检索结果-内蒙古大学图书馆

An Enhancement of Object Detection Using YOLO V8 and Mobile Net in Challenging Conditions

SN computer Science 2025年第4期6卷 1-20页

作者： Pasupuleti, Shailaja Ramalakshmi, K. Gunasekaran, Hemalatha Arokiaraj, Rex Macedo Debnath, Saswati Jebaseeli, T. Jemima Department of Computer Science and Engineering Alliance University Karnataka Anekal Bangalore India AU-Centre of Excellence Department of Computer Vision Alliance University Karnataka Anekal Bangalore India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Computer Science and Engineering Alliance University Karnataka Bangalore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

Autonomous drones and deep learning neural networks are becoming popular tools to revolutionize aircraft operations by partially automating visual inspection processes in aircraft maintenance. The research aims to provide a trustworthy method for locating and classifying surface flaws on aircraft, such as dents, fractures, corrosion, and a few other anomalies. To assess the model performance with and without a lightweight network integration, the implementation merges YOLOv8 and Mobile Net architectures, using dropout regularization and data augmentation approaches. To guarantee the model's performance in low-light situations, the dataset has been carefully selected to contain images replicating such settings. Annotation, environment setup, model training, and online dataset scraping are all covered by the thorough technique. A web-scraped dataset is used to train and validate two popular semantic segmentation algorithms, YOLOv8 and Mobile Net, which show enough performance for segmenting and grading aircraft surface problems in practical settings. The results show that precision and recall values are improved using a hybrid technique that ensembles trained Mobile Net and YOLOv8 models. Using COCO metrics, in the proposed approach an assessment of Ensemble WBF, Mobile Net-YOLO, and YOLOv8 outcomes on test and validation sets, guaranteed reliable object recognition and classification abilities. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Aircraft Classification Mobile-Net Object detection Weighted Box Fusion YOLOv8

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Mamba for 3D Volumetric Medical Image Segmentation

arXiv

引用

arXiv 2025年

作者： Wang, Chaohan Xie, Yutong Chen, Qi Zhou, Yuyin Wu, Qi Australian Institute for Machine Learning The University of Adelaide Adelaide Australia Computer Vision Department MBZUAI Abu Dhabi United Arab Emirates Computer Science and Engineering Department UC Santa Cruz Santa Cruz United States

Mamba, with its selective State Space Models (SSMs), offers a more computationally efficient solution than Transformers for long-range dependency modeling. However, there is still a debate about its effectiveness in high-resolution 3D medical image segmentation. In this study, we present a comprehensive investigation into Mamba’s capabilities in 3D medical image segmentation by tackling three pivotal questions: Can Mamba replace Transformers? Can it elevate multi-scale representation learning? Is complex scanning necessary to unlock its full potential? We evaluate Mamba’s performance across three large public benchmarks—AMOS, TotalSegmentator, and BraTS. Our findings reveal that UlikeMamba, a U-shape Mamba-based network, consistently surpasses UlikeTrans, a U-shape Transformer-based network, particularly when enhanced with custom-designed 3D depthwise convolutions, boosting accuracy and computational efficiency. Further, our proposed multi-scale Mamba block demonstrates superior performance in capturing both fine-grained details and global context, especially in complex segmentation tasks, surpassing Transformer-based counterparts. We also critically assess complex scanning strategies, finding that simpler methods often suffice, while our Tri-scan approach delivers notable advantages in the most challenging scenarios. By integrating these advancements, we introduce a new network for 3D medical image segmentation, positioning Mamba as a transformative force that outperforms leading models such as nnUNet, CoTr, and U-Mamba, offering competitive accuracy with superior computational efficiency. This study provides key insights into Mamba’s unique advantages, paving the way for more efficient and accurate approaches to 3D medical imaging. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Super-Resolution on Low-Resolution Micro-Expression Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Zhou, Ling Wang, Mingpei Huang, Xiaohua Zheng, Wenming Mao, Qirong Zhao, Guoying Macau University of Science and Technology School of Computer Science and Engineering 999078 China Nanjing Institute of Technology School of International Education Oulu School Jiangsu Nanjing211167 China Southeast University Key Laboratory of Child Development and Learning Science Ministry of Education Nanjing210096 China Southeast University Research Center for Learning Science China Southeast University School of Biological Science and Medical Engineering Jiangsu Nanjing210096 China Jiangsu University School of Computer Science and Communication Engineering Jiangsu Zhenjiang212013 China University of Oulu Center for Machine Vision and Signal Analysis 90014 Finland

