Landslides inflict substantial societal and economic damage, underscoring their global significance as recurrent and destructive natural disasters. Recent landslides in northern parts of India and Nepal have caused significant disruption, damaging infrastructure and posing threats to local communities. Convolutional Neural Networks (CNNs), a type of deep learning technique, have shown remarkable success in image processing. Because of their sophisticated architectures, advanced CNN-based models perform better in landslide detection than conventional algorithms. The purpose of this work is to investigate CNNs' potential in more detail, with an emphasis on comparison of CNN based models for better landslide detection. We compared four traditional semantic segmentation models (U-Net, LinkNet, PSPNet, and FPN) and utilized the ResNet50 backbone encoder to implement them. Moreover, we have experimented with the hyperparameters such as learning rates, batch sizes, and regularization techniques to fine-tune the models. We have computed the confusion matrix for each model and used performance metrics including precision, recall and f1-score to evaluate and compare the deep learning models. According to the experimental results, LinkNet gave the best results among the four models having an Accuracy of 97.49% and a F1-score of 85.7% (with 84.49% precision, 87.07% recall). We have also presented a comprehensive comparison of all pixel-wise confusion matrix results and the time taken to train each model.
The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection from Multi-Source Satellite Imagery
Institute of Advanced Research in Artificial Intelligence (IARAI)(高级人工智能研究所(IARAI));Wuhan University(武汉大学);Xidian University(西安电子科技大学);Technical University of Munich(慕尼黑工业大学);German Aerospace Center (DLR)(德国航空航天中心(DLR));Chengdu University of Technology(成都理工大学)
这里介绍了由人工智能高级研究所(IARAI)组织的2022年Landslide 4Sense(L4 S)竞赛的科学成果。比赛的目的是根据全球收集的大规模多来源卫星图像自动检测滑坡。2022 L4 S旨在促进对深度学习(DL)模型最新发展的跨学科研究,用于使用卫星图像的语义分割任务。在过去的几年中,由于卷积神经网络(CNN)的发展,基于DL的模型已经实现了满足图像判读期望的性能。本文的主要目的是介绍本次比赛的细节和最佳性能算法。获奖的解决方案采用了最先进的模型,如Swin Transformer、SegFormer和U-Net。还考虑了高级机器学习技术和策略,如硬示例挖掘,自训练和混合数据增强。此外,我们描述了L4 S基准数据集,以方便进一步的比较,并报告的准确性评估结果在线。这些数据可以在\textit{Future Development Leaderboard}上访问,以便将来在\url{https://www.iarai.ac.at/landslide4sense/challenge/}进行评估,研究人员被邀请提交更多的预测结果,评估他们的方法的准确性,将其与其他用户的方法进行比较,并在理想情况下,改进本文中报告的滑坡检测结果。
From Landslide Conditioning Factors to Satellite Embeddings: Evaluating the Utilisation of Google AlphaEarth for Landslide Susceptibility Mapping using Deep Learning
Xi’an Jiaotong-Liverpool University(西交利物浦大学);University of Liverpool(利物浦大学)
A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data
TU Dresden(德累斯顿工业大学);AICURA medical GmbH(AICURA医疗有限公司);National Center of Tumor Diseases (NCT)(国家肿瘤疾病中心);Max Planck Institute for Human Cognitive and Brain Sciences(马克斯·普朗克人类认知与脑科学研究所)
A Comparative Evaluation of Deep Learning Object Detection Models on a Real-World Multi-Plant Dataset from Africa
Bayero University(巴耶罗大学);Alpen-Adria-Universität Klagenfurt(克拉根福阿尔卑斯-亚得里亚大学);Gombe State University(贡贝州立大学);Aliko Dangote University of Science and Technology(阿里科·丹格特科技大学);Ahmadu Bello University(艾哈迈杜·贝洛大学);Federal University Dutse(杜塞联邦大学)
Deep Network Pruning: A Comparative Study on CNNs in Face Recognition
School of Information Science, Computer and Electrical Engineering, Halmstad University(信息科学、计算机与电气工程学院,哈姆斯塔德大学);Computer Graphics and Vision and AI Group, University of Balearic Islands(计算机图形学与视觉与人工智能小组,巴利阿里大学)
A Comparative Study of Vision Transformers and CNNs for Few-Shot Rigid Transformation and Fundamental Matrix Estimation
Department of Computer Science, Ben-Gurion University of the Negev(本·古里安大学内盖夫分校计算机科学系);School of Electrical and Computer Engineering, Ben-Gurion University of the Negev(本·古里安大学内盖夫分校电气与计算机工程学院);GE Healthcare Science and Technology(通用电气医疗科技)
Complex Network for Complex Problems: A comparative study of CNN and Complex-valued CNN
Otto von Guericke University Magdeburg(马格德堡奥托·冯·格里克大学);German Center for Neurodegenerative Disease(德国神经退行性疾病中心);Center for Behavioral Brain Sciences(行为脑科学中心)
Comparative Evaluation of CNN Architectures for Neural Style Transfer in Indonesian Batik Motif Generation: A Comprehensive Study
Department of Data Science, Telkom University, Purwokerto Campus, Indonesia(数据科学系,电信大学,普尔沃克尔托校区,印度尼西亚);Department of Informatics Engineering, Telkom University, Purwokerto Campus, Indonesia(信息技术工程系,电信大学,普尔沃克尔托校区,印度尼西亚);Center of Excellece Human Centric Engineering, Telkom University, Indonesia(以人为本工程研究中心,电信大学,印度尼西亚)
Enhancing Fingerprint Recognition Systems: Comparative Analysis of Biometric Authentication Algorithms and Techniques for Improved Accuracy and Reliability
Multi-Class Brain Tumor Classification Using Advanced Deep Learning Models: A Comparative Study
Department of Computer Science, Quaid-e-Awam University of Engineering, Sciences & Technology(夸迪-艾瓦姆工程、科学与技术大学计算机科学系);Department of Artificial Intelligence, Quaid-e-Awam University of Engineering, Sciences & Technology(夸迪-艾瓦姆工程、科学与技术大学人工智能系);The Faculty of Artificial Intelligence and Cyber Security, Universiti Teknikal Malaysia Melaka(马来西亚梅拉卡技术大学人工智能与网络安全学院);Department of Data Science, Quaid-e-Awam University of Engineering, Sciences & Technology(夸迪-艾瓦姆工程、科学与技术大学数据科学系);Department of Computer Science and Digital Technologies, School of Architecture, Computing and Engineering, University of East London(东伦敦大学建筑、计算与工程学院计算机科学与数字技术系)