检索结果-内蒙古大学图书馆

Slim-neck by GSConv: a lightweight-design for real-time detector architectures

JOURNAL OF real-time image processing 2024年第3期21卷 62-62页

作者： Li, Hulin Li, Jun Wei, Hanbing Liu, Zheng Zhan, Zhenfei Ren, Qiliang Chongqing Jiaotong Univ Coll Traff & Transportat Chongqing 400074 Peoples R China Chongqing Jiaotong Univ Sch Mechatron & Vehicle Engn Chongqing 400074 Peoples R China Univ British Columbia Okanagan Sch Engn Kelowna BC V1V 1V7 Canada

real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement, and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, slim-neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP(50) for the SODA10M at a speed of similar to 100 FPS on a Tesla T4) compared with the baselines. Code is available at https://***/alanli1997/slim-neck-by-gsconv.

关键词： GSConv deep learning CNNs real-time detection Lightweight Edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhancing lecture capture with deep learning

引用

ADVANCES IN ENGINEERING SOFTWARE 2024年 196卷

作者： Sales, R. M. Giani, S. Univ Cambridge Whittle Lab Cambridge England Univ Durham Durham Coll Durham England

This paper provides an insight into the development of a state-of-the-art video processing system to address limitations within Durham University's 'Encore' lecture capture solution. The aim of the research described in this paper is to digitally remove the persons presenting from the view of a whiteboard to provide students with a more effective online learning experience. This work enlists a 'human entity detection module', which uses a remodelled version of the Fast Segmentation Neural Network to perform efficient binary image segmentation, and a 'background restoration module', which introduces a novel procedure to retain only background pixels in consecutive video frames. The segmentation network is trained from the outset with a Tversky loss function on a dataset of images extracted from various Tik-Tok dance videos. The most effective training techniques are described in detail, and it is found that these produce asymptotic convergence to within 5% of the final loss in only 40 training epochs. A cross-validation study then concludes that a Tversky parameter of 0.9 is optimal for balancing recall and precision in the context of this work. Finally, it is demonstrated that the system successfully removes the human form from the view of the whiteboard in a real lecture video. Whilst the system is believed to have the potential for real-time usage, it is not possible to prove this owing to hardware limitations. In the conclusions, wider application of this work is also suggested.

关键词： Convolutional neural network Semantic image segmentation Binary human segmentation learning rate optimisation Lecture capture technology

来源：评论

学校读者我要写书评

暂无评论

deep learning Innovations for Underwater Waste Detection: An In-Depth Analysis

引用

IEEE ACCESS 2025年 13卷 88917-88929页

作者： Walia, Jaskaran Singh Haridass, Kavietha Pavithra, L. K. Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 India Vellore Inst Technol Ctr Human Movement Analyt Chennai 600127 India

Underwater waste detection is a critical challenge for preserving aquatic ecosystems, particularly due to inherent underwater distortions such as light refraction, occlusion, and scattering. In this study, we present a novel deep learning framework for real-time underwater waste detection by evaluating state-of-the-art object detection algorithms on a manually annotated custom dataset comprising images across various water bodies to represent real-world turbidity, illumination, and occlusion. Our approach incorporates robust feature extraction and specialized data augmentation techniques that effectively mitigate the adverse effects of underwater distortions. We investigate multiple architectures, including YOLOv8n, YOLOv7, YOLOv6s, YOLOv5s, Faster R-CNN, and Mask R-CNN, analyzing key parameters such as mean average precision (mAP), inference speed, and computational efficiency. Our results demonstrate that YOLO-based models achieve faster & accurate performance, with YOLOv8n and YOLOv7 reaching a detection accuracy of 96%, compared to 81% and 83% for Faster R-CNN and Mask R-CNN, respectively. Computationally, YOLOv8n achieves 76 ms (milliseconds) per frame, while YOLOv5s runs at 14 ms per frame, confirming real-time viability for AUV deployment. The proposed approach offers significant advantages over existing methods by enabling rapid, accurate detection with low computational overhead, thereby paving the way for integration with autonomous underwater vehicles (AUVs) for environmental monitoring and waste management.

