Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

The appetite for up-to-date information about earth’s surface is ever increasing, as such information provides a base for a large number of applications, including local, regional and global resources monitoring, land-cover and land-use change monitoring, and environmental studies. The data from remote sensing satellites provide opportunities to acquire information about land at varying resolutions and has been widely used for change detection studies. A large number of change detection methodologies and techniques, utilizing remotely sensed data, have been developed, and newer techniques are still emerging. This paper begins with a discussion of the traditionally pixel-based and (mostly) statistics-oriented change detection techniques which focus mainly on the spectral values and mostly ignore the spatial context. This is succeeded by a review of object-based change detection techniques. Finally there is a brief discussion of spatial data mining techniques in image processing and change detection from remote sensing data. The merits and issues of different techniques are compared. The importance of the exponential increase in the image data volume and multiple sensors and associated challenges on the development of change detection techniques are highlighted. With the wide use of very-high-resolution (VHR) remotely sensed images, object-based methods and data mining techniques may have more potential in change detection.

Change detection from remotely sensed images: From pixel-based to object-based approaches

Multi-level monitoring of subtle urban changes for the megacities of China using high-resolution multi-view satellite imagery

Urbanization is one of the most impactful human activities across the world today affecting the quality of urban life and its sustainable development. Urbanization in Africa is occurring at an unpr...

https://www.tandfonline.com/doi/pdf/10.1080/10095020.2020.1787800

Urban sprawl and its impact on sustainable urban development: a combination of remote sensing and social media data

In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs. We extensively examine the spatial distribution of study sites, employed sensors, used datasets and CNN architectures, and give a thorough overview of applications in EO which used CNNs. Our main finding is that CNNs are in an advanced transition phase from computer vision to EO. Upon this, we argue that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. With a focus on EO applications in this Part II, we complete the methodological review provided in Part I.

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part II: Applications

The ZiYuan-3 (ZY-3) remote sensing satellite is China's first civilian high-resolution stereo mapping satellite. Because the interior orientation parameters measured before launch are biased, the multispectral (four-band) images collected by ZY-3 exhibit low-accuracy band-to-band registration, which affects their subsequent applications. This paper presents a valid method for interior orientation determination of the ZY-3 multispectral sensor by determining the look angles of the charge-coupled device arrays for all bands. One band is chosen as the benchmark band, and its interior orientation is determined using the relevant ZY-3 image collected over the calibration field and the corresponding digital orthoimage map and digital elevation model. The remaining bands are then calibrated using the benchmark band as control data. The quality of the calibration is further enhanced by shortening the calibration period and by combining images collected over different calibration fields, which decreases the negative effects of errors in the satellite's attitude and position data. The interior orientation of the multispectral sensor in ZY-3 was determined using data sets taken over two calibration fields, namely, Dengfeng (Henan Province) and Tianjin. Evaluation experiments were performed using ZY-3 multispectral images and ground control points (GCPs) collected over several different periods and areas. The positioning accuracy of the ZY-3 multispectral images with a limited number of GCPs after calibration of the interior orientation was better than 0.3 pixels, and the band-to-band registration accuracy was up to 0.15 pixels.

Geometric Calibration and Accuracy Assessment of ZiYuan-3 Multispectral Images

The ZiYuan-3 surveying satellite (ZY-3), launched on 9th January 2012, is China's first civilian high-resolution stereo mapping satellite. To ensure the mapping accuracy of ZY-3, considerable research has been conducted since its launch on the calibration and validation of its three-line array charge-coupled device (CCD) sensors (TLC sensors). Its dynamic exterior systematic errors (such as camera installation errors) and static interior distortion were eliminated using 1:2000 digital orthophotomaps and digital elevation models (DEMs) of the Dengfeng (Henan) and Tianjin areas of China as control data. Various CCD alignment calibration models were compared, on the basis of their geometric accuracy after calibration, to determine the optimal model. Finally, validation experiments were performed using ZY-3 TLC images and ground control points (GCPs) collected over Anping in Hebei Province, Zhaodong in Heilongjiang Province and the Taihang Mountain area in China. The positioning accuracy attained its theoretical value over the Anping and Zhaodong areas. Using GCPs whose image coordinates were obtained manually, the plan and height accuracy were found to be better than 3 m and 2 m, respectively.

