families of distributions are not much widely explored and in this article a new family of bivariate distributions is proposed. The new family will extend the univariate transmuted family of distributions and will be helpful in modeling complex joint phenomenon. Statistical properties of the new family of distributions are explored which include marginal and conditional distributions, conditional moments, product and ratio moments, bivariate reliability and bivariate hazard rate functions. The maximum likelihood estimation (MLE) for parameters of the family is also carried out. The proposed bivariate family of distributions is studied for the Weibull baseline distributions giving rise to bivariate transmuted Weibull (BTW) distribution. The new bivariate transmuted Weibull distribution is explored in detail. Statistical properties of the new BTW distribution are studied which include the marginal and conditional distributions, product, ratio and conditional momenst. The hazard rate function of the BTW distribution is obtained. Parameter estimation of the BTW distribution is also done. Finally, real data application of the BTW distribution is given. It is observed that the proposed BTW distribution is a suitable fit for the data used.     

攻击型无人机切换控制系统容错算法研究

攻击型无人机单侧发射或投放重型武器时,可将飞行控制系统看作是一个切换控制系统。针对常见的常值型和时变型两种执行器故障,提出了一种自适应观测器设计方法,同时结合状态反馈控制设计了容错控制器。通过Lyapunov函数推出了观测器的误差是关于故障界输入状态实际稳定的充分条件,通过平均驻留时间方法证明了切换控制系统是全局输入状态实际稳定的。某型攻击型无人机仿真实例表明,此方法能在准确估计故障大小的基础上,有效保持切换飞行控制系统的性能,应用前景十分广阔。     

Coarse head pose estimation of construction equipment operators to formulate dynamic blind spots

Several hundred workers die in construction in the United States every year because equipment operators are unable to see their fellow workers during operation of their vehicle. In this paper we propose a step towards improving this situation by providing an automated method based on range imaging for estimating the coarse head orientation of a construction equipment operator. This research utilizes commercially-available low resolution range cameras to measure the continuously changing field-of-view (FOV) of an equipment operator in outdoor construction. This paper presents a methodology to measure so-called dynamic blind spot maps. The dynamic blind spot map is then projected on a known static equipment blind spot map that already exists to each construction vehicle. A robust computational coarse head pose estimation algorithm and results to three different pieces of construction equipment and multiple operators are presented. The developed method has the potential in automatically determining the spaces around vehicles that are currently not in the field-of-view of the vehicle operator thus providing eventually additional means and technology for improving safety in construction.     

Systematic robustness analysis of least squares mobile robot velocity estimation using a regular polygonal optical mouse array

This paper presents the robust velocity estimation of an omnidirectional mobile robot using a regular polygonal array of optical mice that are installed at the bottom of a mobile robot. First, the velocity kinematics from a mobile robot to an array of optical mice is derived, from which the least squares estimation of the mobile robot velocity is obtained as the simple average of the optical mouse velocity readings. Second, it is shown that a redundant number of optical mice contributes to the robustness of the least squares mobile robot velocity estimation against both measurement noises and partial malfunction of optical mice. Third, the sensitivity analysis of the least squares mobile robot velocity estimation to imprecise installation of optical mice is made, from which a practical method of optical mouse position calibration is devised. Finally, some experimental results using commercial optical mice are given to demonstrate the validity and performance of the proposed mobile robot velocity estimation. Copyright © 2011 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

SPECTRAL RADIUS,KRONECKER PRODUCTS AND STATIONARITY

Abstract. We provide a stochastic proof of the inequality ρ(A?A+B?B) ≥ρ(A?A), where ρ(M) denotes the spectral radius of any square matrix M, i.e. max{|eigenvalues| of M}, and M?N denotes the Kronecker product of any two matrices M and N. The inequality is then used to show that stationarity of the bilinear model will imply stationarity of the linear part, i.e. the linear ARMA model for r= 1 and q= 1. Furthermore, it is shown that stationarity of the subdiagonal model, i.e. the bilinear model with b_ij=0 for i< j, again implies stationarity of its linear part, provided that the stationarity condition given by Bhaskara Rao and his colleagues is met. Interestingly, the conclusion that stationarity of the subdiagonal models, implies that the linear component models cannot be extended to the general non-subdiagonal bilinear models. The last observation is demonstrated via a simple example with p=m= 1, r= 0 and q= 2.     

低温裂纹张开位移预测方法的讨论

把低温影响下的COD试验数据用灰色理论中的累加方法进行累加，可以使一组没有规律的数据成为一条光滑的曲线．然后利用人工神经网络和自适应模糊推理系统两种方法进行预测，算例的结果表明用一次累加后的数列预测精度较高。     

Effective DOA Estimation Under Low Signal-to-Noise Ratio Based on Multi-Source Information Meta Fusion

Efficiently performing high-resolution direction of arrival (DOA) estimation under low signal-to-noise ratio (SNR) conditions has always been a challenge task in the literatures. Obvi-ously, in order to address this problem, the key is how to mine or reveal as much DOA related in-formation as possible from the degraded array outputs. However, it is certain that there is no per-fect solution for low SNR DOA estimation designed in the way of winner-takes-all. Therefore, this paper proposes to explore in depth the complementary DOA related information that exists in spa-tial spectrums acquired by different basic DOA estimators. Specifically, these basic spatial spec-trums are employed as the input of multi-source information fusion model. And the multi-source in-formation fusion model is composed of three heterogeneous meta learning machines, namely neural networks (NN), support vector machine (SVM), and random forests (RF). The final meta-spec-trum can be obtained by performing a final decision-making method. Experimental results illus-trate that the proposed information fusion based DOA estimation method can really make full use of the complementary information in the spatial spectrums obtained by different basic DOA estim-ators. Even under low SNR conditions, promising DOA estimation performance can be achieved.     

基于阈值分割的松材线虫病树计数与定位

松材病虫病是最紧迫的威胁之一,最近对中国针叶林造成了严重破坏,为了阻止松材病虫病的快速传播,必须在早期准确检测和计数受感染的树木。提出了一种基于密度图的方法,用于从高分辨率航拍图像中估计具有松材病虫病的树木数量,方法引入了阈值分割、形态处理和超像素技术,以最大限度地减少由于建筑物和岩石等相似背景物体引起的误差。实验表明,所提出的方法优于密度学习 算法,平均绝对误差、均方根误差和绝对误差方差分别从21.3、22.2和127.2减少到8.0、11.7和59.6,计数准确率从54.7%提高到81.3%。     

Estimation in Random Coefficient Autoregressive Models

Abstract. We propose the quasi‐maximum likelihood method to estimate the parameters of an RCA(1) process, i.e. a random coefficient autoregressive time series of order 1. The strong consistency and the asymptotic normality of the estimators are derived under optimal conditions.