关键词： deep learning Technological innovation Biological system modeling Robots Reviews Accuracy Lighting Benchmark testing YOLO Robot sensing systems Computer vision image processing robotics object detection underwater trash image segmentation deep learning CNN

来源：评论

学校读者我要写书评

暂无评论

DReLNet: abnormal human activity classification in theft surveillance video using reinforcement learning based fusion

引用

SIGNAL image AND VIDEO processing 2025年第3期19卷 1-20页

作者： Kale, Shubhangi Prabhakar Raghunathan, Shriram VIT Bhopal Univ Sch Comp Sci & Engn Bhopal 466114 Madhya Pradesh India MIT Acad Engn Sch Comp Engn Alandi 412105 Maharashtra India

The surge in illegal activities has underscored the critical role of surveillance cameras in monitoring and recording suspicious actions. However, the vast data generated by these systems poses a significant challenge in classifying abnormal activities. To address this, DReLNet is proposed for Abnormal Human Activity Classification in Theft Surveillance Video Using Reinforcement learning-Based Fusion. The approach begins by extracting frames from surveillance videos, followed by noise reduction using a Stacked Bilateral Median Filter. Keyframes are identified via Absolute Consecutive Histogram Difference, and features are extracted using Capsule Net, DenseNet 201, and ResNet-152 models. These features are then fused, and abnormal activities are classified using the deep reinforcement learning-assisted model, DReLNet. The proposed model achieves an accuracy of 99.55% on the Theft dataset, significantly outperforming existing models such as deepCNN, conv_LSTM, Bi_GRU and GRU. Higher accuracy enhances the model's overall performance by reducing the probability of incorrect classifications, which is critical for effective real-time surveillance systems.

关键词： Median filter Reinforcement learning Capsule net DenseNet 201 ResNet-152 Consecutive histogram difference

来源：评论

学校读者我要写书评

暂无评论

real-time Predictability Analysis and Enhancement of deep-learning-Based Object Tracking 24

Real-Time Predictability Analysis and Enhancement of Deep-Le...

引用

6th International Conference on image processing and Machine Vision (IPMV)

作者： Zhang, Mingyang Van Beeck, Kristof Goedeme, Toon Katholieke Univ Leuven Dept Elect Engn PSI EAVISE Res Grp Leuven Belgium

ISBN: (纸本)9798400708473

While Siamese object tracking has witnessed significant advancements, its hard real-time behaviour on embedded devices remains inadequately addressed. In many application cases, an embedded implementation should not only have a minimal execution latency, but this latency should ideally also be having zero variance, i.e. predictable. To bridge this gap, we firstly analyse the real-time predictability of components of a state-of-the-art deep-learning-based object video object tracking system. Our detailed experiments indicate the superiority of FPGA implementations in terms of hard real-time behaviour, but unveil important time-predictability bottlenecks. Then, we craft a dedicated hardware accelerator specifically for the bottleneck. Our method seamlessly integrates advanced tracker features and improves greatly the tracker's speed and time-predictability on embedded systems. Implemented on a KV260 board, our quantized tracker demonstrates superior performance. These findings spotlight the immense promise of hardware acceleration in real-time object tracking and set a benchmark for forthcoming hardware-software co-design pursuits focused on achieving time-predictable object tracking.

关键词： Siamese network FPGA real-time system predictability SiamRPN plus

来源：评论

学校读者我要写书评

暂无评论

Research on Parking Space Detection and Prediction Model Based on CNN-LSTM

引用

IEEE ACCESS 2024年 12卷 30085-30100页

作者： Xu, Zhuye Tang, Xiao Ma, Changxi Zhang, Renshuai Lanzhou Jiaotong Univ Sch New Energy & Power Engn Lanzhou 730070 Peoples R China Changsha Univ Sci & Technol Natl Engn Res Ctr Highway Maintenance Technol Changsha 410114 Hunan Peoples R China Lanzhou Jiaotong Univ Sch New Energy & Power Engn Intelligent Bldg & Bldg Automat Lab Lanzhou 730070 Peoples R China Lanzhou Jiaotong Univ Sch Transportat Lanzhou 730070 Peoples R China

