A Novel 6G Scalable Blockchain Clustering-Based Computer Vision Character Detection for Mobile Images

6G is envisioned as the next generation of wireless communication technology,promising unprecedented data speeds,ultra-low Latency,and ubiquitous Connectivity.In tandem with these advancements,blockchain technology is leveraged to enhance computer vision applications’security,trustworthiness,and transparency.With the widespread use of mobile devices equipped with cameras,the ability to capture and recognize Chinese characters in natural scenes has become increasingly important.Blockchain can facilitate privacy-preserving mechanisms in applications where privacy is paramount,such as facial recognition or personal healthcare monitoring.Users can control their visual data and grant or revoke access as needed.Recognizing Chinese characters from images can provide convenience in various aspects of people’s lives.However,traditional Chinese character text recognition methods often need higher accuracy,leading to recognition failures or incorrect character identification.In contrast,computer vision technologies have significantly improved image recognition accuracy.This paper proposed a Secure end-to-end recognition system(SE2ERS)for Chinese characters in natural scenes based on convolutional neural networks(CNN)using 6G technology.The proposed SE2ERS model uses the Weighted Hyperbolic Curve Cryptograph(WHCC)of the secure data transmission in the 6G network with the blockchain model.The data transmission within the computer vision system,with a 6G gradient directional histogram(GDH),is employed for character estimation.With the deployment of WHCC and GDH in the constructed SE2ERS model,secure communication is achieved for the data transmission with the 6G network.The proposed SE2ERS compares the performance of traditional Chinese text recognition methods and data transmission environment with 6G communication.Experimental results demonstrate that SE2ERS achieves an average recognition accuracy of 88%for simple Chinese characters,compared to 81.2%with traditional methods.For complex Chinese characters,the average recognition accuracy improves to 84.4%with our system,compared to 72.8%with traditional methods.Additionally,deploying the WHCC model improves data security with the increased data encryption rate complexity of∼12&higher than the traditional techniques.

Application of Machine Vision to Vehicle Automatic Collision Warning Algorithm

Using the new technologies such as information technology, communication technology and electronic control technology, vehicle collision warning system（CWS） can acquire road condition, adjacent vehicle march condition as well as its dynamics performance continuously, then it can forecast the oncoming potential collision and give a warning. Based on the analysis of driver＇s driving behavior, algorithm＇s warning norms are determined. Based on warning norms adopting machine vision method, the cooperation collision warning algorithm（CWA） model with multi-input and multi-output is established which is used in supporting vehicle CWS. The CWA is tested using the actual data and the result shows that this algorithm can identify and carry out warning for vehicle collision efficiently, which has important meaning for improving the vehicle travel safety.

Robot stereo vision calibration method with genetic algorithm and particle swarm optimization

Accurate stereo vision calibration is a preliminary step towards high-precision visual posi- tioning of robot. Combining with the characteristics of genetic algorithm （GA） and particle swarm optimization （PSO）, a three-stage calibration method based on hybrid intelligent optimization is pro- posed for nonlinear camera models in this paper. The motivation is to improve the accuracy of the calibration process. In this approach, the stereo vision calibration is considered as an optimization problem that can be solved by the GA and PSO. The initial linear values can be obtained in the frost stage. Then in the second stage, two cameras＇ parameters are optimized separately. Finally, the in- tegrated optimized calibration of two models is obtained in the third stage. Direct linear transforma- tion （DLT）, GA and PSO are individually used in three stages. It is shown that the results of every stage can correctly find near-optimal solution and it can be used to initialize the next stage. Simula- tion analysis and actual experimental results indicate that this calibration method works more accu- rate and robust in noisy environment compared with traditional calibration methods. The proposed method can fulfill the requirements of robot sophisticated visual operation.

Learning-based force servoing control of a robot with vision in an unknown environment

A learning-based control approach is presented for force servoing of a robot with vision in an unknown environment. Firstly, mapping relationships between image features of the servoing object and the joint angles of the robot are derived and learned by a neural network. Secondly, a learning controller based on the neural network is designed for the robot to trace the object. Thirdly, a discrete time impedance control law is obtained for the force servoing of the robot, the on-line learning algorithms for three neural networks are developed to adjust the impedance parameters of the robot in the unknown environment. Lastly, wiping experiments are carried out by using a 6 DOF industrial robot with a CCD camera and a force/torque sensor in its end effector, and the experimental results confirm the effecti veness of the approach.

