检索结果-内蒙古大学图书馆

Proceedings of the 2021 4th International Conference on Artificial Intelligence and Pattern Recognition

作者： Feng Min Peng Liu Wuhan Institute of Technology China

ISBN: (纸本)9781450384087

With the rapid development of deep learning, target detection technology has been widely used in various fields. At this stage, ship detection method in the SAR image based on the ssd algorithm, the accuracy was more improved than traditional methods, but the ssd algorithm takes a long time, and it was difficult to detect and locate the ship target in real time in the missile-borne SAR image. In addition, the ssd model has a large amount of calculation, and has a deviation in the detection of small targets. A ship detection method in the SAR image is proposed in this paper. The method improves the shallow network structure of the ssd algorithm, increases the network of different modules for feature fusion, reduces the loss of information in the training process, improves the feature extraction ability of small ships in the SAR image, and increases the receptive field of shallow features. Experiments was carried on ssdD and SAR-Ship-Dataset datasets. Compared with ssd algorithm, It was increased about 6% and 7% of mAP, which reduced the calculation amount of convolution, and the model size was reduced by about 7M and 10M.

关键词： SAR image ssd algorithm Ship detection feature fusion

来源：评论

学校读者我要写书评

暂无评论

Intelligent Antenna Attitude Parameters Measurement Based on Deep Learning ssd Model

引用

ZTE Communications 2022年第S01期20卷 36-43页

作者： FAN Guotian WANG Zhibin ZTE Corporation Shenzhen 518057China Xidian University Xi’an 710071China

Due to the consideration of safety,non-contact measurement methods are be-coming more ***,massive measurement will bring high labor-cost and low working *** address these limitations,this paper introduces a deep learning model for the antenna attitude parameter measurement,which can be divided into an an-tenna location phase and a calculation phase of the attitude *** the first phase,a single shot multibox detector(ssd)is applied to automatically recognize and discover the antenna from pictures taken by *** the second phase,the located antennas’fea-ture lines are extracted and their attitude parameters are then calculated *** show that the proposed algorithms outperform existing related works in effi-ciency and accuracy,and therefore can be effectively used in engineering applications.

关键词： deep learning drone object detection ssd algorithm visual measurement antenna attitude parameters

来源：评论

学校读者我要写书评

暂无评论

Improving resource recycling based on deep learning

引用

JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS 2024年第4期16卷 527-540页

作者： Xu, Yunjian Guo, Aiyin Guangdong AIB Polytech Sch Intelligent Engn Guangzhou Peoples R China Guangdong AIB Polytech Sch Internet Things Applicat Technol Guangzhou Peoples R China

The manual sorting of recyclable garbage has caused several issues such as the wastage of human resources and low resource utilization. To solve this problem, an improved Single Shot Multibox Detector (ssd) deep learning approach has been developed for recyclable garbage detection. To reduce the number of parameters and make the model easier to deploy and apply, a lightweight network called RepVGG has been chosen to replace the VGG16 network in the ssd. Additionally, the auxiliary convolutional layer structure of the ssd has been modified to further reduce the number of parameters. Additionally, the SK module has been integrated to adaptively adjust the size of the receptive field and enhance the detection accuracy. Experimental results of Waste Classification data set from Kaggle website have demonstrated that the improved ssd model has better detection accuracy and real-time performance, with an accuracy of 95.23%, which is 4.33 percentage points higher than the original ssd, and a detection speed of up to 64 FPS. This algorithm can be better applied in industry.