With the continuous acceleration of urbanization, the parking problem is becoming increasingly serious. How to better manage parking resources has become an urgent problem to be solved in urban development. In this context, according to the historical data and real-time video data collected by the parking camera, this paper proposes an algorithm for parking space detection and state recognition. Through image preprocessing, region of interest selection, Hough line detection, and parking information recognition of the input test image, an intelligent parking space detection model is constructed, which improves the utilization rate of parking space and reduces the management cost. On this basis, according to the free parking space data obtained by the detection algorithm, a short-term demand prediction algorithm for on-road parking based on Convolutional Neural Network (CNN) and Long Short-Term Memory Neural Network (LSTM) was proposed. Through the preprocessing of input parking space data, time vector transformation, data separation, model training, and prediction, the parking demand data is predicted and analyzed. By comparing the prediction results of multiple models, it was found that the CNN-LSTM prediction model had the best model stability and goodness of fit, the lowest Mean Error (MAE) and Root Mean Square Error (RMSE), the errors of working days were 13.301 and 21.156, and the errors of rest days were 12.573 and 20.739, respectively. It shows that CNN-LSTM can effectively capture the time and spatial feature information of parking lot free parking space data, and the prediction accuracy is good, which can be used to predict the number of free parking spaces in parking lots.

关键词： Automobiles Predictive models Convolutional neural networks real-time systems Gray-scale Urban areas image edge detection deep learning Key words deep learning parking space detection image processing convolutional neural network long short-term memory neural network

来源：评论

学校读者我要写书评

暂无评论

PHL-YOLO: a real-time lightweight yarn inspection method

引用

JOURNAL OF real-time image processing 2025年第1期22卷 1-14页

作者： Dai, Jiachao Ren, Jia Li, Shangjie Zhejiang Sci Tech Univ Sch Informat Sci & Engn Hangzhou 310018 Peoples R China Zhejiang Sci Tech Univ Changshan Res Inst Co Ltd Quzhou 324299 Peoples R China

To meet the real-time and high-precision detection requirements in actual yarn production, this paper introduces a novel lightweight yarn detection method named PHL-YOLO, an optimized version of the YOLOv8 algorithm. Initially, we developed the PEC2F module by fusing PConv (partial convolution) and EMA (efficient multi-scale attention) components to enhance the model's feature extraction capabilities while concurrently reducing computational demands and the number of parameters. Subsequently, we deployed the HWD (Haar wavelet downsampling) module for downsampling, which effectively diminishes image resolution without sacrificing the critical information necessary for precise detection. Additionally, to address the excessive parameters and computational complexity in the detection head of YOLOv8, we introduced the LSCDH (lightweight shared convolutional detection head) module, which significantly simplifies the structure of the detection head. Finally, we applied a structured pruning technique, GSPMD (group-level structured pruning method with DepGraph), to further refine the model. The experimental outcomes indicate that our enhanced model PHL-YOLO has achieved a 1.0% increase in precision, a 2.5% improvement in recall, and a 2.3% increase in mAP (mean average precision), along with a 26 FPS performance boost over the original model. Furthermore, our model's computational load and parameter count are only 29.6% and 10.2% of those in the original YOLOv8 model, respectively. PHL-YOLO not only effectively reduces model complexity, but also upholds high performance levels, providing a valuable reference for rapid and accurate yarn detection in real-world production scenarios.

关键词： Yarn inspection deep learning YOLOv8 Lightweight Model pruning

来源：评论

学校读者我要写书评

暂无评论

real-time Registration of Unmanned Aerial Vehicle Hyperspectral Remote Sensing images Using an Acousto-Optic Tunable Filter Spectrometer

引用

DRONES 2024年第7期8卷 329-329页

作者： Liu, Hong Hu, Bingliang Hou, Xingsong Yu, Tao Zhang, Zhoufeng Liu, Xiao Liu, Jiacheng Wang, Xueji Chinese Acad Sci Xian Inst Opt & Precis Mech Xian 710119 Peoples R China Xi An Jiao Tong Univ Sch Elect & Informat Engn Xian 710049 Peoples R China Chinese Acad Sci Key Lab Spectral Imaging Technol Xian 710119 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Differences in field of view may occur during unmanned aerial remote sensing imaging applications with acousto-optic tunable filter (AOTF) spectral imagers using zoom lenses. These differences may stem from image size deformation caused by the zoom lens, image drift caused by AOTF wavelength switching, and drone platform jitter. However, they can be addressed using hyperspectral image registration. This article proposes a new coarse-to-fine remote sensing image registration framework based on feature and optical flow theory, comparing its performance with that of existing registration algorithms using the same dataset. The proposed method increases the structure similarity index by 5.2 times, reduces the root mean square error by 3.1 times, and increases the mutual information by 1.9 times. To meet the real-time processing requirements of the AOTF spectrometer in remote sensing, a development environment using VS2023+CUDA+OPENCV was established to improve the demons registration algorithm. The registration algorithm for the central processing unit+graphics processing unit (CPU+GPU) achieved an acceleration ratio of similar to 30 times compared to that of a CPU alone. Finally, the real-time registration effect of spectral data during flight was verified. The proposed method demonstrates that AOTF hyperspectral imagers can be used in real-time remote sensing applications on unmanned aerial vehicles.