Resume

Le satellite d'observation ZiYuan-3 (ZY-3), lance le 9 janvier 2012, est le premier satellite civil chinois dedie a la cartographie stereoscopique a haute resolution. Pour permettre la precision cartographique de ZY-3, d'importantes recherches ont ete conduites depuis son lancement en vue d’etalonner et valider son capteur TLC (capteur a 3 barrettes de detecteurs CCD). Ses erreurs systematiques externes dynamiques (comme le defaut de montage de la camera) et les distorsions internes statiques ont ete eliminees en utilisant comme donnees de controle des ortho-images numeriques et des modeles numeriques d’elevation (MNE) des regions de Dengfeng, Henan et Tianjin, en Chine. Plusieurs modeles d’etalonnage de l'alignement des CCD ont ete compares en termes d'exactitude geometrique apres etalonnage, afin de determiner le modele optimal. Enfin, des experimentations ont ete menees dans un but de validation en utilisant des images TLC de ZY-3 et des points d'appui sur les sites de Anping (province de Hebei), de Zhaodong (province de Heilongjiang) et des monts Taihang, en Chine. L'exactitude de localisation s'est averee comparable aux previsions theoriques sur les sites de Anping et Zhaodong. L'utilisation de points d'appui avec des coordonnees image determinees manuellement permet d'obtenir des exactitudes planimetrique et altimetrique meilleures que 3 et 12 m, respectivement.

Zusammenfassung

Der ZiYuan-3 Vermessungssatellit (ZY-3), der am 9. Januar 2012 gestartet wurde, ist der erste zivile chinesische Satellit fur hochauflosende Kartierung aus Stereobilddaten. Seit dem Start des Satelliten wurden intensive Forschungsaktivitaten unternommen, um die Kalibrierung und Validierung der 3-Zeilenkamera mit CCD Sensoren (TLC) durchzufuhren. Die dynamischen systematischen Fehler der auseren Orientierung wurden mittels Digitalen Orthobildkarten im Masstab 1:2000 und Digitalen Gelandemodellen (DEMs) in den Regionen Dengfeng, Henan, and Tianjin in China ermittelt. Verschiedene Kalibrier-Methoden fur die Ausrichtung der CCDs wurden untersucht, um mittels den erzielten geometrischen Genauigkeiten nach der Kalibrierung das optimale Modell zu finden. Die Validierung erfolgte nach der Kalibrierung der ZY-3 TLC Bilder mittels Passpunkten, die im Gebiet Anping in der Hebei Province, in Zhaodong in der Heilongjiang Proviz und im Taihang Gebirge in China bestimmt wurden. Die empirische Lagegenauigkeit erreichte den theoretischen Wert in den Gebieten Anping und Zhaodong. Mit manuell gemessenen Passpunkten in den Bilddaten konnte eine Lage- und Hohengenauigkeit von 3 bzw. 2 m erreicht werden.

Resumen

El ZiYuan3 (ZY-3) es el primer satelite civil de China estereoscopico de alta resolucion lanzado el 9 de Enero de 2012. Para garantizar la precision del ZY-3 se han invertido grandes esfuerzos en la calibracion y validacion de sus tres sensores lineales CCD (charge-coupled devices): sensores TLC. Los errores sistematicos que afectan la orientacion exterior (tales como el error en la instalacion de la camara) y las distorsiones de la orientacion interior se eliminaron usando, como datos de referencia y control, ortofotomapas digitales a escala 1:2000 y modelos de elevacion digitales (MEDs) de las areas Dengfeng, Henan y Tianjin en China. Se comparan diferentes modelos de calibracion de la alineacion de los CCDs basandonos en la precision geometrica tras aplicar la calibracion. Finalmente se han llevado a termino experimentos de validacion usando imagenes del ZY-3 y puntos de control en Anping en la provincia de Hebei, en Zhaodong en la provincia de Heilongjiang y en el area de la montana de Taihang en China. Usando los puntos de control capturados manualmente en las imagenes se han obtenido precisiones en planimetria y altimetria mejores que 3 y 2 m respectivamente.