关键词： Recyclable garbage detection ssd algorithm structure re-parameterization deep learning

来源：评论

学校读者我要写书评

暂无评论

A Traffic Sign Recognition Method Under Complex Illumination Conditions

引用

IEEE ACCESS 2023年 11卷 39185-39196页

作者： Yan, Yi Deng, Chao Ma, Junjie Wang, Youfu Li, Yanqi Wuhan Univ Sci & Technol Sch Automobile & Traff Engn Wuhan 430065 Hubei Peoples R China Wuhan Univ Sci & Technol Intelligent Automobile Engn Res Inst Wuhan 430065 Hubei Peoples R China Unmanned Syst Intelligent Percept Control Technol Chengdu 610225 Sichuan Peoples R China Lab Cloud IoT Intelligent Equipment Expressway Con Jinan 250357 Shandong Peoples R China

Environment awareness technology is one of the most critical technologies for autonomous vehicles, and traffic sign recognition is an important branch of environment awareness system, which has important research significance for ensuring traffic safety. To solve the problems of easy omission and inaccurate positioning for traffic sign detection under complex illumination conditions, there are two main innovations in this paper: firstly, an adaptive image enhancement algorithm was proposed to improve the image quality under complex illumination conditions;Secondly, a novel and lightweight attention block named Feature difference (FD) model was proposed to detect and recognize traffic signs. Unlike state-of-the-art attention models, which utilizes the difference between two feature maps to generate the attention mask. In this work, the single-stage target detection algorithm ssd was selected as the basic network, the backbone network was set as ResNet and VGG respectively and FD module was added. A large number of experiments were carried out to evaluate the optimization effect of FD module. The following conclusions can be drawn: image enhancement algorithms can provide better image samples;The FD model can be integrated into most of CNNs just by adding some shortcut connections, which does not introduce any additional parameters and layers;The average detection accuracy with FD module is 1.80% higher and the average recall rate was 1.51% higher than that without FD module, which has no great influence on the running speed. The FD module has better enhancement effect for dark image detection;The detection accuracy of the FD module is slightly better than other attention modules including BAM, CBAM and SE;The FD model can be used to evaluate the effect of the convolutional operation on features, which could help to find convolutional layers that have little effect on the accuracy of recognition for the network pruning.

关键词： Object detection Feature extraction Convolution Autonomous vehicles Lighting Transportation Target recognition Autonomous driving complex illumination conditions traffic signs detection feature difference model ssd algorithm

来源：评论

学校读者我要写书评

暂无评论

Bus passenger flow statistics algorithm based on deep learning

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2020年第39-40期79卷 28785-28806页

作者： Zhang, Yong Tu, Wentao Chen, Kairui Wu, C. H. Li, Li Ip, W. H. Chan, C. Y. Shenzhen Univ ATR Key Lab Natl Def Technol Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Lab Artificial Intelligence & Digital E Shenzhen 518060 Peoples R China Georgia Gwinnett Coll Sch Sci & Technol Lawrenceville GA 30043 USA Hang Seng Univ Hong Kong Dept Supply Chain & Informat Management Hong Kong 999077 Peoples R China Shenzhen Inst Informat Technol Shenzhen 518172 Peoples R China Univ Saskatchewan Coll Engn Saskatoon SK Canada Hong Kong Polytech Univ Dept Ind & Syst Engn Hong Kong 999077 Peoples R China

Bus passenger flow statistics can be used to improve passenger travelling experience and reduce trip delay, this is very important for intelligent transportation. In this paper, a bus passenger flow statistics algorithm based on ssd (Single Shot MultiBox Detector) and Kalman filter is proposed to obtain passenger flow statistics from surveillance cameras on the buses. The method modifies the ssd model to a two-class model and trains the two-class ssd model using the bus dataset first, then the model is used to detect the position of the passengers in each frame and are tracked with the Kalman filter. Finally, according to the passenger trajectory, the traffic statistics of passenger getting on and off will be generated. The results of some conducted experiments show that the proposed bus passenger flow statistics algorithm is more accurate and robust than traditional methods.

