TY - GEN
T1 - Automatic Desert/Mountain Detection from Satellite Image Using Deep Transfer Learning
AU - Kadry, Seifedine
AU - Prudhvi, