Segmentation is one of the most popular classification techniques which still have semantic labels. In this context, the segmentation of different objects such as cars, airplanes, ships, and buildings that are independent of background and objects such as land use and vegetation classes, which are difficult to discriminate from the background is considered. However, in image segmentation studies, various difficulties such as shadow, image blockage, a disorder of background, lighting, shading that cause fundamental modifications in the appearance of features are often encountered. With the development of technology, obtaining high spatial resolution satellite imageries and aerial photographs contain detailed texture information have been facilitated easily. Parallel to these improvements, deep learning architectures have widely been used to solved several computer vision tasks with an increasing level of difficulty. Thus, the regional characteristics, artificial and natural objects, can be perceived and interpreted precisely. In this study, two different subset data that were produced from a great open-source labeled image sets were used to segmentation of roads. The used labeled data set consists of 150 satellite images of size 1500 x 1500 pixels at a 1.2 m resolution, which was not efficient for training. In order to avoid any problem, the imageries were divided into smaller dimensions. Selected images from the data set divided into small patches of 256 x 256 pixels and 512 x 512 pixels to train the system, and comparisons between them were carried out. To train the system using these datasets, two different artificial neural network architectures U-Net and Fully Convolutional Networks (FCN), which are used for object segmentation on high-resolution images, were selected. When the test data with the same size as the training data set were analyzed, approximately 97% extraction accuracy was obtained from high-resolution imageries trained by FCN in 512 x 512 dimensions.
Özİnsansız Hava Araçları (İHA) otomatik veya yarı otomatik uçuş prensibine sahip başlangıçta askeri amaçlar için kullanılan motorlu veya motorsuz hava araçlarıdır. Son yıllarda meydana gelen gelişmelerle birlikte İHA'lar, afet yönetimi ve planlama, ormancılık, fotogrametrik değerlendirme, yol ve nehir gözlemleri, arazilerin üç boyutlu (3B) modellerinin üretilmesi gibi birçok ticari ve akademik çalışmalarda yaygın olarak kullanılmaya başlanmıştır. İHA'lara digital kameralarının entegre edilmesi yüksek çözünürlükte görüntülerin elde edilmesini sağlamıştır. Bu görüntülerin değerlendirilmesi zor ve zaman alıcı olmasına rağmen dijital fotogrametri ile birlikte bu sorun ortadan kalkmakta ve objenin veya arazinin 3 boyutlu(3B) yoğun nokta bulutu, sayısal yüzey modeli (SYM) ve ortogörüntüleri üretilebilmektedir. Bu çalışmada İTÜ Ayazağa Kampüsünde, 60m, 80m ve 100m yüksekliklerinde uçuşlar gerçekleştirilerek 60m ve 80m yükseklikte 90°, 100m yükseklikte 45°, 60° ve 90° kamera açıları ile yüksek çözünürlüklü sayısal görüntüler elde edilerek alanın ortogörüntüleri üretilmiştir. Daha sonra çalışma alanında jeodezik yöntemler kullanılarak önceden tesis edilmiş 5 adet yer kontrol noktası ile ortogörüntülerin doğrulukları test edilmiştir. Ayrıca, farklı yüksekliklerin ve aynı yükseklikte farklı kamera açılarından üretilen ortogörüntünün doğruluk irdelemesi gerçekleştirilmiştir. Anahtar Kelimeler: İnsansız Hava Aracı (İHA), OrtoGörüntü, Eğik Fotogrametri, Dijital Fotogrametri The Investigation of The Height and The Camera Angle in The Production of Orthoimage with Images of Unmanned Aerial Vehicle (UAV)Abstract Unmanned Aerial Vehicles (UAV) are motorized or non-motorized aerial vehicle with an automatic or semiautomatic flight principle. Firstly, UAV's were used for military purposes. Along with the developments in recent years, UAV's have been widely used in many commercial and scientific studies such as disaster management and planning, forestry, photogrammetric assessment, road and river observations and the production of 3D models of land or object. High-resolution images can be obtained with the integration of digital cameras into UAV's. Although image processing is difficult and time-consuming, digital photogrammetry alleviates this problem and can produce 3D dense point cloud, Digital Surface Model (DSM) and orthoimages. In this study, ortoimage was obtained from high resolution digital images which taken using 90° camera angles at 60 and 80-meter altitude and 45°, 60° and 90° camera angles at 100-meter altitude in Istanbul Technical University Ayazağa campus. Subsequently, using geodetic methods, accuracy of ortoimages were tested via 5 ground control points which established before study. Also, effect of different altitude and camera angles at same altitude on accuracy of ortoimages were invastigated.
Numerous deep learning techniques have been explored in pursuit of achieving precise road segmentation; nonetheless, this task continues to present a significant challenge. Exposing shadows and the obstruction of objects are the most important difficulties associated with road segmentation using optical image data alone. By incorporating additional data sources, such as LiDAR data, the accuracy of road segmentation can be improved in areas where optical images are insufficient to segment roads properly. The missing information in spectral data due to the object blockage and shadow effect can be compensated by the integration of 2D and 3D information. This study proposes a feature-wise fusion strategy of optical images and point clouds to enhance the road segmentation performance of a deep learning model. For this purpose, high-resolution satellite images and airborne LiDAR point cloud collected over Florida, USA, were used. Eigenvalue-based and geometric 3D property-based features were calculated based on the LiDAR data. These optical images and LiDAR-based features were used together to train, end-to-end, a deep residual U-Net architecture. In this strategy, the high-level features generated from optical images were concatenated with the LiDAR-based features before the final convolution layer. The consistency of the proposed strategy was evaluated using ResNet backbones with a different number of layers. According to the obtained results, the proposed fusion strategy improved the prediction capacity of the U-Net models with different ResNet backbones. Regardless of the backbone, all models showed enhancement in prediction statistics by 1% to 5%. The combination of optical images and LiDAR point cloud in the deep learning model has increased the prediction performance and provided the integrity of road geometry in woodland and shadowed areas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.