Uzaktan algılanan görüntülerde bina yoğunluğu kestirimi için derin öğrenme
Yükleniyor...
Dosyalar
Tarih
2019-09
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Institute of Electrical and Electronics Engineers Inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Bu bildiri, derin öğrenme yöntemleri uygulayarak uzaktan algılamalı optik görüntülerde bina yoğunluğunun noktasal olarak kestirilmesi ile ilgilidir. Bu çalışma kapsamında, evrişimsel sinir ağına (ESA) dayalı derin öğrenme yöntemlerine başvurulmuştur. Önceden eğitilmiş, VGG-16 ve FCN-8s derin mimarileri bu probleme uyarlanmış ve ince ayar verilerek eğitilmiştir. Kestirilen değerler yerleşim bölgelerinde bina yoğunluk haritası oluşturmak için kullanılmıştır. Her iki mimarinin karşılaştırmalı benzetim sonuçları, güdümlü eğitim için binaları gösteren detaylı haritalara ihtiyaç duyulmadan hassas yoğunluk kestirimi yapılabileceğini göstermektedir.
This paper is about point-wise estimation of building density from remote sensing optical imagery using deep learning methods. Convolutional neural network (CNN) based deep learning approaches are used for this work. Pre-trained VGG-16 and FCN-8s deep architectures are adapted to the problem and fine-tuned with additional training. Estimated values are used to generate building heat maps in urban areas. Comparative simulation results of the two architectures reveal that accurate density estimation is possible without the need for detailed maps of building locations during supervised training.
This paper is about point-wise estimation of building density from remote sensing optical imagery using deep learning methods. Convolutional neural network (CNN) based deep learning approaches are used for this work. Pre-trained VGG-16 and FCN-8s deep architectures are adapted to the problem and fine-tuned with additional training. Estimated values are used to generate building heat maps in urban areas. Comparative simulation results of the two architectures reveal that accurate density estimation is possible without the need for detailed maps of building locations during supervised training.
Açıklama
Anahtar Kelimeler
Bina yoğunluk kestirimi, Derin öğrenme, Uzaktan algılama, Accurate density estimation, Additional training, Building density estimation, Building heat maps, Building locations, Building densities, Buildings, CNN, Comparative simulation, Comparative simulation results, Convolution, Convolutional network, Convolutional neural nets, Convolutional neural network, Deep architectures, Deep learning, Deep learning approaches, Deep learning methods, Density estimation, Geophysical image processing, Learning (artificial intelligence), Learning approach, Network architecture, Neural networks, Optical images, Point-wise estimation, Pre-trained VGG-16, Remote sensing, Remote sensing optical imagery, Remotely sensed imagery, Supervised training, Supervised trainings, Time 8.0 s
Kaynak
2019 4th International Conference on Computer Science and Engineering (UBMK)
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
Cilt
Sayı
Künye
Suberk, N. T. & Ateş, H. F. (2019). Deep learning for building density estimation in remotely sensed imagery. Paper presented at the 423-428. doi:10.1109/UBMK.2019.8907133
