3 OPISTESTNEGA PROJEKTA RAF V letu 2022 smo na Gursu podprli izvedbo projekta »Poševno aero fotografiranj e - test«, katerega predmet naročila je bila izvedba poševnega aerofotografiranja (PAF) za ...pridobitev aerofotografij treh različnih geometrijskih ločljivosti na treh različnih testnih lokacijah v Sloveniji. Rezultat zajema aerofotografij in GNSS/ INS meritev so: natančni parametri zunanje orientacije aerofotografij, digitalni model površja (DMP), popolni ortofoto (POF), 3D mreža (angl. 3D meshY izdelana pa je bila tudi aplikacija za pregledovanje in izvajanje osnovnih meritev na poševnih aerofotografijah. Fotografiranje Ljubljane se je izvajalo z različico PAS880İ, ki ima v sistem dodan tudi NIR fotoaparat z ločljivostjo 150 MP. Sistem za zajem fotografij je bil nameščen na letalo, kot je prikazano na sliki 3, kjer je tudi skica smeri in oblike zajetih fotografij. 4 IZDELKI TESTNEGA PROJEKTA Uporabniku naj zanimivejši izdelki testnega projekta so: orientirane poševne aero fotografij e, digitalni model površja, popolni ortofoto, 3D mreža ter aplikacija za pregledovanje in 3D merjenje. S slike jerazvidno, da poševne aerofortografije ponujajo veliko boljšo prostorsko in semantično predstavo o izbrani stavbi, kot bi jo omogočale zgolj nadirne aerofotografije. 4.2 Digitalni model višin (DMV) Za prikaz višinskih podatkov površja Zemlje običajno uporabljamo digitalni model višin (DMV), ki se deli na dva tipa: digitalni model reliefa (DMR), ki modelira teren, in digitalni model površja (DMP), ki modelira površje.
Vse aerofotografije, ki niso bile izdelane v okviru projekta CAS, so del tako imenovanega posebnega aerofotografiranja Slovenije (PAS). Osnovni izdelek so bile aerofotografije s parametri zunanje ...orientacije, izračunane v procesu aerotriangulacije in narejene z dvema razli čnima nominalnima dolžinama talnega intervala (DTI), in sicer z DTI 25 centimetrov za območja, obarvana v modro, in z DTI 50 centimetrov za območja, ki so obarvana svetleje (glej sliko 2). Skupaj je bilo v letu 2006 zajetih 10.341 barvnih aerofotografij, ki so bile orientirane v procesu aerotriangulacije (Klanjšček in sod., 2007). Ločljivosti digitalnih aerofotoaparatov se je zaradi napredka razvoja tehnologije s 104 megapikslov (MP, angl. megapixel) povečala na 136 MP (tretjina aerofotografij tega cikla CAS) oziroma 196 MP (dve tretjini aerofotografij tega cikla CAS).
Abstract
In order to solve the problems of large number, small size and low detection accuracy of vehicle targets in aerial photography, a target detection algorithm based on improved YOLOv3 is ...proposed in this paper. Firstly, aiming at the problem of small target information loss of road vehicles, a new detection size is added.Secondly, in order to better detect small targets, a 104x104 scale detection layer is added on the basis of the three detection layers of the traditional yolov3 network structure.The k-means + + algorithm is used to cluster the data set, and a new ground target detection candidate frame is obtained. The loss function is improved by using Focal loss function in the classification loss function and using DIoUloss function based on IoUloss improvement in the regression loss function.The improved YOLOv3 algorithm can identify the road vehicle target more accurately without the decline of speed, and reduce the miss rate. The improved algorithm is tested on Visdrone dataset, and the experimental data show that the average accuracy of the improved algorithm is 94.04%, and the average detection accuracy (mAP) is improved by 2.94%.The detection accuracy of the proposed improved YOLOv3 algorithm is better than that of YOLOv3.
