基于差分进化算法的手眼标定方法

针对眼在手机器人视觉系统的手眼标定问题，提出了一种基于差分进化算法的手眼标定方法。首先建立了眼在手机器人视觉系统手眼标定的数学模型，通过李群李代数理论，将手眼标定问题转化为误差函数的优化问题，同时保证了优化问题的最优解落在特殊欧氏群ＳＥ（３）上。通过差分进化算法对优化问题进行求解，避免了求解过程中的局部最优问题。最后在实物平台上进行了手眼标定实验，实验结果验证了算法的可行性和有效性。     

Effects of apparent image velocity and complexity on the dynamic visual field using a high-speed train driving simulator

Train driving is a highly visual task. The visual capabilities of the train driver affects driving safety and driving performance. Understanding the effects of train speed and background image complexity on the visual behavior of the high-speed train driver is essential for optimizing performance and safety. This study investigated the role of the apparent image velocity and complexity on the dynamic visual field of drivers. Participants in a repeated-measures experiment drove a train at nine different speeds in a state-of-the-art high-speed train simulator. Eye movement analysis indicated that the effect of image velocity on the dynamic visual field of high-speed train driver was significant while image complexity had no effect on it. The fixation range was increasingly concentrated on the middle of the track as the speed increased, meanwhile there was a logarithmic decline in fixation range for areas surrounding the track. The extent of the visual search field decreased gradually, both vertically and horizontally, as the speed of train increased, and the rate of decrease was more rapid in the vertical direction. A model is proposed that predicts the extent of this tunnel vision phenomenon as a function of the train speed.Relevance to industryThis finding can be used as a basis for the design of high-speed railway system and as a foundation for improving the operational procedures of high-speed train driver for safety.     

基于GL0816传感器的高速线阵CMOS相机系统设计

为了满足印刷等高端工业检测中物体快速运动,需要大幅面、高行频、高分辨率图像采集等要求,研发了一款微米级高分辨率、高速线阵工业相机。首先,介绍了高行频、高分辨率国产CMOS图像传感器GL0816的功能与特点。然后,基于该芯片设计了一套高速大幅面高分辨率线阵工业相机系统,该系统采用FPGA作为整个系统的控制核心,以DDR3LSDRAM作为图像缓存器,以GigE vision2.0协议为输出标准,以SFP+作为高速图像输出接口。最后,搭建相机系统测试环境,对所设计的相机进行系统测试。结果表明:该相机系统行分辨率为8 192,可连续采集2 000行作为一帧图像输出,行频为50kHz,动态范围为57.32dB,信噪比为40.95dB,具有实时图像采集功能。该相机系统具有大幅面、高帧频、高分辨率、高信噪比、宽动态范围等优点,适用于印刷检测行业快速运动目标捕获成像及图像实时显示。     

基于深度学习的四旋翼无人机单目视觉避障方法

针对无人机避障问题，提出一种基于深度学习的四旋翼无人机单目视觉避障方法。首先通过目标检测框选出目标在图像中的位置，并通过计算目标选框上下边距的长度，以此来估量出障碍物到无人机之间的距离；然后通过协同计算机判断是否执行避障动作；最后使用基于Pixhawk搭建的飞行实验平台进行实验。实验结果表明，该方法可用于无人机低速飞行条件下避障。该方法所用到的传感器只有一块单目摄像头，而且相对于传统的主动式传感器避障方法，所占用无人机的体积大幅减小。该方法鲁棒性较好，能够准确识别不同姿态的人，实现对人避障。     

Numerical comparison of sampling strategies for BRDF data manifolds

The bidirectional reflectance distribution function (BRDF) is one of the fundamental concepts in such diverse fields as multidimensional reflectometry, computer graphics and computer vision. BRDF manifolds form an infinite-dimensional space, but typically the available measurements are very scarce. Therefore, an efficient learning strategy is crucial when performing the measurements.In this paper, we perform simulation studies within a mathematical framework that allows to establish more efficient BRDF sampling and measurement strategies in the sense of statistical design of experiments and generalized proactive learning. Our simulation studies suggest that the default BRDF measurement strategy is suboptimal for a wide class of loss functions.     

