检索结果-内蒙古大学图书馆

Surveying You Only Look Once (YOLO) Multispectral Object Detection Advancements, applications, and Challenges

ieee ACCESS 2025年 13卷 7366-7395页

作者： Gallagher, James E. Oughton, Edward J. George Mason Univ Geog & Geoinformat Sci Dept Fairfax VA 22030 USA

Multispectral imaging and deep learning have emerged as powerful tools supporting diverse use cases from autonomous vehicles to agriculture, infrastructure monitoring and environmental assessment. The combination of these technologies has led to significant advancements in object detection, classification, and segmentation tasks in the non-visible light spectrum. This paper considers 400 total papers, reviewing 200 in detail to provide an authoritative meta-review of multispectral imaging technologies, deep learning models, and their applications, considering the evolution and adaptation of you only look once (YOLO). Ground-based collection is the most prevalent approach, totaling 63% of the papers reviewed, although uncrewed aerial systems (UAS) for YOLO-multispectral applications have doubled since 2020. The most prevalent sensor fusion is red-green-blue (RGB) with long-wave infrared (LWIR), comprising 39% of the literature. YOLOv5 remains the most used variant for adaption to multispectral applications, consisting of 33% of all modified YOLO models reviewed. Future research needs to focus on: 1) developing adaptive YOLO architectures capable of handling diverse spectral inputs that do not require extensive architectural modifications;2) exploring methods to generate large synthetic multispectral datasets;3) advancing multispectral YOLO transfer learning techniques to address dataset scarcity;and 4) innovating fusion research with other sensor types beyond RGB and LWIR.

关键词： YOLO Convolutional neural networks computer architecture Deep learning Reviews Accuracy Multispectral imaging Feature extraction computer vision Adaptation models Multispectral object detection you only look once (YOLO) convolutional neural networks (CNN) deep learning RGB LWIR HSI MSI NIR SAR

来源：评论

学校读者我要写书评

暂无评论

Multispectral Semantic Segmentation for Land Cover Classification: An Overview

引用

ieee JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 14295-14336页

作者： Ramos, Leo Thomas Sappa, Angel D. Univ Autonoma Barcelona Comp Vis Ctr Barcelona 08193 Spain Kauel Inc Silicon Valley CA 94025 USA ESPOL Polytech Univ Guayaquil 090112 Ecuador

Land cover classification (LCC) is a process used to categorize the earth's surface into distinct land types. This classification is vital for environmental conservation, urban planning, agricultural management, and climate change research, providing essential data for sustainable decision making. The use of multispectral imaging (MSI), which captures data beyond the visible spectrum, has emerged as one of the most utilized image modalities for addressing this task. In addition, semantic segmentation techniques play a vital role in this domain, enabling the precise delineation and labeling of land cover classes within imagery. The integration of these three concepts has given rise to an intriguing and ever-evolving research field, witnessing continuous advancements aimed at enhancing multispectral semantic segmentation (MSSS) methods for LCC. Given the dynamic nature of this field, there is a need for a thorough examination of the latest trends and advancements to understand its evolving landscape. Therefore, this article presents a review of current aspects in the field of MSSS for LCC, addressing the following key points: 1) prevalent datasets and data acquisition methods;2) preprocessing methods for managing MSI data;3) typical metrics and evaluation criteria used for assessing performance of methods;4) current techniques and methodologies employed;and 5) spectral bands beyond the visible spectrum commonly utilized. Through this analysis, our objective is to provide valuable insights into the current state of MSSS for LCC, contributing to the ongoing development and understanding of this dynamic field while also providing perspectives for future research directions.

关键词： computer vision (CV) deep learning (DL) image segmentation land cover classification (LCC) multispectral imaging (MSI) semantic segmentation remote sensing satellite imagery deep learning (DL) image segmentation land cover classification (LCC) multispectral imaging (MSI) semantic segmentation remote sensing satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery

Spectral Transfer Guided Active Domain Adaptation For Therma...