关键词： acousto-optic tunable filter image registration real-time processing spectral imaging UAV remote sensing

来源：评论

学校读者我要写书评

暂无评论

deep learning-assisted common temperature measurement based on visible light imaging

引用

Chinese Physics B 2024年第8期33卷 230-236页

作者：朱佳仪何志民黄成曾峻林惠川陈福昌余超群李燕张永涛陈焕庭蒲继雄 College of Physics and Information Engineering Minnan Normal UniversityZhangzhou 363000China Fujian Provincial Key Laboratory of Light Propagation and Transformation College of Information Science&EngineeringHuaqiao UniversityXiamen 361021China

real-time,contact-free temperature monitoring of low to medium range(30℃-150℃)has been extensively used in industry and agriculture,which is usually realized by costly infrared temperature detection *** paper proposes an alternative approach of extracting temperature information in real time from the visible light images of the monitoring target using a convolutional neural network(CNN).A mean-square error of<1.119℃was reached in the temperature measurements of low to medium range using the CNN and the visible light *** angle and imaging distance do not affect the temperature detection using visible optical images by the ***,the CNN has a certain illuminance generalization ability capable of detection temperature information from the images which were collected under different illuminance and were not used for *** to the conventional machine learning algorithms mentioned in the recent literatures,this real-time,contact-free temperature measurement approach that does not require any further image processing operations facilitates temperature monitoring applications in the industrial and civil fields.

关键词： convolutional neural network visible light image temperature measurement low-to-medium-range temperatures

来源：评论

学校读者我要写书评

暂无评论

EdgeScan for IoT Contextual Understanding With Edge Computing and image Captioning

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第6期12卷 6519-6535页

作者： Hafeth, Deema Abdal Al-Khafajiy, Mohammed Kollias, Stefanos Univ Lincoln Sch Comp Sci Lincoln LN6 7TS England Natl Tech Univ Athens Sch Elect & Comp Engn Athens 15780 Greece

The emergence of Edge Computing has shifted the processing capabilities in proximity to the Internet of Things (IoT) data sources, offering solutions to latency and bandwidth constraints applications. This shift complements Cloud Computing, especially in handling real-time data processing and enhancing processing. image processing, particularly image captioning for smart monitoring systems, benefits greatly from this synergy. image captioning plays a crucial role in understanding visual data. While early methods excelled in encoder-decoder frameworks and attention mechanisms, they often overlooked semantic representations which are essential for comprehensive image understanding. To address this gap, we introduce the EdgeScan framework, leveraging Edge Computing for image analysis and semantic feature extractions closer to data sources. EdgeScan integrates visual and semantic features to create more informative and enriched image captions that enhance image captioning accuracy. The EdgeScan image captioning model architecture is capable of 1) learning the salient image region's specific feature representation and 2) co-embedding visual attention and semantic attributes in one space for feature fusion. This improves models' ability to interpret and respond to data in a meaningful way, which is particularly valuable for IoT applications that require a deep understanding of the semantics of diverse and constantly changing data for efficient operation. Extensive experiments were conducted on the MS-COCO dataset to demonstrate the superiority of EdgeScan in both quantitative and qualitative performance, achieving highest consensus-based image description evaluation score of 120.9, as well as notable scores of 78.6 for BLEU@1 and 57.7 for recall-oriented understudy for gisting evaluation metrics, promising advancements in IoT-driven image understanding and competitiveness against the state of the art.

关键词： image edge detection Cloud computing Semantics Computational modeling Edge computing Visualization Data models Feature extraction Data processing image captioning Internet of Things (IoT) semantic attentions semantic attentions

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：