Defect detection in magnetic tile images based on stationary wavelet transform

A novel approach using stationary wavelet transform (SWT) is proposed for automatically detecting low-contrast defects under various light conditions in magnetic tile images. In this method, the uneven background was removed by Sobel operation. Then the index low-pass filtering and the nonlinear enhancement were respectively used to eliminate the interference and enhance the target in subbands produced by SWT. To verify the validity of the proposed algorithm, extensive experiments were conducted in a novel machine vision based system. As the result shows, the proposed method achieves an accuracy rate of 92.86% in detecting various defects in magnetic tile surfaces with the average operation time of 0.5190 s, and is superior to traditional methods in terms of the high reliability and accuracy.     

A machine-vision inspection system for conveying attitudes of columnar objects in packing processes

This paper is a new study on developing a machine vision system for inspecting the conveying attitudes of columnar objects. The presented system consists of image pre-processing, feature extraction, and attitude diagnosis. First of all, in order to segment the objects from the background (namely image pre-processing), an improved maximum between-class variance method is proposed for searching a histogram peak and calculating a threshold value based on the statistics and probability, to solve the problems caused by the non-uniform brightness in a realistic conveyor belt. Then, an open morphological operation is used to eliminate the noise from the binary images produced in the pre-processing step. In the second step (feature extraction), the features of columnar objects are determined by four methods, edge line detecting method, intercepting method, rectangle locating method and feature statistic method. Finally, the diagnosis for the conveying attitudes of columnar objects is based on a hybrid classifier using random forests, and a fuzzy logic. The proposed system is applied to a realistic process for packing industrial explosives. The results of experiments show that the proposed system allows efficient and accurate 100% inspection for the conveying attitude, which ensures the high speed and steady operation of a packing line.     

Visual classification of waste material for nuclear decommissioning

Redundant and nonoperational buildings at nuclear sites go through the process of ‘decommissioning’, involving decontamination of nuclear waste material and demolition of physical infrastructure. One challenging problem currently faced by the nuclear industry during this process is the segregation of redundant waste material into a choice of ‘post-processes’ based upon the nature and extent of its radioactivity that may pose a serious threat to the environment. Following an initial inspection, waste materials are subjected to treatment, disruption and consigned to various types of export containers. To date, the process of objects (waste) classification is performed manually. In order to automate this process, robotic platforms can be deployed that utilise robust and fast vision systems for visual classification of nuclear waste material. This paper proposes a novel solution incorporating a machine vision system for autonomous identification of waste material from decommissioned nuclear plants. Rotation and scale invariant moments are used to describe object shapes in the visual scene whereas a random forest learning algorithm performs object classification. Using nuclear waste simulants (from the nuclear plant decommissioning process), an exhaustive ‘proof-of-concept’ quantitative assessment of the proposed technique is performed, in order to test its applicability within the current problem domain.     

Camera based precision measurement in improving measurement accuracy

This paper presents a vision based software system which is developed in order to improve the precision measurement in machining technology. Precision measurement, monitoring and control are very important in manufacturing technology. In order to increase the accuracy of the measurement system; application of camera or vision is very useful. Automatic control is also vital for the measurement performance to be improved. During measurement of the gear profile; human monitoring sometimes may face danger as this is a stylus contact scanning system and the stylus is very small and thin as well as the probe moves with a maximum speed of 10 mm/s. The existing methods for gear measurement are either time consuming or expensive. This paper presents the successful implementation of the vision system in precision engineering which saves times and increases safety of the measurement system with the increment of the measurement performance. Color based stylus tracking algorithm is implemented in order to acquire better performance of the developed system. Stylus tracking based measurement is the key issue of the present research.