Micro-expression recognition (MER) in low-resolution (LR) scenarios presents an important and complex challenge, particularly for practical applications such as group MER in crowded environments. Despite considerable advancements in super-resolution (SR) techniques for enhancing the quality of LR images and videos, few study has focused on investigate SR for improving LR MER. The scarcity of investigation can be attributed to the inherent difficulty in capturing the subtle motions of micro-expressions, even in original-resolution MER samples, which becomes even more challenging in LR samples due to the loss of distinctive features. Furthermore, a lack of systematic benchmarking and thorough analysis of SR-assisted MER methods has been noted. This paper tackles these issues by conducting a series of benchmark experiments that integrate both SR and MER methods, guided by an in-depth literature survey. Specifically, we employ seven cutting-edge state-of-the-art (SOTA) MER techniques and evaluate their performance on samples generated from 22 SOTA SR techniques, thereby addressing the problem of SR in MER. Through our empirical study, we uncover the primary challenges associated with SR-assisted MER and identify avenues to tackle these challenges by leveraging recent advancements in both SR and MER methodologies. Our analysis provides insights for progressing toward more efficient SR-assisted MER. © 2010-2012 IEEE.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

RCCNet: An Efficient Convolutional Neural Network for Histological Routine Colon Cancer Nuclei Classification 15

RCCNet: An Efficient Convolutional Neural Network for Histol...

引用

15th International Conference on Control, Automation, Robotics and vision, ICARCV 2018

作者： Shabbeer Basha, S.H. Ghosh, Soumen Kishan Babu, Kancharagunta Ram Dubey, Shiv Pulabaigari, Viswanath Mukherjee, Snehasis Indian Institute of Information Technology Computer Vision and Machine Learning Groups Sri City Andhra Pradesh517646 India

ISBN: (纸本)9781538695821

Efficient and precise classification of histological cell nuclei is of utmost importance due to its potential applications in the field of medical image analysis. It would facilitate the medical practitioners to better understand and explore various factors for cancer treatment. The classification of histological cell nuclei is a challenging task due to the cellular heterogeneity. This paper proposes an efficient Convolutional Neural Network (CNN) based architecture for classification of histological routine colon cancer nuclei named as RCCNet. The main objective of this network is to keep the CNN model as simple as possible. The proposed RCCNet model consists of 1, 512, 868 learnable parameters which are significantly less compared to the popular CNN models such as AlexNet, CIFAR-VGG, GoogLeNet, and WRN. The experiments are conducted over publicly available routine colon cancer histological dataset 'CRCHistoPhenotypes'. The results of the proposed RCCNet model are compared with five state-of-the-art CNN models in terms of the accuracy, weighted average F1 score and training time. The proposed method has achieved a classification accuracy of 80.61% and 0.7887 weighted average F1 score. The proposed RCCNet is more efficient and generalized in terms of the training time and data over-fitting, respectively. © 2018 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Determining mice sex from chest X-rays using deep learning 2

Determining mice sex from chest X-rays using deep learning

引用

2nd IEEE International Conference on Cyberspace, CYBER NIGERIA 2020

作者： Ajiboye, Abiodun Babalola, Kola Institute of Computer Vision and Machine Learning Lagos Nigeria European Molecular Biology Laboratory European Bioinformatics Institute Cambridgshire United Kingdom

ISBN: (纸本)9781665444095

This Following on from work by Babalola et al. It is shown that the sex of mice can be determined from x-ray images of the chest region alone using convolutional neural networks. The anatomical differences that may be responsible for this is further sinvestigated, as it may be useful in determining phenotype changes caused by knocking out genes - hence in understanding genotype-phenotype effects. Our results indicate that the cervical vertebrae may play an important role in the ability of our convolutional neural network to classify the sex of mice correctly using only x-rays of the chest region. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

FAST3D: Flow-Aware Self-Training for 3D Object Detectors 32

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

引用

32nd British machine vision Conference, BMVC 2021

作者： Fruhwirth-Reisinger, Christian Opitz, Michael Possegger, Horst Bischof, Horst Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria Amazon

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g. geographic location, sensor setup, weather condition). State-of-the-art self-training approaches, however, mostly ignore the temporal nature of autonomous driving data. To address this issue, we propose a flow-aware self-training method that enables unsupervised domain adaptation for 3D object detectors on continuous LiDAR point clouds. In order to get reliable pseudo-labels, we leverage scene flow to propagate detections through time. In particular, we introduce a flow-based multi-target tracker that exploits flow consistency to filter and refine resulting tracks. The emerged precise pseudo-labels then serve as a basis for model re-training. Starting with a pre-trained KITTI model, we conduct experiments on the challenging Waymo Open Dataset to demonstrate the effectiveness of our approach. Without any prior target domain knowledge, our results show a significant improvement over the state-of-the-art. © 2021. The copyright of this document resides with its authors.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

DRT: Detection Refinement for Multiple Object Tracking 32

DRT: Detection Refinement for Multiple Object Tracking

引用

32nd British machine vision Conference, BMVC 2021

作者： Wang, Bisheng Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Cao, Guo School of Computer Science and Engineering Nanjing University of Science and Technology China Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria

