检索结果-南通市图书馆

第37届中国控制会议

作者： Hua Wang DingSheng Zhang Zhonghua Miao Shanghai Key Laboratory of Power Station Automation Technology School of Mechatronics Engineering and AutomationShanghai University

Face Recognition plays a very important role in numerous occasions based on visual security in recent days. The current methods of face recognition are to extract the different features of different faces to distinguish from others, so feature extraction has become a vital step in face recognition. For this reason, this paper presents a new fusion of local difference binary（LDB） and histogram of oriented gradients（HOG） for face recognition. We use LDB descriptor to extract the local pattern features of a face image. At the same time, the edge features of the original image are extracted by using HOG descriptor. The proposed new fusion of features improves the shortcomings of the low accuracy and avoids the problems that the dimension of the general fusion of features is too high. The experimental results on ORL and Yale face database verify the validity of the proposed fusion of features.

关键词： Face recognition Local difference binary Histogram of oriented gradients Fusion of features

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Deep learning based curb detection with Lidar

引用

High Technology Letters 2022年第3期28卷 272-279页

作者：王小华 LIAO Zhonghe MA Pin miao zhonghua School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200444P.R.China

Curb detection provides road boundary information and is important to road detection.However,curb detection is challenging due to the problems such as various curb shapes,colour,discontinuity.In this work,a novel learning-based method for curb detection is proposed using Lidar point clouds,considering that Lidars are not sensitive to illumination and are relatively stable to weather conditions.A deep neural network,named EdgeNet,is constructed and trained,which handles point clouds in an end-to-end way.After EdgeNet is properly trained,curb points are then segmented in the neural network output.In order to train,a curb point annotation algorithm is also designed to generate training dataset.The curb detection method works well with different road scenarios including intersections.The experimental results validate the effectiveness and robustness of this curb detection method.

关键词： curb detection EdgeNet curb annotation algorithm

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Experimental verification of formation control in nonholonomic multi-mobile robots

Experimental verification of formation control in nonholonom...

引用

第40届中国控制会议

作者： Dongdong Wang Jin Zhou Chuangxin He Zhonghua Miao School of Mechatronic Engineering and Automation Shanghai University Shanghai Institute of Applied Mathematics and Mechanics and Shanghai Key Laboratory of Mechanics in Energy Engineering Shanghai University

Mobile robots is one of the well-known nonholonomic system. A new kinematic consistency controller is proposed for a nonholonomic mobile robot model with an integrated approach of kinematic and torque controllers to accomplish tracking control of the target trajectory. In this paper, the reliability of the controller is demonstrated using simulation software and a two-drive wheel mobile robot experimental platform to validate the controller.

关键词： nonholonomic mobile robots tracking controller experimental validation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Distributed Consensus Control of Nonlinear Multiagent Systems Satisfying Incremental Quadratic Constraints

Distributed Consensus Control of Nonlinear Multiagent System...

引用

第40届中国控制会议

作者： Yuchen Qian Zhonghua Miao Xiaojin Zhu Chuangxin He the School of Macaronic Engineering and Automation Shanghai University

In this paper, we investigate the problem of leaderless consensus control for the multiagent systems with nonlinear dynamics satisfying incremental quadratic constraints. A distributed dynamic consensus protocol, decided by communication among neighboring agents, has been presented to render nonlinear agents consensus by choosing appropriate coupling weights without knowing full state information. Further, extensions to consensus strategies with nonlinear dynamics for the leaderfollowing fashion are also addressed. In contrast to the conventional nonlinear consensus control methodologies, the proposed approach generalizes the Lipschitz condition and the combined condition of one-sided Lipschitz and quadratic inner-boundness conditions to a new generalized type of nonlinearity, which shows us a less conservative result in the Lyapunov proof. Finally,the simulation results for six agents are presented to show the feasibility and effectiveness of the proposed control protocol.

关键词： Distributed consensus control incremental multiplier matrix（δMM） incremental quadratic constraints（δQC） nonlinear multiagent systems

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Intelligent vehicle pedestrian tracking based on YOLOv3 and DASiamRPN

Intelligent vehicle pedestrian tracking based on YOLOv3 and ...

引用

第40届中国控制会议

作者： Chuangxin He Xu Zhang Zhonghua Miao Teng Sun School of Mechanical and Electrical Engineering and Automation Shanghai University

In the field of robot and autopilot,aiming at the difficulty that the traditional single target pedestrian tracking algorithm needs manual frame selection,this paper puts forward a pedestrian tracking algorithm which blends YOLOv3 and DASiam RPN to realize the designated pedestrian tracking.The algorithm automatically selects the tracking target through YOLOv3,and then uses the tracking target as the template to input into DASiamRPN for tracking.The real-time pedestrian tracking experiment based on the Kinect camera was carried out,and the tracking effects of SiamRPN,Deepsort,SiamFC and Mosse+KCF algorithms were compared.The experimental results show that the optimal running speed of DASiamRPN is 34 fps while ensuring the tracking accuracy.Finally,the algorithm has been applied to Bulldog robot based on ROS,and the pedestrian tracking is realized successfully,which verifies the real-time and robustness of the algorithm.

关键词： Pedestrian tracking YOLO DASiamRPN ROS

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Research on Auto-follow Row Assist Technology of Cotton Picker with Adaptive Speed

Research on Auto-follow Row Assist Technology of Cotton Pick...