引用

ieee/CVF Conference on computer vision and Pattern Recognition (CVPR)

作者： Ustun, Berkcan Kaya, Ahmet Kagan Ayerden, Ezgi Cakir Altinel, Fazil Aselsan Inc Res Ctr Yenimahalle Turkiye Middle East Tech Univ Dept Elect & Elect Engn Ankara Turkiye

ISBN: (纸本)9798350302493

The exploitation of visible spectrum datasets has led deep networks to show remarkable success. However, real-world tasks include low-lighting conditions which arise performance bottlenecks for models trained on large-scale RGB image datasets. Thermal IR cameras are more robust against such conditions. Therefore, the usage of thermal imagery in real-world applications can be useful. Unsupervised domain adaptation (UDA) allows transferring information from a source domain to a fully unlabeled target domain. Despite substantial improvements in UDA, the performance gap between UDA and its supervised learning counterpart remains significant. By picking a small number of target samples to annotate and using them in training, active domain adaptation tries to mitigate this gap with minimum annotation expense. We propose an active domain adaptation method in order to examine the efficiency of combining the visible spectrum and thermal imagery modalities. When the domain gap is considerably large as in the visible-to-thermal task, we may conclude that the methods without explicit domain alignment cannot achieve their full potential. To this end, we propose a spectral transfer guided active domain adaptation method to select the most informative unlabeled target samples while aligning source and target domains. We used the large-scale visible spectrum dataset MS-COCO as the source domain and the thermal dataset FLIR ADAS as the target domain to present the results of our method. Extensive experimental evaluation demonstrates that our proposed method outperforms the state-of-the-art active domain adaptation methods. The code and models are publicly available.(1)

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles

D4: Detection of Adversarial Diffusion Deepfakes Using Disjo...

引用

ieee/CVF Winter Conference on applications of computer vision (WACV)

作者： Hooda, Ashish Mangaokar, Neal Feng, Ryan Fawaz, Kassem Jha, Somesh Prakash, Atul Univ Wisconsin Madison Madison WI 53706 USA Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9798350318920;9798350318937

Detecting diffusion-generated deepfake images remains an open problem. Current detection methods fail against an adversary who adds imperceptible adversarial perturbations to the deepfake to evade detection. In this work, we propose Disjoint Diffusion Deepfake Detection (D4), a deepfake detector designed to improve black-box adversarial robustness beyond de facto solutions such as adversarial training. D4 uses an ensemble of models over disjoint subsets of the frequency spectrum to significantly improve adversarial robustness. Our key insight is to leverage a redundancy in the frequency domain and apply a saliency partitioning technique to disjointly distribute frequency components across multiple models. We formally prove that these disjoint ensembles lead to a reduction in the dimensionality of the input subspace where adversarial deepfakes lie, thereby making adversarial deepfakes harder to find for black-box attacks. We then empirically validate the D4 method against several black-box attacks and find that D4 significantly outperforms existing state-of-the-art defenses applied to diffusion-generated deepfake detection. We also demonstrate that D4 provides robustness against adversarial deepfakes from unseen data distributions as well as unseen generative techniques.

关键词： 3D adversarial attack and defense methods Adversarial learning Algorithms Algorithms etc Generative models for image video

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Cross-spectrum Depth Estimation by visible-Light and Thermal Cameras

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第10期24卷 10937-10947页

作者： Guo, Yubin Qi, Xinlei Xie, Jin Xu, Cheng-Zhong Kong, Hui Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China Univ Macau Dept Comp Sci State Key Lab Internet Things Smart City SKL IOTSC Macau Peoples R China Univ Macau Dept Electromech Engn EME State Key Lab Internet Things Smart City SKL IOTSC Macau Peoples R China

Cross-spectrum depth estimation aims to provide a reliable depth map under variant-illumination conditions with a pair of dual-spectrum images. It is valuable for autonomous driving applications when vehicles are equipped with two cameras of different modalities. However, images captured by different-modality cameras can be photometrically quite different, which makes cross-spectrum depth estimation a very challenging problem. Moreover, the shortage of large-scale open-source datasets also retards further research in this field. In this paper, we propose an unsupervised visible light(VIS)-image-guided cross-spectrum (i.e., thermal and visible-light, TIR-VIS in short) depth-estimation framework. The input of the framework consists of a cross-spectrum stereo pair (one VIS image and one thermal image). First, we train a depth-estimation base network using VIS-image stereo pairs. To adapt the trained depth-estimation network to the cross-spectrum images, we propose a multi-scale feature-transfer network to transfer features from the TIR domain to the VIS domain at the feature level. Furthermore, we introduce a mechanism of cross-spectrum depth cycle-consistency to improve the depth estimation result of dual-spectrum image pairs. Meanwhile, we release to society a large cross-spectrum dataset with visible-light and thermal stereo images captured in different scenes. The experiment result shows that our method achieves better depth-estimation results than the compared existing methods. Our code and dataset are available on https://***/whitecrow1027/CrossSP_Depth.

