Automatic extraction of man-made objects from high-resolution satellite imagery by information fusion

2005 ◽  
Author(s):  
◽  
Xiaoying Jin
Keyword(s):  
High Resolution ◽  
Satellite Imagery ◽  
Contextual Information ◽  
Automatic Extraction ◽  
Building Extraction ◽  
Geospatial Information ◽  
University Of Missouri ◽  
Sensing Applications ◽  
High Resolution Satellite Imagery ◽  
The University

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] Recently available high-resolution commercial satellite imagery provides an important new data source for remote sensing applications. Automated feature extraction (AFE) techniques can assist human analysts by rapidly locating geospatial information and have the potential to significantly reduce the amount of time to process and analyze geospatial data. In this research, we have designed and developed systems for automatic extraction of man-made objects (roads, buildings and vehicles) from high-resolution satellite imagery. We conclude that AFE can be greatly enriched and improved by multiinformation fusion and/or multi-cue integration. For road extraction and building extraction respectively, multiple detectors were developed and the extraction performance was greatly improved using multi-detector fusion from different information sources. For vehicle detection, a GIS road vector layer was used to incorporate contextual information and an implicit vehicle model including spectral and spatial characteristics was learned by a morphological shared-weight neural network. An important characteristic of our research on road and building extraction is that our extraction strategies are fully automated with only a few preset parameters. Compared with related research in these areas, the performance evaluations of our extraction systems are among the highest statistical values reported in literature thus far.

scholarly journals Mapping Large-Scale Plateau Forest in Sanjiangyuan Using High-Resolution Satellite Imagery and Few-Shot Learning

2022 ◽  
Vol 14 (2) ◽  
pp. 388
Author(s):  
Zhihao Wei ◽  
Kebin Jia ◽  
Xiaowei Jia ◽  
Pengyu Liu ◽  
Ying Ma ◽  
...  
Keyword(s):  
High Resolution ◽  
Satellite Imagery ◽  
Large Scale ◽  
Ground Truth ◽  
Fine Tuning ◽  
Forest Monitoring ◽  
Learning Method ◽  
Ground Truth Data ◽  
Sensing Applications ◽  
High Resolution Satellite Imagery

Monitoring the extent of plateau forests has drawn much attention from governments given the fact that the plateau forests play a key role in global carbon circulation. Despite the recent advances in the remote-sensing applications of satellite imagery over large regions, accurate mapping of plateau forest remains challenging due to limited ground truth information and high uncertainties in their spatial distribution. In this paper, we aim to generate a better segmentation map for plateau forests using high-resolution satellite imagery with limited ground-truth data. We present the first 2 m spatial resolution large-scale plateau forest dataset of Sanjiangyuan National Nature Reserve, including 38,708 plateau forest imagery samples and 1187 handmade accurate plateau forest ground truth masks. We then propose an few-shot learning method for mapping plateau forests. The proposed method is conducted in two stages, including unsupervised feature extraction by leveraging domain knowledge, and model fine-tuning using limited ground truth data. The proposed few-shot learning method reached an F1-score of 84.23%, and outperformed the state-of-the-art object segmentation methods. The result proves the proposed few-shot learning model could help large-scale plateau forest monitoring. The dataset proposed in this paper will soon be available online for the public.

KAJIAN PROTOTIPE PETA DESA MENGGUNAKAN CITRA SATELIT RESOLUSI TINGGI

2017 ◽  
Vol 19 (2) ◽  
pp. 147
Author(s):  
Bambang Riadi ◽  
Tia Rizka N Rachma
Keyword(s):  
High Resolution ◽  
Rural Communities ◽  
Satellite Imagery ◽  
Technical Specification ◽  
Thematic Maps ◽  
Geospatial Information ◽  
Vector Maps ◽  
High Resolution Satellite Imagery ◽  
The Village

<p align="center"><strong>ABSTRAK</strong></p><p class="JudulABSInd">Peta desa merupakan peta tematik bersifat dasar yang menyajikan unsur-unsur alam dan unsur tema khusus yang pemilihan skalanya mempertimbangkan penyajian seluruh wilayah desa tersajikan dalam satu muka peta. Pengkajian prototipe peta desa bertujuan untuk menguji spesifikasi teknis pembuatan peta desa dan menyediakan peta desa yang dapat memenuhi keperluan masyarakat desa dan pengguna lainnya. Penelitian juga bertujuan untuk mengkaji hal-hal teknis dan non teknis terkait pembuatan peta desa. Data yang digunakan dalam penelitian ini adalah citra tegak resolusi tinggi (CTRT) yang diperoleh dari Badan Informasi Geospasial (BIG). Metode yang digunakan terdiri dari dua tahap, yaitu tahap delineasi batas desa secara kartometrik dan tahap penyajian peta desa. Tahapan delineasi batas desa secara kartometrik mengacu pada Peraturan Menteri dalam Negeri (Permendagri) No. 45 Tahun 2016, sedangkan tahap penyajian peta desa sesuai spesifikasi yang tertuang dalam Peraturan Kepala BIG No. 3 tahun 2016. Selanjutnya peta yang sudah sesuai spesifikasi tersebut diuji melalui kegiatan wawancara dengan aparat desa dan masyarakat untuk mengetahui kebutuhan masyarakat desa akan unsur-unsur yang perlu ditampilkan pada peta. Hasil dari penelitian adalah prototipe peta desa, dengan studi kasus desa Karangligar. Prototipe peta desa mengusulkan penambahan dari spesifikasi penyajian peta yang tertuang dalam Peraturan Kepala BIG, yaitu dengan penambahan unsur kontur, penambahan daftar koordinat titik kartometrik hasil kesepakatan, serta pewarnaan yang disesuaikan  dengan warna dasar citra sebagai latar belakangnya. Selain itu, berdasar hasil wawancara dan diskusi dengan masyarakat desa, diketahui warga lebih mudah membaca dan menggunakan peta dalam bentuk peta garis daripada peta citra.</p><p class="abstrakindo"><strong>Kata kunci</strong>: desa, peta desa, batas desa, Karangligar, citra tegak resolusi tinggi</p><p class="judulABS">                                                             <strong>   ABSTRACT</strong></p><p><em>Village maps are included in the category of basic-thematic maps which presents natural features and special theme considering the scale, and all village area show in one map. Study of village maps prototype is intended to examine technical specification of village map that can fulfill the needs of rural communities and other users, as well as be reviewing the technical and non-technical matters related to making the village map. The data used in this study is orthorectified high-resolution satellite imagery, from Geospatial Information Agency. Method of this study divided into two parts. The first is a delineation of village border that refers to Indonesian Minister of Home Affairs’s Regulation (Permendagri No. 45/2016), then presenting the village map based on a specification of Head of Indonesian Geospatial Information Agency’s Regulation (Peraturan Kepala BIG No.3/2016). The map that fulfills the specification tested by a discussion with the villagers to confirm the villagers need of the map. The result of this research is Village map prototype in Karangligar Village. The prototype of village maps proposed additional elements to complete the village maps, such as adding contour elements, adding the list of coordinates of cartometric points (presented the border points), and modify the element colors adjusted to the color of satellite imagery as the base-map. Moreover, from discussion with villagers as map user, known that villagers more easily got information from a map if it presented in vector maps than imagery maps.</em><em></em></p><p><strong><em>Keywords</em></strong><em>: village, village map, village border, Karangligar, high resolution satellite imagery</em><em></em></p>

Sign in / Sign up

Export Citation Format

Share Document