检索结果-内蒙古大学图书馆

Recognizing human behaviors from surveillance videos using the ssd algorithm

JOURNAL OF SUPERCOMPUTING 2021年第7期77卷 6852-6870页

作者： Pan, Husheng Li, Yuzhen Zhao, Dezhu Tsinghua Univ Acad Arts & Design Beijing Peoples R China Kyung Hee Univ Grad Sch Technol Management Yongin 17104 South Korea Shenzhen Metro Grp Co Ltd Ticketing Ctr Shenzhen 518026 Peoples R China

The aim is to better recognize human behaviors from surveillance videos. Human behavior recognition technology based on surveillance videos is researched, given the intellectual development of massive surveillance video data with full coverage. This technology builds a human behavior detection and recognition model using the new Single Shot MultiBox Detector (ssd) algorithm, which improves the recognition accuracy. The constructed model's effectiveness is verified through comparisons with other traditional human behavior recognition algorithms via the TensorFlow framework. Results demonstrate the ssd model-based recognition algorithm's accuracy is significantly higher than that of Direct Part Marking and Fast Convolutional Neural Network (CNN) algorithms. ssd's average speed is 0.146 s/frame, and the average accuracy on different datasets is 82.8%. If the target is close or partially occluded, the ssd algorithm can also accurately detect the central target, and the detection efficiency is twice that of the R-CNN algorithm. The algorithm proposed has a simple structure and fast processing speed, which can solve the problems in target detection. The research results can provide a theoretical basis for the research on target detection related to human behavior recognition.

关键词： Human action recognition Monitoring scenarios Human behaviors Deep learning ssd algorithm

来源：评论

学校读者我要写书评

暂无评论

Identifying student behavioural states in business English listening classroom based on ssd algorithm

引用

INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY 2023年第4期73卷 288-296页

作者： Gao, Xuewei Xin, Juan Xian Aeronaut Inst Sch Humanities & Foreign Languages Xian Shannxi Peoples R China MUFG Bank Ltd Dept CIB Credit London England

By analysing students' behavioural states, one can evaluate their level of participation, engagement and focus in learning activities. Therefore, this study designs a method for identifying student behaviour states in business English listening classes based on the ssd algorithm. The behaviour state features are input into the improved ssd algorithm model. Within the model, behavioural state features are gradually extracted through operations such as convolution and pooling, and the classification and recognition results of student behavioural states are output. In the experimental results, the Cohen's Kappa coefficient of the identification results obtained by this method can reach 0.974, and the global minimum and maximum values of the Matthews correlation coefficient are 0.80 and 0.95, indicating that the identification results of this method are effective.

关键词： business English listening class student behaviour status state identification ssd algorithm image enhancement feature extraction

来源：评论

学校读者我要写书评

暂无评论

Adaptive stereo object tracking system based-on block-based ssd algorithm and camera configuration parameter

Adaptive stereo object tracking system based-on block-based ...

引用

Conference on Visual Communications and Image Processing 2003

作者： Ko, JH Huh, Y Park, CJ Kim, ES Kwangwoon Univ Sch Elect Engn Natl Res Lab Media 3D Seoul 139701 South Korea

ISBN: (纸本)0819450235

In this paper, an adaptive stereo object tracking system based on a block-based ssd(sum of squared difference) algorithm and camera configuration parameters is proposed. That is, by applying ssd algorithm to the reference image of the previous frame and the input image of the current frame, each location coordinate of a moving target in the right and left images are extracted and the respective shifted distances from the reference target position which is assumed to be at the origin in the initial frame are detected. Using the pan/tilt's moving angle calculated from the target's shifted distance and the configuration parameters of a stereo camera system, the block-mask size of a target object can be adaptively determined. The target image segmented with this block mask is used as a reference image in the next stage of tracking, and it is automatically updated according to the same procedure during the course of target tracking. From some experiments using sequential 48 frames of the dynamic stereo image, it is analyzed that the horizontal and vertical stereo disparities on the target object after stereo tracking are kept to be very low values of 1.5 and 0.4 pixels on average, respectively.

关键词： stereo object tracking ssd algorithm convergence angle pan/tilt

来源：评论

学校读者我要写书评

暂无评论

Research on pedestrian occlusion detection based on ssd algorithm 19

Research on pedestrian occlusion detection based on SSD algo...