关键词： Index Terms-Unsupervised learning transfer learning mul-tispectral imaging computer vision

来源：评论

学校读者我要写书评

暂无评论

Digital and Physical-World Attacks on Remote Pulse Detection 22

Digital and Physical-World Attacks on Remote Pulse Detection

引用

22nd ieee/CVF Winter Conference on applications of computer vision (WACV)

作者： Speth, Jeremy Vance, Nathan Flynn, Patrick Bowyer, Kevin W. Czajka, Adam Univ Notre Dame Notre Dame IN 46556 USA

ISBN: (纸本)9781665409155

Remote photoplethysmography (rPPG) is a technique for estimating blood volume changes from reflected light without the need for a contact sensor. We present the first examples of presentation attacks in the digital and physical domains on rPPG from face video. Digital attacks are easily performed by adding imperceptible periodic noise to the input videos. Physical attacks are performed with illumination from visible spectrum LEDs placed in close proximity to the face, while still being difficult to perceive with the human eye. We also show that our attacks extend beyond medical applications, since the method can effectively generate a strong periodic pulse on 3D-printed face masks, which presents difficulties for pulse-based face presentation attack detection (PAD). The paper concludes with ideas for using this work to improve robustness of rPPG methods and pulse-based face PAD.

关键词： Performance evaluation computer vision Lighting Medical services Photoplethysmography Light emitting diodes Robustness

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor Ensemble-guided Attention Network for Aerial Vehicle Perception beyond visible spectrum

Multi-sensor Ensemble-guided Attention Network for Aerial Ve...

引用

ieee/CVF Conference on computer vision and Pattern Recognition (CVPR)

作者： Kwasniewska, Alicja MacAllister, Anastacia Nicolas, Rey Garza, Javier SiMa Technol 226 Airport Pkwy San Jose CA 95110 USA Gen Atom 14200 Kirkham Way Poway CA 92064 USA Lockheed Martin 1 Lockheed Blvd Ft Worth TX 76108 USA

ISBN: (纸本)9798350302493

Researchers from different market domains have made significant developments in Artificial Intelligence (AI) enabling more advanced automated sensing systems and, thus, eliminating the need for the time-consuming manual analysis of data, which is prone to human errors. However, successful deployment of such systems in real world applications requires careful design and analysis of the proposed models. This work focuses on perception done on Unmanned Aerial Vehicles (UAV) using multi-task learning. There are multiple challenges when considering such platforms. First of all, they often operate in difficult and dynamic conditions affected by various factors, such as background noises, ego-noise of the motors and occluded views. At the same time, they require high performance local compute, co-designed with optimized software solutions that meet small size, weight, and power (SWaP) requirements. Therefore, the AI models designed for such systems should not introduce computational and memory overheads to allow for real time processing at the embedded edge. Taking this into account, this work proposes a novel neural network-based system that utilizes ensemble-guided modulations of audio path fused with the infrared (IR) visual embedding using the attention mechanism. The ensemble mechanism doesn't require spawning new ensemble members, but instead operates on FiLM (Feature-wise Linear Modulation) activation, making it suitable for resource-constraints embedded edge platforms. The performed experiments show that the proposed network outperforms a single FiLM network by 15% and is more robust to noise.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Pseudo-label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection

Pseudo-label Generation and Various Data Augmentation for Se...

引用

ieee/CVF Conference on computer vision and Pattern Recognition (CVPR)

作者： Yu, Jun Zhang, Liwen Du, Shenshen Chang, Hao Lu, Keda Zhang, Zhong Yu, Ye Wang, Lei Ling, Qiang Univ Sci & Technol China Hefei Anhui Peoples R China Hefei ZhanDa Intelligence Technol Co Ltd Hefei Anhui Peoples R China Hefei Univ Technol Hefei Anhui Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Semi-supervised learning is a highly researched problem, but existing semi-supervised object detection frameworks are based on RGB images, and existing pre-trained models cannot be used for hyperspectral images. To overcome these difficulties, this paper first select fewer but suitable data augmentation methods to improve the accuracy of the supervised model based on the labeled training set, which is suitable for the characteristics of hyperspectral images. Next, in order to make full use of the unlabeled training set, we generate pseudo-labels with the model trained in the first stage and mix the obtained pseudo-labels with the labeled training set. Then, a large number of strong data augmentation methods are added to make the final model better. We achieve the SOTA, with an AP of 26.35, on the Semi-Supervised Hyperspectral Object Detection Challenge (SSHODC) in the CVPR 2022 Perception beyond the visible spectrum workshop, and win the first place in this Challenge.

关键词： Training computer vision Conferences Object detection Semisupervised learning Data models Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Hyperspectral Object Detection Challenge Results - PBVS 2022

Semi-Supervised Hyperspectral Object Detection Challenge Res...