关键词： Computer vision Deep learning Bus passenger flow statistics ssd algorithm

来源：评论

学校读者我要写书评

暂无评论

Tacho-less automatic rotational speed estimation (TARSE) for a mechanical system with gear pair under non-stationary conditions

引用

MEASUREMENT 2019年 145卷 480-494页

作者： Ruiz Barrios, Mario Luis Hernandez Montero, Fidel Ernesto Gomez Mancilla, Julio Cesar Palomino Marin, Evelio Univ Pinar del Rio Dept Telecommun & Elect Pinar Del Rio Cuba Technol Univ Havana Jose Antonio Echeverria Dept Telecommun & Telemat Havana Cuba Inst Politecn Nacl Lab Vibrac & Rotodinam ESIME Mexico City DF Mexico Tech Univ Havana Jose Antonio Echeverria Innovat & Maintenance Ctr Havana Cuba

The condition monitoring of mechanical systems by vibration analysis becomes a problem whenever the rotational speed varies and is unknown. This work proposes an algorithm to automatically estimate the rotational speed from the vibration generated by a gear pair. The algorithm is based on the decomposition of the vibration signal into mono-component signals and the detection of amplitude modulations. Singular Spectrum Decomposition was used for decomposing the vibration signal into the mono-component signals, and a non-quadratic phase coupling analysis was applied in order to detect the amplitude modulations. The algorithm is validated by working with simulated and true signals resulting from the application of different speed profiles. Finally, two practical cases are presented: (1) the implementation of order tracking through the rotational angle estimated by the new algorithm;and (2) the identification of the first harmonic of gear-mesh frequency from a time-frequency representation of the vibration signal. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Amplitude modulation detection Gear vibration Lock-in amplifier ssd algorithm TARSE

来源：评论

学校读者我要写书评

暂无评论

Target detection of hyperspectral image based on spectral saliency

引用

IET IMAGE PROCESSING 2019年第2期13卷 316-322页

作者： Zhang, Xiaorong Pan, Zhibin Hu, Bingliang Zheng, Xi Liu, Weihua Xi An Jiao Tong Univ Sch Elect & Informat Engn Xian 710049 Shaanxi Peoples R China Univ Chinese Acad Sci Beijing 100039 Peoples R China Chinese Acad Sci Xian Inst Opt & Precis Mech Xian 710119 Shaanxi Peoples R China Chinese Acad Sci Inst Earth Environm Xian 710061 Shaanxi Peoples R China

Target detection of hyperspectral image (HSI) is a research hotspot in the field of remote sensing. It is of particular importance in many domains, especially in military application. Unsupervised target detection is usually more difficult because there is no prior information about target. Traditional algorithms exploit spectral information, only. This study introduces the idea of saliency detection from the visual technique into HSI processing domain and proposes a novel approach named spectral saliency target detection (ssd). It establishes a novel salient model, which utilises both spatial saliency and spectral saliency. In the framework of ssd, it combines the model with spectral matching algorithm to make it perform well even in situations where the target is concealed and small. A HSI set comprised of eight different scenes with complex background is setup to evaluate the performance of the proposed algorithm. The final visible detection results demonstrate that the ssd algorithm outperforms the others. The receiver operation characteristic (ROC) curve and area under the ROC curve are applied to evaluate the results. The proposed algorithm shows superior and stable performance.

关键词： hyperspectral imaging object detection remote sensing geophysical image processing hyperspectral image remote sensing unsupervised target detection spectral saliency target detection HSI set spectral matching algorithm ssd algorithm

来源：评论

学校读者我要写书评

暂无评论

RETRACTED: Kssd: single-stage multi-object detection algorithm with higher accuracy (Retracted article. See vol. 17, pg. 301, 2023)

引用

IET IMAGE PROCESSING 2020年第15期14卷 3651-3661页

作者： Hou, Qingshan Xing, Jinsheng Shanxi Normal Univ Sch Math & Comp Sci Linfen Shanxi Peoples R China