Deep learning methods have led to remarkable progress in multiple object tracking (MOT). However, when tracking in crowded scenes, existing methods still suffer from both inaccurate and missing detections. This paper proposes Detection Refinement for Tracking (DRT) to address these two issues for people tracking. First, we construct an encoder-decoder backbone network with a novel semi-supervised heatmap training procedure, which leverages human heatmaps to obtain a more precise localization of the targets. Second, we integrate a "one patch, multiple predictions" mechanism into DRT which refines the detection results and recovers occluded pedestrians at the same time. Additionally, we leverage a data-driven LSTM-based motion model which can recover lost targets at a negligible computational cost. Compared with strong baseline methods, our DRT achieves significant improvements on publicly available MOT datasets. In addition, DRT generalizes well, i.e. it can be applied to any detector to improve their performance. © 2021. The copyright of this document resides with its authors.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Robust Autonomous Vehicle Pursuit Without Expert Steering Labels

引用

IEEE Robotics and Automation Letters 2023年第10期8卷 6595-6602页

作者： Pan, Jiaxin Zhou, Changyao Gladkova, Mariia Khan, Qadeer Cremers, Daniel Technical University of Munich Computer Vision Group Garching85748 Germany Munich Data Science Institute Garching85748 Germany Munich Center for Machine Learning Munchen80333 Germany University of Oxford OxfordOX1 3AZ United Kingdom

In this work, we present a learning method for both lateral and longitudinal motion control of an ego-vehicle for the task of vehicle pursuit. The car being controlled does not have a pre-defined route, rather it reactively adapts to follow a target vehicle while maintaining a safety distance. To train our model, we do not rely on steering labels recorded from an expert driver, but effectively leverage a classical controller as an offline label generation tool. In addition, we account for the errors in the predicted control values, which can lead to a loss of tracking and catastrophic crashes of the controlled vehicle. To this end, we propose an effective data augmentation approach, which allows to train a network that is capable of handling different views of the target vehicle. During the pursuit, the target vehicle is firstly localized using a Convolutional Neural Network. The network takes a single RGB image along with cars' velocities and estimates target vehicle's pose with respect to the ego-vehicle. This information is then fed to a Multi-Layer Perceptron, which regresses the control commands for the ego-vehicle, namely throttle and steering angle. We extensively validate our approach using the CARLA simulator on a wide range of terrains. Our method demonstrates real-time performance, robustness to different scenarios including unseen trajectories and high route completion. © 2016 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Even big data is not enough: need for a novel reference modelling for forensic document authentication

Even big data is not enough: need for a novel reference mode...

引用

作者： Garain, Utpal Halder, Biswajit Computer Vision and Pattern Recognition Unit and Centre for Artificial Intelligence and Machine Learning Indian Statistical Institute 203 B. T. Road Kolkata700108 India Department of CSE Narula Institute of Technology Agarpara Kolkata700109 India

With the emergence of big data, deep learning (DL) approaches are becoming quite popular in many branches of science. Forensic science is no longer an exception. However, there are certain problems in forensic science where the solutions would hardly benefit from the recent advances in DL algorithms. Document authentication is one such problem where we can have many reference samples, and with the big data scenario probably we would have even more number of reference samples but number of defective or forged samples will remain an issue. Experts often encounter situations where there is no or hardly a scanty number of forged samples available. In such situation, employment of data-hungry algorithms would be inefficient as they will not be able to learn the forged samples properly. This paper addresses this problem and proposes a novel reference modelling framework for forensic document authentication. The approach is based on Mahalanobis space. Two questioned document examination problems have been studied to show the effectiveness of our reference modelling algorithm which has also been compared to a commonly used learning approach, namely neural network-based classification. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

FAST3D: Flow-aware self-training for 3D object detectors

arXiv

引用

arXiv 2021年

作者： Fruhwirth-Reisinger, Christian Opitz, Michael Possegger, Horst Bischof, Horst Christian Doppler Laboratory for Embedded Machine Learning Institute of Computer Graphics and Vision Graz University of Technology

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g., geographic location, sensor setup, weather condition). State-of-the-art self-training approaches, however, mostly ignore the temporal nature of autonomous driving data. To address this issue, we propose a flow-aware self-training method which enables unsupervised domain adaptation for 3D object detectors on continuous LiDAR point clouds. In order to get reliable pseudo-labels, we leverage scene flow to propagate detections through time. In particular, we introduce a flow-based multi-target tracker, that exploits flow consistency to filter and refine resulting tracks. The emerged precise pseudo-labels then serve as a basis for model re-training. Starting with a pre-trained KITTI model, we conduct experiments on the challenging Waymo Open Dataset to demonstrate the effectiveness of our approach. Without any prior target domain knowledge, our results show a significant improvement over the state-of-the-art. © 2021, CC BY-NC-SA.

关键词： Object detection

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：