引用

ieee/CVF Conference on computer vision and Pattern Recognition (CVPR)

作者： Rangnekar, Aneesh Mulhollan, Zachary Vodacek, Anthony Hoffman, Matthew Sappa, Angel Blasch, Erik Yu, Jun Zhang, Liwen Du, Shenshen Chang, Hao Lu, Keda Zhang, Zhong Gao, Fang Yu, Ye Shuang, Feng Wang, Lei Ling, Qiang Shyam, Pranjay Yoon, Kuk-Jin Kim, Kyung-Soo Rochester Inst Technol Rochester NY 14623 USA ESPOL Polytech Univ Guayaquil Ecuador Comp Vision Ctr Campus UAB Barcelona Spain US Air Force Res Lab Rome NY USA

ISBN: (纸本)9781665487399

This paper summarizes the top contributions to the first semi-supervised hyperspectral object detection (SSHOD) challenge, which was organized as a part of the Perception beyond the visible spectrum (PBVS) 2022 workshop at the computer vision and Pattern Recognition (CVPR) conference. The SSHODC challenge is a first-of-its-kind hyperspectral dataset with temporally contiguous frames collected from a university rooftop observing a 4-way vehicle intersection over a period of three days. The dataset contains a total of 2890 frames, captured at an average resolution of 1600 x 192 pixels, with 51 hyperspectral bands from 400nm to 900nm. SSHOD challenge uses 989 images as the training set, 605 images as validation set and 1296 images as the evaluation (test) set. Each set was acquired on a different day to maximize the variance in weather conditions. Labels are provided for 10% of the annotated data, hence formulating a semi-supervised learning task for the participants which is evaluated in terms of average precision over the entire set of classes, as well as individual moving object classes: namely vehicle, bus and bike. The challenge received participation registration from 38 individuals, with 8 participating in the validation phase and 3 participating in the test phase. This paper describes the dataset acquisition, with challenge formulation, proposed methods and qualitative and quantitative results. [GRAPHICS] .

关键词： Training computer vision Conferences Training data Object detection Semisupervised learning Transformers

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Impact of Rain on Perception in Automated Vehicle applications

IEEE OPEN JOURNAL OF VEHICULAR TECHNOLOGY

引用

ieee OPEN JOURNAL OF VEHICULAR TECHNOLOGY 2025年 6卷 1018-1032页

作者： Brophy, Tim Mullins, Darragh Parsi, Ashkan Horgan, Jonathan Ward, Enda Denny, Patrick Eising, Ciaran Deegan, Brian Glavin, Martin Jones, Edward Univ Galway Sch Engn Galway H91TK33 Ireland Univ Galway Ryan Inst Galway H91TK33 Ireland Lero Res Ireland Ctr Software Limerick V94NYD3 Ireland Valeo Vis Syst Tuam H54Y276 Ireland Univ Limerick Dept Comp Sci & Informat Syst Limerick V94T9PX Ireland Univ Limerick Dept Elect & Comp Engn Limerick V94T9PX Ireland

The reliable performance of object detection perception algorithms in automated vehicles under adverse conditions such as rain is critical for maintaining vulnerable road user safety. visible-spectrum cameras provide a rich source of information and are cost-effective compared with other sensors;however, their performance can degrade under adverse environmental conditions. Despite the general consensus that the object detection performance in computer vision is adversely affected by rain, there is a relative lack of research investigating this relationship in detail. This study investigates the performance of object detection under rain conditions, focusing on algorithm performance and low-level object characteristics. Using the publicly available BDD100 k dataset, this study examines object detection performance across multiple deep-learning object detection architectures, analyzing error types and image characteristics under rain and no rain conditions. In addition, statistical methods were used to compare image-level metrics to determine statistical significance. The results reveal that rain is not detrimental to object detection performance, and in some cases, better performance is observed. For some models, medium-sized objects experience improved detection and classification under rain conditions, while large objects experience a slight decline in performance. The error analysis shows an increase in localization errors and a decrease in classification errors. The object-level analysis revealed statistically significant changes in the contrast-to-noise ratio, entropy, mean pixel value, pixel variance, hue, saturation, and value, with hue and saturation experiencing the most significant changes. This study highlights the need for more detailed weather labeling in datasets to fully understand the nuances of the relationship between rain and object detection.

关键词： Rain Object detection Meteorology Prevention and mitigation Machine learning Roads Optical distortion Lenses Cameras Autonomous vehicles Adverse weather object detection machine learning automated vehicles

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：