Considering that the single shot multibox detector (ssd) algorithm will be missed or even false when is used to detect the small- and medium-sized objects, in this study, Kullback-Leibler single shot multibox detection (Kssd) object detection algorithm is proposed to improve the accuracy of small- and medium-sized objects detection. Firstly, the details in the detection process are visualised with gradient-weighted class activation mapping technology, and the details of each detection layer are shown in the form of class activation maps. Then it is noted that the phenomenon of the false or missed detection of the objects to be detected on small- and medium-sized objects in the ssd algorithm is related to the regression loss function. Accordingly, Kullback-Leibler border regression loss strategy is adopted and non-maximum suppression algorithm is used to output the final prediction boxes. Experimental results show that compared with the existed detection algorithms, the improved algorithm in this study has higher accuracy and stability, and can significantly improve the detection effect on small- and medium-sized objects.

关键词： object detection Kssd multiobject detection algorithm single shot multibox detector algorithm Kullback-Leibler single shot multibox detection medium-sized objects detection detection process gradient-weighted class activation mapping technology detection layer class activation maps false missed detection ssd algorithm regression loss function Kullback-Leibler border regression loss strategy nonmaximum suppression algorithm detection effect medium-sized objects small-sized objects

来源：评论

学校读者我要写书评

暂无评论

Visual Communication Design of Weak and Small Target Images Based on Image Processing Model and Data Fusion

引用

TEHNICKI VJESNIK-TECHNICAL GAZETTE 2024年第3期31卷 815-823页

作者： Zhang, Xu Wuhan Univ Commun Wuhan 430205 Hubei Peoples R China

The essence of computer vision technology is to combine computers with image data to enhance their understanding and perception abilities. One of the major research hotspots in computer vision technology is the object recognition, and in the field of object recognition, a major challenge is the recognition of weak and small target images. In response to the current difficulty in detecting weak and small target images, a visual communication design with image processing models and data fusion was proposed. The Single Shot MultiBox Detector was improved to construct a weak and small target detection model, and the feature fusion method was combined to enhance its weak and small target detection ability. The ablation experiment showed that in contrast with the original model, the improved model improved the detection ability of weak and small targets by 26.54%, and the overall accuracy improved by 11.05%. Two other advanced algorithms were selected for comparison with the research algorithm, and the accuracy of the research algorithm was better, with a higher accuracy of 47.67% -79.56% than the comparison algorithm. The response time was shorter, reaching 0.62 seconds. Visual communication time and success rate performed better, with a communication time lead of 9 s to 19 s and a success rate lead of 16% to 27%. In summary, the algorithm proposed by the research institute has higher accuracy in detecting small and weak images, as well as higher visual communication efficiency and success rate, which has stronger practical significance in the field of computer vision.

关键词： attention mechanism detection of weak and small targets feature fusion ssd algorithm

来源：评论

学校读者我要写书评

暂无评论

Traffic sign detection algorithm based on feature expression enhancement

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第25期80卷 33593-33614页

作者： Sun, Chao Wen, Mi Zhang, Kai Meng, Ping Cui, Rongcheng Shanghai Univ Elect Power Coll Comp Technol & Sci Shanghai 200090 Peoples R China

Traffic sign detection is an important research direction in computer vision, which is of great significance for autonomous driving and advanced assisted driving systems. Due to the complexity of traffic signs in natural scenes, existing traffic sign detection algorithms have disadvantages such as high false detection rates and poor robustness. To improve the accuracy of traffic sign detection, a feature expression enhanced ssd(Essd) detection algorithm is proposed. Essd extracts semantic information in a lightweight way, adds detailed information for fusion, and forms a new feature map through multiple convolution operations to enhance feature expression. Meanwhile, a new target default box was designed to increase the focus on traffic signs. The ssd and Essd were retrained on TT100K and CCTSDB datasets. Experimental results show that the mAP of the improved Essd is 81.26% and 90.52% and can improve AP up to 40%. The robustness of the Essd model was verified using the PASCAL VOC data set, which showed better detection of small objects.

关键词： Target detection Traffic sign detection Small object detection ssd algorithm

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：