引用

International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)

作者： Zhang, Yin Lin, Jianqiang Guangxi Univ Sci & Technol Liu Zhou Peoples R China

ISBN: (纸本)9781450372985

As a basic identification technology, pedestrian detection provides technical support for many areas such as security monitoring and autonomous driving,and has a wide range of application scenarios. Based on the Single Shot MultiBox Detector (ssd) target detection algorithm, this paper trains a pedestrian detection system based on the ssd target detection framework with a self-built occlusion pedestrian dataset for the specific target of occlusion pedestrians. The test set and the re-annotated INRIA test set were used to compare the HOG+SVM based pedestrian detection system and the trained ssd model in OpenCV. The experimental results show that the detection effect of the ssd model is significantly better than the traditional pedestrian detection system based on HOG+SVM. The features learned by the deep convolutional neural network are more robust.

关键词： Occlusion pedestrian detection Deep learning ssd algorithm Self-built pedestrian database

来源：评论

学校读者我要写书评

暂无评论

An active contour based ssd algorithm for tracking a moving object

An active contour based SSD algorithm for tracking a moving ...

引用

Conference on Real-Time Imaging VIII

作者： Han, Y Song, P Chung, H Hahn, H Soongsil Univ Sch Elect Engn Seoul 156743 South Korea

ISBN: (纸本)0819452009

Since the shape of a 3D object moving in 3D space changes a lot in 2D image due to translation and rotation, it is very difficult to track the object using the ssd algorithm which finds the matching object in the input image using the template of the moving object. To solve the problem, this paper presents an enhanced ssd algorithm which updates the template based on an extended snake algorithm adaptive to the shape variation. The proposed snake algorithm uses the derivative of the area as the constraint energy to determine the boundary of an interested area considering the progressive variation of the shape. The performance of the proposed algorithm has been proved by the experiments where a mobile robot with one camera tracks a 31) target object translating and rotating arbitrarily in the 3D workspace.

关键词： snake algorithm object tracking ssd algorithm mobile robot visual tracking

来源：评论

学校读者我要写书评

暂无评论

Defect detection of photovoltaic modules based on improved ssd algorithm 2

Defect detection of photovoltaic modules based on improved S...

引用

2nd International Conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023

作者： Kong, Xiangyu Xu, Wanxuan Xu, Bohao Jin, Hui Zhan, Peihong Guangdong Polytechnic of Science and Trade Institute of Information Guangzhou510430 China

ISBN: (纸本)9798350331417

Automated inspection of unmanned aerial vehicles (UAVs) offers an effective solution to address the operational and maintenance requirements of large-scale distributed photovoltaic systems. Due to the abundance of image data generated by UAVs, a robust algorithm is needed to achieve higher recognition accuracy and faster processing speed. In this regard, we propose an enhanced Single Shot MultiBox Detector (ssd) algorithm for detecting defects in photovoltaic (PV) modules. The novel algorithm incorporates an attention mechanism into the original ssd algorithm and leverages transfer learning to enhance both detection speed and accuracy. It is capable of automatically identifying and classifying common PV module defects such as glass breakage, yellowing of the light receiving surface, and dust accumulation. Experimental results demonstrate that the improved ssd algorithm outperforms other state-of-the-art algorithms including Faster-RCNN, YOLO3, and VGG16-ssd in terms of recognition accuracy, recall rate, and detection speed. Consequently, the proposed algorithm significantly enhances the efficiency of defect recognition in photovoltaic modules. © 2023 IEEE.

关键词： Attention mechanism Deep learning Photovoltaic detection ssd algorithm Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Elderly Fall Detection Based on Improved ssd algorithm

引用

Journal of New Media 2021年第1期3卷 1-10页

作者： Jiancheng Zou Na Zhu Bailin Ge Don Hong North China University of Technology Beijing100144China Department of Mathematical Sciences Middle Tennessee State UniversityMurfreesboroTN 37132USA

We propose an improved a single-shot detector(ssd)algorithm to detect falls of the *** VGG16 network part of the ssd network is replaced with the MobilenetV2 *** the same time,we change the infrastructure of MobilenetV2 network,the three layers that were not down-sampled at the end were removed,which can make the model structure simpler and faster to *** complete Intersection-over-Union(CIoU)loss function is introduced to get a good regression of the target borders that have different sizes and different *** use Feature Pyramid Network(FPN)for up-sampling,it can fuse low-level feature maps with high resolution and high-level feature maps with rich semantic *** sampling results,we use the Secure Shell(SSH)module to extract different receptive fields,which improves the detection *** model ensures that the accuracy of the elderly fall detection remains unchanged,but it greatly improves the detection speed that only takes 10 milliseconds to detect a picture.

