OBSUM: An object-based spatial unmixing model for spatiotemporal fusion of remote sensing images DOI Creative Commons
Houcai Guo, Dingqi Ye, Hanzeyu Xu

и другие.

Remote Sensing of Environment, Год журнала: 2024, Номер 304, С. 114046 - 114046

Опубликована: Фев. 13, 2024

Spatiotemporal fusion aims to improve both the spatial and temporal resolution of remote sensing images, thus facilitating time-series analysis at a fine scale. However, there are several important issues that limit application current spatiotemporal methods. First, most methods based on pixel-level computation, which neglects valuable shape information ground objects. Moreover, many existing cannot accurately retrieve strong changes between available high-resolution image base date predicted one. This study proposes an Object-Based Spatial Unmixing Model (OBSUM), incorporates object-based unmixing, overcome two abovementioned problems. OBSUM consists one preprocessing step three steps, i.e., object-level residual compensation, compensation. The performance was compared with seven representative agricultural sites. experimental results demonstrated outperformed other in terms accuracy indices visual effects over time-series. Furthermore, also achieved satisfactory crop progress monitoring mapping. Therefore, it has great potential generate accurate observations for supporting various applications.

Язык: Английский

Fractal-Based Pattern Quantification of Mineral Grains: A Case Study of Yichun Rare-Metal Granite DOI Creative Commons
Yue Liu, Tao Sun,

Kaixing Wu

и другие.

Fractal and Fractional, Год журнала: 2024, Номер 8(1), С. 49 - 49

Опубликована: Янв. 12, 2024

The quantification of the irregular morphology and distribution pattern mineral grains is an essential but challenging task in ore-related mineralogical research, allowing for tracing footprints pattern-forming geological processes that are crucial to understanding mineralization and/or diagenetic systems. In this study, a large model, namely, Segmenting Anything Model (SAM), was employed automatically segment annotate quartz, lepidolite albite derived from Yichun rare-metal granite (YCRMG), based on which series fractal multifractal methods, including box-counting calculation, perimeter–area analysis spectra, were implemented. results indicate YCRMG show great scaling invariance within range 1.04~52,300 μm. automatic annotation photomicrographs yields accurate dimensions with error only 0.6% thus can be utilized efficient fractal-based grain quantification. resultant display distinct diagram dimension (Db) versus (DPA), lepidolites sandwiched between greater-valued quartz lower-valued albites. Snowball-textured albites, i.e., concentrically arranged laths K-feldspar, exhibit characteristic Db values ranging 1.6 1.7, coincide indices growth model. zonal albites strictly increasing trend regarding exponents core rim, forming featured “fractal-index banding” radar diagram. This suggests snowball texture gradually evolved rim core, leading greater outer zones, represent higher complexity maturity evolving system, supports metasomatic origin texture. Our study demonstrates analyses aid model effective characterizing complex patterns grains.

Язык: Английский

Процитировано

9
Learning without Exact Guidance: Updating Large-Scale High-Resolution Land Cover Maps from Low-Resolution Historical Labels DOI
Zhuohong Li,

Wei He,

Jiepan Li

и другие.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Год журнала: 2024, Номер 64, С. 27717 - 27727

Опубликована: Июнь 16, 2024

Язык: Английский

Процитировано

9
Enhancing Crop Mapping through Automated Sample Generation Based on Segment Anything Model with Medium-Resolution Satellite Imagery DOI Creative Commons
Jialin Sun, Shuai Yan, Thomas Alexandridis

и другие.

Remote Sensing, Год журнала: 2024, Номер 16(9), С. 1505 - 1505

Опубликована: Апрель 24, 2024

Crop mapping using satellite imagery is crucial for agriculture applications. However, a fundamental challenge that hinders crop progress the scarcity of samples. The latest foundation model, Segment Anything Model (SAM), provides an opportunity to address this issue, yet few studies have been conducted in area. This study investigated parcel segmentation performance SAM on commonly used medium-resolution (i.e., Sentinel-2 and Landsat-8) proposed novel automated sample generation framework based SAM. comprises three steps. First, image optimization automatically selects high-quality images as inputs Then, potential samples are generated masks produced by Finally, subsequently subjected cleaning procedure acquire most reliable Experiments were Henan Province, China, southern Ontario, Canada, six proven effective classifiers. effectiveness our method demonstrated through combination field-survey-collected differently proportioned Our results indicated directly remains challenging, unless parcels large, regular shape, distinct color differences from surroundings. Additionally, approach significantly improved classifiers alleviated problem. Compared trained only samples, resulted average improvement 16% 78.5% respectively. random forest achieved relatively good performance, with weighted-average F1 0.97 0.996 obtained two areas, contributes insights into solutions highlights promising application models like

Язык: Английский

Процитировано

8
FusionVision: A Comprehensive Approach of 3D Object Reconstruction and Segmentation from RGB-D Cameras Using YOLO and Fast Segment Anything DOI Creative Commons
Safouane El Ghazouali,

Youssef Mhirit,

Ali Oukhrid

и другие.