Determiningrelativeposition and attitude of a close non-cooperative target based on the SIFT algorithm

A binocular stereo vision positioning method based on the scale-invariant feature trans- form （SIFT） algorithm is proposed. The SIFT algorithm is for extracting distinctive invariant features from images. First, image median filtering is used to eliminate image noise. Then, according to the characteristics of the target satellite, image map is used to extract the middle part of the target satel- lite. At last, the feature match point under the SIFT algorithm is extracted, and the three-dimension- al position and orientation are calculated. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The experimental result shows that the al- gorithm works well and the maximum relative error is within 0. 02 m and 2.5 o

Automatic Identification of Tomato Maturation Using Multilayer Feed Forward Neural Network with Genetic Algorithms (GA)

We set up computer vision system for tomato images. By using this system, the RGB value of tomato image was converted into HIS value whose H was used to acquire the color character of the surface of tomato. To use multilayer feed forward neural network with GA can finish automatic identification of tomato maturation. The results of experiment showed that the accuracy was up to 94%.

Employment of predictive search algorithm in digital image correlation

A predictive search algorithm to estimate the size and direction of displacement vectors was presented.The algorithm decreased the time of calculating the displacement of each pixel.In addition,the updating reference image scheme was used to update the reference image and to decrease the computation time when the displacement was larger than a certain number.In this way,the search range and computational complexity were cut down,and less EMS memory was occupied.The capability of proposed search algorithm was then verified by the results of both computer simulation and experiments.The results showed that the algorithm could improve the efficiency of correlation method and satisfy the accuracy requirement for practical displacement measuring.

GNSS/SINS/视觉导航鲁棒算法

全球导航卫星系统(Global Navigation Satellite System, GNSS)、捷联惯性导航系统(Strapdown Inertial Navigation System, SINS)和视觉传感器优势互补,3者信息融合可获得高精度、无漂移的导航定位信息.针对GNSS/SINS/视觉融合导航易受运动速度、光照变化、遮挡等影响导致定位精度和鲁棒性降低问题,本文在图优化框架的代价函数中加入SoftLOne鲁棒核函数,设置量测值粗差检验程序,降低离群点带来的负面影响.进一步,对量测值计算残差进行卡方检验,对超限残差降权处理,提高系统精度和鲁棒性.实验结果表明,本文算法较不施加鲁棒核函数、不采用异常值剔除策略和卡方检验的传统算法,以及加入其他鲁棒核函数的算法精度更高、鲁棒性更好,能够较大程度提升GNSS/SINS/视觉导航定位精度和鲁棒性,在大尺度环境下,未出现较大漂移误差,绝对位姿均方根误差0.735 m,绝对位姿误差标准差0.336 m.

基于实际工程项目的装配参数视觉检测实践教学设计

根据“新工科”建设对实践教学的要求,结合精密制造行业视觉检测实际工程项目,对智能制造专业的机器视觉课程实践教学进行了教学案例设计。根据实际工程项目案例将教学实验划分为基础型、综合型、创新型三类,旨在增强学生的工程体验感,使学生能够循序渐进地掌握机器视觉的知识点和应用技能,促进本科实践教学课程建设,提高学生的创新能力和工程实践能力。

An improved self-calibration approach based on adaptive genetic algorithm for position-based visual servo

An improved self-calibrating algorithm for visual servo based on adaptive genetic algorithm is proposed in this paper. Our approach introduces an extension of Mendonca-Cipolla and G. Chesi＇s self-calibration for the positionbased visual servo technique which exploits the singular value property of the essential matrix. Specifically, a suitable dynamic online cost function is generated according to the property of the three singular values. The visual servo process is carried out simultaneous to the dynamic self-calibration, and then the cost function is minimized using the adaptive genetic algorithm instead of the gradient descent method in G. Chesi＇s approach. Moreover, this method overcomes the limitation that the initial parameters must be selected close to the true value, which is not constant in many cases. It is not necessary to know exactly the camera intrinsic parameters when using our approach, instead, coarse coding bounds of the five parameters are enough for the algorithm, which can be done once and for all off-line. Besides, this algorithm does not require knowledge of the 3D model of the object. Simulation experiments are carried out and the results demonstrate that the proposed approach provides a fast convergence speed and robustness against unpredictable perturbations of camera parameters, and it is an effective and efficient visual servo algorithm.

A machine vision approach to seam tracking in real-time in PAW of large-diameter stainless steel tube

Manual monitoring and seam tracking through watching weld pool images in real-time, by naked eyes or by industrial TV, are experience-depended, subjective, labor intensive, and sometimes biased. So it is necessary to realize the automation of computer-aided seam tracking. A PAW (plasma arc welding) seam tracking system was developed, which senses the molten pool and the seam in one frame by a vision sensor, and then detects the seam deviation to adjust the work piece motion adaptively to the seam position sensed by vision sensor. A novel molten pool area image-processing algorithm based on machine vision was proposed. The algorithm processes each image at the speed of 20 frames/second in real-time to extract three feature variables to get the seam deviation. It is proved experimentally that the algorithm is very fast and effective. Issues related to the algorithm are also discussed.

无人机影像GrabCut路面裂缝识别

无人机影像裂缝提取是近年来研究的热点问题之一。针对无人机影像强边缘信息干扰问题,本文提出了一种基于GrabCut算子的裂缝识别方法。该方法首先运用GrabCut算子提取保留裂缝的前景路面,然后运用去噪、边缘检测和双阈值轮廓识别方法探测路面裂缝。这种裂缝识别方法较好地排除了大量伪边缘信息和次生噪声干扰,实现了高分辨率无人机影像裂缝自动识别。试验结果表明,基于GrabCut算子的路面提取方法优于颜色特征提取算法和分水岭算法,适用于复杂场景路面提取,具有较高的普适性;同时,该方法可以快速获取裂缝信息,检测尺度可以人为控制,易于实现多尺度裂缝信息识别。研究结果可应用于路面裂缝定位识别、线性路面设施检测及路面灾害性评估等领域。

基于线结构光的厚板焊缝特征点提取算法

针对厚板结构件在使用激光视觉系统时图像特征区域提取难和工件表面加工不均匀漫反射等导致特征点提取困难的问题,提出基于线结构光的厚板焊缝特征点提取算法。首先,激光视觉系统获取焊缝图像并使用YOLOv4算法进行预训练,利用训练获取的权重文件自动检测并获取焊缝特征感兴趣区域(ROI);其次,对ROI进行降噪、二值化等处理,通过逐行(列)搜索法得到焊缝中心线;最后,根据不同焊缝类型,基于最小二乘法使用距离法和直线段聚类的方法来提取特征点。实验结果表明:该方法可有效提取不同类型的焊缝特征点,具有鲁棒性强、识别误差小等特点。

基于改进StackCNN网络和集成学习的脑电信号视觉分类算法

针对直接使用图像诱发的脑电信号进行视觉分类的现有研究少,并且视觉分类的平均准确率低等问题,设计了一种卷积神经网络(CNN)和集成学习相结合的方法,用于学习脑电信号相关的视觉特征表示。通过在StackCNN网络中加入K-max池化方法,解决在提取脑电特征时信息丢失的问题,并结合Bagging算法增强网络的泛化能力,该方法称为StackCNN-B。采用基于残差神经网络(ResNet)回归对图像进行分类,验证StackCNN-B方法在图像分类上的性能。消融实验及与现有研究对比实验的结果表明:所提方法识别准确率较高,在学习脑电信号的视觉特征表示上的平均准确率达到99.78%,在图像分类上的平均准确率达到96.45%,与Bi-LSTM-AttGW方法相比,平均提高了0.28百分点和2.97百分点。研究结果验证了脑电信号可以有效地解码与视觉识别相关的人类大脑活动,也表明所提出StackCNN-B模型的优越性。

基于双目深度筛选的ORB-SLAM3算法

针对ORB-SLAM3算法中特征点存在易丢失、精度低,进而导致双目在复杂场景下运动轨迹误差大的问题,本文设计了一种改进的ORB-SLAM3算法。首先,在ORB特征匹配算法中引入自适应角点检测技术,增加特征点的采集数量,并采用光流法跟踪图像特征,提高关键帧的创建成功率;其次,以特征点为中心,作区域搜索,提高实时性;然后,采用双向左右一致性检验筛选最优视差,应用Prosac算法去除误匹配点对;最后,结合深度信息对关键帧进行筛选,提高关键帧的质量,优化相机位姿。采用KITTI和EuRoc数据集进行了试验,验证了改进算法在绝对轨迹误差上具有良好的优化效果。

基于MIDE个体寻优的采摘机器人轨迹规划仿真

为了提高移动式采摘机器人的作业效率,实现高效率高精度的采摘作业,提出改进DE算法下移动式采摘机器人轨迹规划方法。建立移动式采摘机器人的动力学模型,获取采摘机器人的动力学特性;根据该特性,建立基于双目视觉的针孔成像模型完成采摘机器人果实采摘经过的路径点收集;将得到的路径点作为种群个体,对DE算法实施改进,选取一种基于多种群移民的差分进化算法(MIDE)展开个体寻优并输出最优解,实现移动式采摘机器人的最优轨迹规划。实验结果表明,所提方法具有较高的收敛能力和搜索效率,能够有效提高机器人的工作效率和稳定性。

基于双目视觉的6D位姿测量误差补偿方法

针对双目视觉设备测量误差较大且单点测量误差在视野范围内分布不一致,导致测量6D位姿精度和稳定性较差的问题,提出了一种测量误差补偿方法。为了解决传统回归模型在小样本多输入多输出情况下拟合效果较差的问题,采用基于多输出最小二乘支持向量回归(MLSSVR)的算法,实现了单点测量误差准确预测,并采用遗传算法对模型超参数进行全局寻优;为了实现跟踪坐标系的位姿测量误差补偿,结合位姿测量原理,将线性问题转化为最优估计问题,通过最小化坐标变换误差函数,将多个单点预测误差转化为多点耦合误差,从而实现了6D位姿测量误差补偿。实验结果表明,所提方法将跟踪坐标系的平均位置测量误差在3个方面上分别降低了63.4%、45.2%和75.0%,平均姿态测量误差分别降低50%、48.4%和53.1%;与其它现有补偿方法相比,所提方法能显著提高双目视觉设备的测量精度,并保证不同观测角度下的测量误差补偿有效性。

基于RepNet的自闭症健康监测方法研究

自闭症谱系障碍(ASD)患者在社交互动、语言交流和兴趣等方面表现出正常行为的偏差。随着自闭症患者数量的增加,迫切需要在早期进行自闭症筛查,以尽早提供专业治疗。目前自闭症筛查主要仰赖家长填写调查问卷和医疗专业人员进行人工观察和评估,这种方式效率较低且需要耗费较长的时间。机器算法在自闭症筛查领域的应用尚未得到广泛采纳。为提高筛查效率和准确性,探讨机器视觉算法RepNet在识别自闭症患者重复动作方面的有效性,使用RepNet算法分析包含重复性和非重复性动作的视频,评估Repnet的准确性;通过分析包含自闭症患儿重复动作的视频,评估RepNet在自闭症重复性动作筛查中的准确性和匹配性。结果表明:RepNet在检测自闭症患者的重复行为方面表现出极高的有效性和准确性。

双目结构光视觉引导的螺栓自动装配系统设计

为解决螺栓自动化装配过程中存在的零件位姿快速获取和在弱纹理、反光等复杂场景中实现精确定位等难题,基于双目结构光视觉原理,研制了一套螺栓自动装配系统。首先,通过双目结构光视觉系统获取工件场景的三维信息,涉及光栅条纹图案的获取、双目标定、多频外差法求解绝对相位、相位校正、极线校正、立体匹配,接着采用欧式聚类对重建的点云数据进行分割,获取单个螺栓的三维点云聚类,然后利用迭代最近点(ICP)算法估计模板点云到目标点云的位姿变换矩阵,识别连接螺栓在空间中的位姿,最后结合机械臂末端进行自动装配拧紧。实验结果表明,整个装配过程可自动完成,单个螺栓拧紧装配时间约为10 s,系统测试平均轴孔对中误差不超过1.20 mm,误差标准差不超过0.11 mm。

基于双目视觉的输送带表面损伤定量分析方法

为了对输送带表面损伤进行定量分析以有效判断其损伤程度,并根据损伤程度选择检修方法和时间,为工作人员检修提供依据,提出了一种基于双目立体视觉的输送带表面损伤定量分析方法。该方法首先对双目相机进行相机标定,对输送带表面损伤图像进行图像处理校正、立体匹配,基于视差原理根据三角测量原理获取目标点的三维空间信息,通过数学计算模型对损伤程度进行定量分析,提出了改进的Census变换和SGM(semi-global matching)算法相结合的立体匹配算法。结果表明:提出的改进算法匹配效果有所提升,和Census变换算法及梯度算法进行对比,误匹配率分别降低了5.26百分点和3.92百分点,得出的视差图精度最高;通过提出的方法对输送带表面损伤进行定量分析,在输送带损伤长度、宽度、深度三者误差中,损伤深度误差最大为8.5%,仍在可接受范围。