On Dec. 22, 2018, at approximately 20:55-57 local time, Anak Krakatau volcano, located in the Sunda Straits of Indonesia, experienced a major lateral collapse during a period of eruptive activity ...that began in June. The collapse discharged volcaniclastic material into the 250 m deep caldera southwest of the volcano, which generated a tsunami with runups of up to 13 m on the adjacent coasts of Sumatra and Java. The tsunami caused at least 437 fatalities, the greatest number from a volcanically-induced tsunami since the catastrophic explosive eruption of Krakatau in 1883 and the sector collapse of Ritter Island in 1888. For the first time in over 100 years, the 2018 Anak Krakatau event provides an opportunity to study a major volcanically-generated tsunami that caused widespread loss of life and significant damage. Here, we present numerical simulations of the tsunami, with state-of the-art numerical models, based on a combined landslide-source and bathymetric dataset. We constrain the geometry and magnitude of the landslide source through analyses of pre- and post-event satellite images and aerial photography, which demonstrate that the primary landslide scar bisected the Anak Krakatau volcano, cutting behind the central vent and removing 50% of its subaerial extent. Estimated submarine collapse geometries result in a primary landslide volume range of 0.22-0.30 km
, which is used to initialize a tsunami generation and propagation model with two different landslide rheologies (granular and fluid). Observations of a single tsunami, with no subsequent waves, are consistent with our interpretation of landslide failure in a rapid, single phase of movement rather than a more piecemeal process, generating a tsunami which reached nearby coastlines within ~30 minutes. Both modelled rheologies successfully reproduce observed tsunami characteristics from post-event field survey results, tide gauge records, and eyewitness reports, suggesting our estimated landslide volume range is appropriate. This event highlights the significant hazard posed by relatively small-scale lateral volcanic collapses, which can occur en-masse, without any precursory signals, and are an efficient and unpredictable tsunami source. Our successful simulations demonstrate that current numerical models can accurately forecast tsunami hazards from these events. In cases such as Anak Krakatau's, the absence of precursory warning signals together with the short travel time following tsunami initiation present a major challenge for mitigating tsunami coastal impact.
Changes to vegetation structure and composition in forests adapted to frequent fire have been well documented. However, little is known about changes to the spatial characteristics of vegetation in ...these forests. Specifically, patch sizes and detailed information linking vegetation type to specific locations and growing conditions on the landscape are lacking. We used historical and recent aerial imagery to characterize historical vegetation patterns and assess contemporary change from those patterns. We created an orthorectified mosaic of aerial photographs from 1941 covering approximately 100,000 ha in the northern Sierra Nevada. The historical imagery, along with contemporary aerial imagery from 2005, was segmented into homogenous vegetation patches and classified into four relative cover classes using random forests analysis. A generalized linear mixed model was used to compare topographic associations of dense forest cover on the historical and contemporary landscapes. The amount of dense forest cover increased from 30 to 43% from 1941 to 2005, replacing moderate forest cover as the most dominant class. Concurrent with the increase in extent, the area-weighted mean patch size of dense forest cover increased tenfold, indicating greater continuity of dense forest cover and more homogenous vegetation patterns across the contemporary landscape. Historically, dense forest cover was rare on southwesterly aspects, but in the contemporary forest, it was common across a broad range of aspects. Despite the challenges of processing historical air photographs, the unique information they provide on landscape vegetation patterns makes them a valuable source of reference information for forests impacted by past management practices.
Digital ortho quarter quad tiles of NAIP imagery were downloaded from the USDA Farm Service Agency's (FSA) Aerial Photography Field Office (APFO) (i.e. http://apfo.usda.gov/).
Land cover (LC) and land use (LU) have commonly been classified separately from remotely sensed imagery, without considering the intrinsically hierarchical and nested relationships between them. In ...this paper, for the first time, a highly novel Joint Deep Learning framework is proposed and demonstrated for LC and LU classification. The proposed Joint Deep Learning (JDL) model incorporates a multilayer perceptron (MLP) and convolutional neural network (CNN), and is implemented via a Markov process involving iterative updating. In the JDL, LU classification conducted by the CNN is made conditional upon the LC probabilities predicted by the MLP. In turn, those LU probabilities together with the original imagery are re-used as inputs to the MLP to strengthen the spatial and spectral feature representations. This process of updating the MLP and CNN forms a joint distribution, where both LC and LU are classified simultaneously through iteration. The proposed JDL method provides a general framework within which the pixel-based MLP and the patch-based CNN provide mutually complementary information to each other, such that both are refined in the classification process through iteration. Given the well-known complexities associated with the classification of very fine spatial resolution (VFSR) imagery, the effectiveness of the proposed JDL was tested on aerial photography of two large urban and suburban areas in Great Britain (Southampton and Manchester). The JDL consistently demonstrated greatly increased accuracies with increasing iteration, not only for the LU classification, but for both the LC and LU classifications, achieving by far the greatest accuracies for each at around 10 iterations. The average overall classification accuracies were 90.18% for LC and 87.92% for LU for the two study sites, far higher than the initial accuracies and consistently outperforming benchmark comparators (three each for LC and LU classification). This research, thus, represents the first attempt to unify the remote sensing classification of LC (state; what is there?) and LU (function; what is going on there?), where previously each had been considered separately only. It, thus, has the potential to transform the way that LC and LU classification is undertaken in future. Moreover, it paves the way to address effectively the complex tasks of classifying LC and LU from VFSR remotely sensed imagery via joint reinforcement, and in an automatic manner.
•Joint Deep Learning (JDL) was first proposed for land cover and land use classification.•JDL incorporated patch-based CNN and pixel-based MLP with joint reinforcement and mutual complementarity.•The joint distributions between LC and LU were formulated into a Markov process through iterative updating.•Increased accuracies were achieved for both LC and LU in an automatic fashion with iteration.•The JDL framework is readily generalisable to hierarchical representations at multiple levels and scales.
PDF
