检索结果-南通市图书馆

Drone-YOLOv7: small target detection in UAV remote sensing images using YOLOv7-tiny with dynamic head

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： Yang Ye Yang Sen tong jigang Wang Zenghui Tianjin University of Technology Department of Electrical Engineering， University of South Africa

In the task of detecting targets in unmanned aerial vehicles （UAVs） aerial images， the challenge arises from small size and wide scale span of targets， making their location， extraction and feature distinction difficult. Similar categories are susceptible to confusion. To address these issues， an improved YOLOv7-tiny aerial detection algorithm is proposed. Firstly， to improve the identification of small targets， a small target detection layer is added while removing the maximum target detection layer to enhance the localization ability of small targets and make the model lightweight. Secondly， a CBAM （Convolutional Block Attention Module） attention mechanism is incorporated at the connection between the backbone and neck to focus on the target area and eliminate interference. Additionally， to further enhance the classification and location capabilities of the targets， the detection head is replaced with a dynamic head （DYHead） with a unified channel number to fuse scale， space and task awareness in a single module. Finally， to overcome the difficulty of extracting features， the neck is replaced with a CS-FPN （Cross-Scale Feature Pyramid Network） structure with cross-scale connections to amplify feature fusion. Comparative experiments on the VisDrone2021 dataset show that the proposed model can improve mAP50and mAP0.5:0.95by 8.3% and 6.1%， respectively， compared to the original YOLOv7-tiny model， and significant improvements are also observed on CARPK and SeaDronesSee datasets.

关键词：

Hyperbolic cosine transformer for LiDAR 3D object detection

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： tong jigang Yang Fanhang Yang Sen Du Shengzhi Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory， Tianjin University of Technology Department of Electrical Engineering， Tshwane University of Technology

Recently， Transformer has achieved great success in computer vision. However， it is constrained because the spatial and temporal complexity grows quadratically with the number of large points in 3D object detection applications from point clouds. Previous point-wise methods are suffering from time consumption and limited receptive fields to capture information among points. To address these limitations， we propose the cosh-attention， which reduces the computation complexity of space and time from the quadratic order to linear order with respect to the number of points. In the cosh-attention， the traditional softmax operator is replaced by non-negative ReLU activation and hyperbolic-cosine-based operator with re-weighting mechanism. Then based on the key component， cosh-attention， we present a two-stage hyperbolic cosine transformer (ChTR3D) for 3D object detection from point clouds. It refines proposals by applying cosh-attention in linear computation complexity to encode rich contextual relationships among points. Extensive experiments on the widely used KITTI dataset and Waymo Open Dataset demonstrate that， compared with vanilla attention， the cosh-attention significantly improves the inference speed with competitive performance. Experiment results show that， among two-stage state-of-the-art methods using point-level features to refine proposals， the proposed ChTR3D is the fastest one.

关键词：

Liquid refractive index measurement method based on orthogonal polarization laser self-mixing interference

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： ZHAO Yan WANG Haipeng DU Shengzhi tong jigang KANG Jun School of Electrical Engineering and Automation， Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Department of Electrical Engineering， Tshwane University of Technology

In this paper， a novel method combining orthogonal polarization laser self-mixing interference is proposed. The method utilizes a rotating cuvette to measure the refractive index of liquids at different concentrations. The cuvette is filled with the liquid to be measured and rotated by a certain angle. The change in the number of interference fringes， caused by comparing an empty cuvette with a liquid-filled cuvette， is used to calculate the refractive index of the liquid. A four-fold logic subdivision algorithm is then used to improve measurement resolution. The experimental results show that for pure water and different NaCl and glucose solutions concentrations， the average relative errors are 0.47%， 0.59%， and 2.17%， respectively， with the maximum relative error within ±2.54%. The standard deviation of all solutions is less than 3.4%.

关键词：

Weak feedback self-mixing interference fringe slope discrimination method based on deep learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： ZHAO Yan LIN Maohua DU Shengzhi tong jigang LIU Bin HAN Fangfang School of Electrical Engineering and Automation， Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Department of Electrical Engineering， Tshwane University of Technology

In order to identify the tilt direction of the self-mixing interference (SMI) signals under weak feedback regime interfered by noise， a deep learning method is proposed. The one-dimensional U-Net (1D U-Net) neural network can discriminate the direction of self-mixing fringes accurately and quickly. For experimental SMI signals， the 1D U-Net can be used for discriminant direction after a one-step normalization. Simulation and experimental results show that the proposed method is suitable for SMI signals with noise within the whole weak feedback regime， and can maintain a high discrimination accuracy for signals interfered by 5dB noise. Combined with fringe counting method， accurate and rapid SMI signal displacement reconstruction can be realized.

关键词：

Multi-scale detector optimized for small target

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2024年第4期20卷 243-248页

作者： ZHU Yongchang YANG Sen tong jigang WANG Zenghui School of Electrical Engineering and Automation Tianjin University of TechnologyTianjin 300384China Center of Artificial Intelligence and Data Science University of South AfricaFlorida 1709South Africa Department of Electrical Engineering University of South AfricaFlorida 1709South Africa

The effectiveness of deep learning networks in detecting small objects is limited,thereby posing challenges in addressing practical object detection *** this research,we propose a small object detection model that operates at multiple *** model incorporates a multi-level bidirectional pyramid structure,which integrates deep and shallow networks to simultaneously preserve intricate local details and augment global ***,a dedicated multi-scale detection head is integrated into the model,specifically designed to capture crucial information pertaining to small *** comprehensive experimentation,we have achieved promising results,wherein our proposed model exhibits a mean average precision(mAP)that surpasses that of the well-established you only look once version 7(YOLOv7)model by 1.1%.These findings validate the improved performance of our model in both conventional and small object detection scenarios.

