eess.IV - 2023-10-12

Cross-correlation image analysis for real-time particle tracking

  • paper_url: http://arxiv.org/abs/2310.08770
  • repo_url: None
  • paper_authors: Leonardo R. Werneck, Cody Jessup, Austin Brandenberger, Tyler Knowles, Charles W. Lewandowski, Megan Nolan, Ken Sible, Zachariah B. Etienne, Brian D’Urso
  • for: 用于实时图像分析,尤其是在反馈控制系统中。
  • methods: 使用新的算法,可以实时检测图像中的微小移动,并且可以抗干扰。
  • results: 实现了实时图像分析,并且可以达到干扰限制的精度。
    Abstract Accurately measuring translations between images is essential in many fields, including biology, medicine, geography, and physics. Existing methods, including the popular FFT-based cross-correlation, are not suitable for real-time analysis, which is especially vital in feedback control systems. To fill this gap, we introduce a new algorithm which approaches shot-noise limited displacement detection and a GPU-based implementation for real-time image analysis.
    摘要 精准测量图像之间的翻译是许多领域的关键,包括生物学、医学、地理学和物理学。现有的方法,包括受欢迎的FFT基于的横距矩阵相关,不适合实时分析,尤其是在反馈控制系统中。为填补这一漏洞,我们介绍了一种新的算法,可以实现射频噪声限制的位移检测,以及基于GPU的实时图像分析实现。

Unlocking the capabilities of explainable fewshot learning in remote sensing

  • paper_url: http://arxiv.org/abs/2310.08619
  • repo_url: None
  • paper_authors: Gao Yu Lee, Tanmoy Dam, Md Meftahul Ferdaus, Daniel Puiu Poenar, Vu N Duong
  • for: 这个评论旨在提供一个最新的概述,探讨深度学习方法在基于遥感图像的任务上的效率和可效性。
  • methods: 这篇评论提出了一些新的几何学学习方法,以及现有的数据集的应用。
  • results: 评论表明,几何学学习方法可以有效地适应基于遥感图像的更广泛和多样化的视角。同时,评论也评估了一些最新的state-of-the-art几何学学习方法在隐私场景中的性能。
    Abstract Recent advancements have significantly improved the efficiency and effectiveness of deep learning methods for imagebased remote sensing tasks. However, the requirement for large amounts of labeled data can limit the applicability of deep neural networks to existing remote sensing datasets. To overcome this challenge, fewshot learning has emerged as a valuable approach for enabling learning with limited data. While previous research has evaluated the effectiveness of fewshot learning methods on satellite based datasets, little attention has been paid to exploring the applications of these methods to datasets obtained from UAVs, which are increasingly used in remote sensing studies. In this review, we provide an up to date overview of both existing and newly proposed fewshot classification techniques, along with appropriate datasets that are used for both satellite based and UAV based data. Our systematic approach demonstrates that fewshot learning can effectively adapt to the broader and more diverse perspectives that UAVbased platforms can provide. We also evaluate some SOTA fewshot approaches on a UAV disaster scene classification dataset, yielding promising results. We emphasize the importance of integrating XAI techniques like attention maps and prototype analysis to increase the transparency, accountability, and trustworthiness of fewshot models for remote sensing. Key challenges and future research directions are identified, including tailored fewshot methods for UAVs, extending to unseen tasks like segmentation, and developing optimized XAI techniques suited for fewshot remote sensing problems. This review aims to provide researchers and practitioners with an improved understanding of fewshot learnings capabilities and limitations in remote sensing, while highlighting open problems to guide future progress in efficient, reliable, and interpretable fewshot methods.
    摘要 现代技术的进步有效地提高了深度学习方法对于图像基于远程感知任务的效率和效果。然而,需要大量标注数据可能限制深度神经网络对现有远程感知数据集的应用。为解决这个挑战,几何学习(fewshot learning)作为一种有价值的方法来启用学习。 although previous research has evaluated the effectiveness of fewshot learning methods on satellite-based datasets, little attention has been paid to exploring the applications of these methods to datasets obtained from UAVs, which are increasingly used in remote sensing studies. In this review, we provide an up-to-date overview of both existing and newly proposed fewshot classification techniques, along with appropriate datasets that are used for both satellite-based and UAV-based data. Our systematic approach demonstrates that fewshot learning can effectively adapt to the broader and more diverse perspectives that UAV-based platforms can provide. We also evaluate some state-of-the-art fewshot approaches on a UAV disaster scene classification dataset, yielding promising results. We emphasize the importance of integrating XAI techniques like attention maps and prototype analysis to increase the transparency, accountability, and trustworthiness of fewshot models for remote sensing. Key challenges and future research directions are identified, including tailored fewshot methods for UAVs, extending to unseen tasks like segmentation, and developing optimized XAI techniques suited for fewshot remote sensing problems. This review aims to provide researchers and practitioners with an improved understanding of fewshot learning's capabilities and limitations in remote sensing, while highlighting open problems to guide future progress in efficient, reliable, and interpretable fewshot methods.

MUN-FRL: A Visual Inertial LiDAR Dataset for Aerial Autonomous Navigation and Mapping

  • paper_url: http://arxiv.org/abs/2310.08435
  • repo_url: None
  • paper_authors: Ravindu G. Thalagala, Sahan M. Gunawardena, Oscar De Silva, Awantha Jayasiri, Arthur Gubbels, George K. I Mann, Raymond G. Gosine
    for:This paper aims to promote GNSS-denied navigation research by providing a unique outdoor aerial dataset captured using a multi-sensor payload.methods:The dataset includes hardware synchronized monocular images, IMU measurements, 3D LiDAR point-clouds, and high-precision RTK-GNSS based ground truth.results:The paper provides a performance summary of state-of-the-art methods applied on the datasets.Here is the same information in Simplified Chinese text:for:这篇论文目的是促进GNSS denied navigation研究,提供一个独特的外部飞行数据集,通过多感器 payload 所捕获。methods:数据集包括硬件同步化的单镜像,IMU测量,3D LiDAR 点云,以及高精度 RTK-GNSS 基准数据。results:论文提供了现有方法在数据集上的性能摘要。
    Abstract This paper presents a unique outdoor aerial visual-inertial-LiDAR dataset captured using a multi-sensor payload to promote the global navigation satellite system (GNSS)-denied navigation research. The dataset features flight distances ranging from 300m to 5km, collected using a DJI M600 hexacopter drone and the National Research Council (NRC) Bell 412 Advanced Systems Research Aircraft (ASRA). The dataset consists of hardware synchronized monocular images, IMU measurements, 3D LiDAR point-clouds, and high-precision real-time kinematic (RTK)-GNSS based ground truth. Ten datasets were collected as ROS bags over 100 mins of outdoor environment footage ranging from urban areas, highways, hillsides, prairies, and waterfronts. The datasets were collected to facilitate the development of visual-inertial-LiDAR odometry and mapping algorithms, visual-inertial navigation algorithms, object detection, segmentation, and landing zone detection algorithms based upon real-world drone and full-scale helicopter data. All the datasets contain raw sensor measurements, hardware timestamps, and spatio-temporally aligned ground truth. The intrinsic and extrinsic calibrations of the sensors are also provided along with raw calibration datasets. A performance summary of state-of-the-art methods applied on the datasets is also provided.
    摘要 Note: "Simplified Chinese" is used to refer to the written form of Chinese that uses simpler characters and grammar than Traditional Chinese. However, it is important to note that there is no single standard for Simplified Chinese, and different regions may use different forms of Simplified Chinese. The translation provided above is based on the common usage of Simplified Chinese in Mainland China.