关键词： ssd algorithm MobileNetV2 network fall detection

来源：评论

学校读者我要写书评

暂无评论

ANOMALY DIAGNOSIS METHOD AND CONDITION ASSESSMENT OF POWER METERING DEVICE BASED ON ssd algorithm

引用

SCALABLE COMPUTING-PRACTICE AND EXPERIENCE 2023年第4期24卷 1177-1184页

作者： Jiang, Chao Wang, Jinghua Wang, Yue Zhao, Wanru Shanghai Univ Elect Power Sch Econ & Management Shanghai 200090 Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200000 Peoples R China State Grid Shanghai Mkt Serv Ctr Shanghai 200030 Peoples R China

The advancement of anomaly diagnosis methods plays a crucial role in classifying and analyzing data, particularly in distinguishing between normal and abnormal patterns. This study explores the utilization of Support Vector Machine (SVM) techniques to facilitate the selection of pertinent data, thus enhancing the accuracy of anomaly detection. Furthermore, this research delves into the condition assessment process, which offers valuable insights into the real-time state of entities passing through power metering devices. Drawing upon a wealth of secondary data sources, this study employs the ssd algorithm to gain a comprehensive understanding of power metering devices and their interrelated aspects. The ssd algorithm, with its diverse anchor points, is revealed as a powerful tool for quantifying the energy flow passing through the power metering device. This approach not only aids in precise energy measurement but also provides essential insights into the functioning of power metering systems. By combining anomaly diagnosis, SVM techniques, and the ssd algorithm, this study contributes to a deeper comprehension of power metering devices' performance and their capacity to accurately measure energy. These insights have significant implications for improving the overall reliability and efficiency of power metering in various applications.

关键词： anomaly diagnosis secondary data ssd algorithm power metering devices

来源：评论

学校读者我要写书评

暂无评论

Detecting Defects on Solid Wood Panels Based on an Improved ssd algorithm

引用

SENSORS 2020年第18期20卷 5315.-5315.页

作者： Ding, Fenglong Zhuang, Zilong Liu, Ying Jiang, Dong Yan, Xiaoan Wang, Zhengguang Nanjing Forestry Univ Coll Mech & Elect Engn Nanjing 210037 Peoples R China

Wood is widely used in construction, the home, and art applications all over the world because of its good mechanical properties and aesthetic value. However, because the growth and preservation of wood are greatly affected by the environment, it often contains different types of defects that affect its performance and ornamental value. To solve the issues of high labor costs and low efficiency in the detection of wood defects, we used machine vision and deep learning methods in this work. A color charge-coupled device camera was used to collect the surface images of two types of wood from Akagi and Pinus sylvestris trees. A total of 500 images with a size of 200 x 200 pixels containing wood knots, dead knots, and checking defects were obtained. The transfer learning method was used to apply the single-shot multibox detector (ssd), a target detection algorithm and the DenseNet network was introduced to improve the algorithm. The mean average precision for detecting the three types of defects, live knots, dead knots and checking was 96.1%.

关键词： solid wood panels defect detection ssd algorithm DenseNet network

来源：评论

学校读者我要写书评

暂无评论

An enhanced method for surface defect detection in workpieces based on improved MobileNetV2-ssd

引用

EXPERT SYSTEMS 2025年第1期42卷

作者： Qiu, Junlin Shen, Yongshan Lin, Jianchu Qin, Yuxin Yang, Jian Lei, Hengdan Li, Minghui Huaiyin Inst Technol Fac Comp & Software Engn Huaian Peoples R China Huaiyin Inst Technol Fac Comp & Software Engn Huaian 223001 Peoples R China

In the process of workpieces production, surface defects are prone to occur, and these defects come in a wide variety and are often intermixed, making defect detection and classification exceptionally challenging. With the development of artificial intelligence and deep learning, to tackle this problem, this paper introduces an enhanced single shot multibox detector algorithm based on MobileNetV2 for the detection of surface defects. The method utilizes MobileNetv2 as the backbone of the feature extraction network to obtain six feature layers with different detection scales from the baseline network, that is, the original 1 x 1 feature prediction layer is deleted and a 75 x 75 feature prediction layer is added, which is closer to the specific features of the defects on the surface of the workpiece. In the additional feature layer, two parallel dilated convolution structures are connected, introducing depth-separable convolution and dilated convolution, combining skip connections and pixel-wise addition operations. A special feature fusion structure is proposed to perform feature fusion for small, medium and large target detection layers, which effectively solves the problem of missed and false detection. Moreover, it refines candidate bounding box aspect ratios within the training set through the utilization of the K-means clustering algorithm, ensuring a better match with real boxes. The experimental results demonstrate the effectiveness of the enhanced model, and the mean average precision value reaches 88.72%. Compared to other state-of-the-art detection methods, it exhibits superior capabilities.

关键词： artificial intelligence deep learning feature fusion parallel dilated convolution structure ssd algorithm surface defects in workpieces

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：