关键词： networks details thereby

维普期刊数据库

Research on Trajectory of Quadrotor Elastic Suspension Load System Based on Differential Flatness and RRT* Algorithm

在线全文

学校读者我要写书评

暂无评论

Research on Trajectory of Quadrotor Elastic Suspension Load ...

Research on Control of Quadcopter Suspension System Based on Differential Flatness Theory and Back-stepping Sliding Mode Control

第43届中国控制会议

作者： Zhikun Wang Sen Yang jigang tong Shengzhi Du Tian Xie The School of Electrical Engineering and Automation Tianjin University of Technology Department of Electrical Engineering Tshwane University of Technology

The paper introduces a method for trajectory planning of quadrotors with elastic suspension load systems in complex environments. The method combines differential flatness and RRT* algorithm to address challenges such as large load swing due to obstacle avoidance, elastic rope suspension load, and significant trajectory corner changes. Firstly, a dynamic model of the elastic suspension load system is established and shown to possess differential flatness. The load's position variable is chosen as the flat output, enabling the representation of all other system state variables using the flat output and its derivatives, thereby reducing solution complexity. Secondly, the RRT* obstacle avoidance algorithm incorporates a target bias mechanism to guide sampling points towards the target point, improving convergence speed. During random tree node expansion, considerations include the elastic rope constraint and load swing angle constraint between the quadrotor and the load to prevent collisions with obstacles. Finally, a sixth-degree B-spline curve is utilized for the purpose of smoothing and optimizing the trajectory. This method has been compared with the A algorithm, and simulation results show that the proposed method has better anti swing effect.

关键词： Quadrotor Suspended load Trajectory planning RRT~* algorithm Obstacle avoidance

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 Control of Quadcopter Suspension System Based on...

第43届中国控制会议

作者： Peiyang Duan jigang tong Tian Xie Shengzhi Du Sen Yang The School of Electrical Engineering and Automation Tianjin University of Technology Department of Electrical Engineering Tshwane University of Technology

Quadcopter UAV elastic suspension system has a good development prospect due to its flexible and easy-to-operate features. However,during the flight transportation process,the oscillation of load,the irregular extension of elastic ropes,and the oscillation of UAV may lead to safety problems such as UAV crashes. In order to solve the above problems,this paper introduces a quadcopter transportation system with a suspended load with highly elastic ropes and establishes a dynamic model of the system. In this paper,the model is first transformed by differential flatness theory to establish the corresponding control variable order,and then the virtual control variables are introduced to control the swing angle and rope length by using back-stepping and sliding mode control methods,so as to achieve the purpose of swing reduction while controlling the position of the UAV. The stability of system is demonstrated using the Lyapunov method. Numerical simulation results show that the proposed control method can enable the system to reach the specified position rapidly,the swing of load can converge quickly,and the rope length can be stabilized swiftly,which avoids the occurrence of flight accidents.

关键词： Quadcopter suspension system Elastic rope Differential flatness theory Swing reduction control

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

基于主动视觉的人脸检测与跟踪算法研究

系统仿真学报 2015年第5期27卷 973-979页

作者：董恩增闫胜旭佟吉钢天津理工大学自动化学院复杂系统控制理论及应用重点实验室天津300384

基于融合Kalman滤波的Camshift算法与Adaboost算法相结合的方法,提出了一种基于主动视觉的人脸检测与跟踪算法。利用Adaboost算法与融合的Camshift算法实现人脸自主检测与跟踪;根据目标形心与视场中心的位置关系以及人脸区域与视场的面... 详细信息

基于融合Kalman滤波的Camshift算法与Adaboost算法相结合的方法,提出了一种基于主动视觉的人脸检测与跟踪算法。利用Adaboost算法与融合的Camshift算法实现人脸自主检测与跟踪;根据目标形心与视场中心的位置关系以及人脸区域与视场的面积关系,设计了云台控制算法。该控制算法通过对云台摄像机进行水平、垂直和变焦控制,达到自动调整云台摄像机参数的目的。基于硬件平台对所提出的主动视觉算法进行实验验证,实验结果显示,主动视觉算法具有较高的运行效率,能够实时的检测和跟踪人脸目标,扩大了摄像机的跟踪范围。

关键词： Camshift Adaboost 人脸检测主动视觉云台控制

维普期刊数据库

在线全文

学校读者我要写书评

暂无评论

网络视频流混沌加密系统的FPGA设计实现

哈尔滨工程大学学报 2011年第6期32卷 760-766页

作者：佟吉钢张振新陈增强孙青林南开大学信息技术科学学院天津300071

目前计算机平台下图像及视频的混沌加密应用的实现中,若使用常规的安全加密算法计量太大,而选择性加密算法的实现需要熟知视频流的格式,针对这些算法的局限和不足,从嵌入式系统应用的角度考虑提出了基于FPGA的实时视频加密.在FPGA开发... 详细信息

目前计算机平台下图像及视频的混沌加密应用的实现中,若使用常规的安全加密算法计量太大,而选择性加密算法的实现需要熟知视频流的格式,针对这些算法的局限和不足,从嵌入式系统应用的角度考虑提出了基于FPGA的实时视频加密.在FPGA开发板上植入基于32位M icrob laze处理器的μCL inux操作系统,同时结合各种必要的IP核,利用其有限的硬件资源对网络实时视频数据进行完全加密并实现了基于混沌和超混沌在内的多种双重加密算法,并可随机进行选择.采用双网卡模式,将其设计成一款方便实用的即插即用型网络视频加密平台.实验证明,该系统在局域网的环境中运行稳定可靠,加密效果理想,使用方便.

关键词：混沌加密 FPGA 视频流网络 μCLinux

维普期刊数据库