摘要

资源三号测绘卫星发射于2012年1月9日,是中国第一颗民用高分辨率立体测绘卫星。为保障资源三号卫星立体测图精度,发射以来针对资源三号三线阵相机开展了系列在轨几何检校及精度验证工作。采用河南区域、天津区域1:2000的数字正射影像、数字高程模型(DEM)作为控制数据,对资源三号三线阵相机动态外参数误差(载荷安装误差等)、静态内参数误差(相机畸变)进行了在轨几何检校,采用各种内方位元素模型进行在轨几何检校的精度对比,确定了适用于资源三号在轨几何检校的最优内方位元素模型。采用河北安平区域、肇东区域的高精度靶标控制点进行立体平差验证,立体定位精度达到理论极限精度;采用太行山区域的外业GPS控制点进行大区域立体平差验证,平面精度优于3m、高程精度优于2m。

In‐Orbit Geometric Calibration And Validation Of Zy‐3 Linear Array Sensors

The ZiYuan-3 surveying satellite (ZY-3) is a high-precision civilian satellite imaging sensor. Since its launch on January 9, 2012, it has been in operation for one and a half years. Although the initial postlaunch ZY-3 geometric accuracy was verified during an in-orbit operation period, on-orbit calibration was still necessary from time to time. This on-orbit calibration has vastly improved the location accuracy in planimetry for ZY-3 panchromatic images. This letter briefly describes the principle of on-orbit calibration and production processes of sensor-corrected products. Furthermore, block adjustment based on a rational function model test showed planimetric and vertical accuracy values of 10 m and 5 m, respectively, without ground control points (GCPs). The accuracy values improved to 3 m and 2 m, respectively, with a few GCPs. The statistics results are from ten different regions with independent checkpoints (ICPs). All accuracy values are the root-mean-square error of ICPs. Therefore, ZY-3 can be used for the generation of cartographic maps at the 1 : 50 000 scale and for revision and updates of 1 : 25 000 scale maps. Compared with other mainstream high-resolution satellite images of the same ground resolution, ZY-3's geometric accuracy is almost the same and sometimes even better.

Geometric Accuracy Validation for ZY-3 Satellite Imagery

A low Earth orbiter (LEO)-based navigation signal augmentation system is considered as a complementary of current global navigation satellite systems (GNSS), which can accelerate precise positioning convergence, strengthen the signal power, and improve signal quality. Wuhan University is dedicated to LEO-based navigation signal augmentation research and launched one scientific experimental satellite named Luojia-1A. The satellite is capable of broadcasting dual-frequency band ranging signals over China. The initial performance of the Luojia-1A satellite navigation augmentation system is assessed in this study. The ground tests indicate that the phase noise of the oscillator is sufficiently low to support the intended applications. The field ranging tests achieve 2.6 m and 0.013 m ranging precision for the pseudorange and carrier phase measurements, respectively. The in-orbit test shows that the internal precision of the ephemeris is approximate 0.1 m and the clock stability is 3 × 10−10. The pseudorange and carrier phase measurement noise evaluated from the geometry-free combination is about 3.3 m and 1.8 cm. Overall, the Luojia-1A navigation augmentation system is capable of providing useable LEO navigation augmentation signals with the empirical user equivalent ranging error (UERE) no worse than 3.6 m, which can be integrated with existing GNSS to improve the real-time navigation performance.

Guo Zhang

Papers

Geometric Calibration and Accuracy Assessment of ZiYuan-3 Multispectral Images

In‐Orbit Geometric Calibration And Validation Of Zy‐3 Linear Array Sensors

Geometric Accuracy Validation for ZY-3 Satellite Imagery

Initial Assessment of the LEO Based Navigation Signal Augmentation System from Luojia-1A Satellite.

Basic Products of the ZiYuan-3 Satellite and Accuracy Evaluation