引用

第40届中国控制会议

作者： Chuangxin He Chao Wu Nan Li Zhonghua Miao School of Mechanical and Electrical Engineering and Automation Shanghai University

In order to improve the alignment quality of the cotton picker and reduce the labor intensity of the driver,an auto-follow row assist technology of the cotton picker based on speed adaptive is designed.Take the 4 MY-6 cotton picker produced by MODERN AGRICULTURAL EQUIPMENT Co.,Ltd.as the research platform,The course deviation is used as the input of the controller,The controller adjusts the PID parameters online according to the speed of the cotton picker,and then adjusts the Angle of the rear wheel,so that the head of the cotton picker can automatically align with the cotton row.The field experiment results show that the method proposed in this paper can adapt to the change of the cotton picker’s walking speed well,and has a good effect on the auto-follow row,which provides a technical reference for automatic navigation of cotton harvesting operation.

关键词： Cotton picker auto-follow row adaptive control Course tracking

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Pose measurement of small-size aircraft based on machine vision

Pose measurement of small-size aircraft based on machine vis...

引用

第40届中国控制会议

作者： Yunhui Li Ou Fang Zhonghua Miao Ju Huo School of Mechatronic Engineering and Automation Shanghai University School of Electrical Engineering and Automation Harbin Institute of Technology

In small-size aircraft ground tests,pose measurement is significant for the validation of aircraft control and guidance algorithm development and performance evaluation.In order to achieve a precise value of the pose in the aircraft ground test,Firstly,an aircraft ground test localization system based on machine vision has been established and proposed a global localization method for the smaller sizes of aircraft ground test.Multi-view matching of feature points is realized by using the spatiotemporal consistency method.The method of uncertainty analysis is used to realize the high precision 3D reconstruction of feature points from multiple views.The pose parameters of the aircraft are solved by using the pose estimation algorithm of non-collinear vectors.The feasibility and accuracy of the pose measurement algorithm are verified by simulation and actual experiment.The experimental results show that:under the condition of the measurement range is 6000 mm×6000 mm×3000 mm,the size of the aircraft is about 400 mm,and the 3D positioning accuracy of the feature points is 2.9 mm,the theoretical accuracy of the pose measurement algorithm based on vector crossover can reach 0.5°（3σ） and 3 mm（3σ） respectively.The actual relative measurement accuracy up to 1.3 °（3σ） and 4 mm（3σ）.It meets the requirements of stable and reliable performance evaluation,high precision,and strong anti-jamming ability of small-size aircraft guidance and control system.

关键词： Machine vision Ground test of aircraft Pose estimation Vector cross

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Lidar Odometry Key Frame Selection Based on Displacement Vector Similarity

Lidar Odometry Key Frame Selection Based on Displacement Vec...

引用

第40届中国控制会议

作者： Fang Ou Yunhui Li Zhonghua Miao Jin Zhou School of Mechatronic Engineering and Automation Shanghai University

In order to improve the efficiency and reduce the cumulative error of lidar odometry caused by key frame update. This paper proposes a key frame selection method based on displacement vector similarity. First, calculate the pose between the current frame and the reference key frame according to the Normal Distribution Transform（NDT） algorithm;then, set the Manhattan distance between the two frames above, and calculate the cosine similarity of the displacement vector;finally, update the key frame according to the similarity threshold. The experimental results show that the key frame selection method proposed in this paper can effectively improve the key frame update efficiency and reduce the cumulative error of the odometry: compared with the NDT method updating key frame based on the distance, the maximum absolute error is reduced by 11.88 meters, and the relative error is reduced by 8%,time consumption has been reduced by 55 seconds.

关键词： Lidar Odometry Cosine Similarity Normal Distributions Transform（NDT）

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Design of Vision Control System of Tomato Picking Robot

Design of Vision Control System of Tomato Picking Robot

引用

第40届中国控制会议

作者： Chuangxin He Chunyu Deng Nan Li Zhonghua Miao School of Mechatronic Engineering and Automation Shanghai University

Tomato picking is a relatively complex production link in the overall process of tomato production.It is the labor-intensive work and it is urgent to use automated picking of tomato fruits.Therefore,this article mainly uses the depth camera and the six-degree-of-freedom manipulator to study the construction of the visual servo system,the modeling and kinematics simulation of the manipulator in the automatic tomato picking robot.We have established a robot visual servo system that can be directly grasped based on the robot operating system（ROS）.The system acquires fruit targets through visual sensors,uses the depth and color information of the targets,and uses coordinated control strategies for hands and eyes at different distances.The tomato picking space is divided into multiple picking sub-regions,and the picking path planning is combined with the obstacle avoidance algorithm to improve the overall efficiency of tomato picking.

关键词： Picking robot ROS vision servo system hand and eye coordination strategy

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Adaptive Dynamic Programming for Nonlinear Impulse Systems

Adaptive Dynamic Programming for Nonlinear Impulse Systems

引用

第36届中国控制会议

作者： Xiaohua Wang Yanru Lian Zhonghua Miao School of Mechatronics Engineering and Automation Shanghai University Shanghai Key Laboratory of Power Station Automation Technology of Shanghai University

ISBN: (纸本)9781538629185

Impulse systems describe impulsive phenomena and consider instantaneous impact on the states of the system. Optimal control of nonlinear impulse system hardly obtains analytical solutions considering the impulse nature. A new numerical algorithm based Adaptive dynamic programming（ADP） herein provides numerical approximation to the optimal control solutions. The difficulty designing ADP algorithm in such system lies in the policy update part. Variational method is adopted for policy update between two consecutive impulses. Simulations are presented for algorithm validations.

关键词： Nonlinear Fixed-time Impulse Systems Optimal Control Adaptive Dynamic Programming（ADP） Variational Method

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：