Sensors, Год журнала: 2024, Номер 24(9), С. 2889 - 2889

Опубликована: Апрель 30, 2024

In the realm of computer vision, integration advanced techniques into pre-processing RGB-D camera inputs poses a significant challenge, given inherent complexities arising from diverse environmental conditions and varying object appearances. Therefore, this paper introduces FusionVision, an exhaustive pipeline adapted for robust 3D segmentation objects in imagery. Traditional vision systems face limitations simultaneously capturing precise boundaries achieving high-precision detection on depth maps, as they are mainly proposed RGB cameras. To address FusionVision adopts integrated approach by merging state-of-the-art techniques, with instance methods. The these components enables holistic (unified analysis information obtained both color D channels) interpretation data, facilitating extraction comprehensive accurate order to improve post-processes such 6D pose estimation, Simultanious Localization Mapping (SLAM) operations, dataset extraction, etc. employs YOLO identifying within image domain. Subsequently, FastSAM, innovative semantic model, is applied delineate boundaries, yielding refined masks. synergy between their scene understanding ensures cohesive fusion segmentation, enhancing overall precision segmentation.

Язык: Английский

Процитировано

8
A novel weakly-supervised method based on the segment anything model for seamless transition from classification to segmentation: A case study in segmenting latent photovoltaic locations DOI Creative Commons
Ruiqing Yang, Guojin He, Ranyu Yin

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 130, С. 103929 - 103929

Опубликована: Май 25, 2024

In the quest for large-scale photovoltaic (PV) panel extraction, substantial data volumes are essential, given demand sub-meter rooftop PV resolution. This requires concept of Latent Photovoltaic Locations (LPL) to reduce scope amount subsequent processing. order minimize manual annotation, a pioneering weakly-supervised framework is proposed, which capable generating pixel-level annotations segmentation based on image-level and provides two datasets required classification-then-segmentation strategy without more annotations. The strong noise-resistance Segment Anything Model (SAM) discovered in extremely difficult rough coarse pseudo-label refinement, which, after integrating probability updating mechanism, achieves seamless transition from scene classification semantic segmentation. resulting national LPL distribution map, rendered at 2 m resolution, showcases commendable 92 % accuracy F1-score 91 %, advantages terms efficiency have been verified through large number experiments. process explores how use fundamental models accelerate remote sensing information extraction process, crucial current trajectory deep learning sensing. relevant code available https://github.com/Github-YRQ/LPL.

Язык: Английский

Процитировано

8
MeSAM: Multiscale Enhanced Segment Anything Model for Optical Remote Sensing Images DOI
Xichuan Zhou, Fu Liang, Lihui Chen

и другие.

IEEE Transactions on Geoscience and Remote Sensing, Год журнала: 2024, Номер 62, С. 1 - 15

Опубликована: Янв. 1, 2024

Segment anything model (SAM) has been widely applied to various downstream tasks for its excellent performance and generalization capability. However, SAM exhibits three limitations related remote sensing semantic segmentation task: 1) the image encoders excessively lose high-frequency information, such as object boundaries textures, resulting in rough masks; 2) due being trained on natural images, faces difficulty accurately recognizing objects with large-scale variations uneven distribution images; 3) output tokens used mask prediction are images not applicable segmentation. In this paper, we explore an efficient paradigm applying of images. Furthermore, propose MeSAM, a new fine-tuning method more suitable adapt it tasks. Our first introduces inception mixer into encoder effectively preserve features. Secondly, by designing decoder remote-sensing correction incorporating multiscale connections, make up difference from Experimental results demonstrated that our significantly improves accuracy outperforming some state-of-the-art methods. The code will be available at https://github.com/Magic-lem/MeSAM.

Язык: Английский

Процитировано

7
A Segment Anything Model based weakly supervised learning method for crop mapping using Sentinel-2 time series images DOI Creative Commons
Jialin Sun, Shuai Yan, Xiaochuang Yao

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 133, С. 104085 - 104085

Опубликована: Авг. 10, 2024

Язык: Английский

Процитировано

7
Extracting vectorized agricultural parcels from high-resolution satellite images using a Point-Line-Region interactive multitask model DOI
Mengmeng Li,

Chengwen Lu,

Mengjing Lin

и другие.

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 231, С. 109953 - 109953

Опубликована: Янв. 22, 2025

Язык: Английский

Процитировано

1
Comparative Study of Agricultural Parcel Delineation Deep Learning Methods using Satellite Images: Validation through Parcels Complexity DOI Creative Commons
Amine Hadir, Mohamed Adjou,

Olga Assainova

и другие.

Smart Agricultural Technology, Год журнала: 2025, Номер unknown, С. 100833 - 100833

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

1
多层次分支跨尺度融合的遥感图像语义分割网络 DOI

曾军英 Zeng Junying,

邓森耀 Deng Senyao,

秦传波 Qin Chuanbo

и другие.

Laser & Optoelectronics Progress, Год журнала: 2025, Номер 62(4), С. 0428003 - 0428003

Опубликована: Янв. 1, 2025

Процитировано

1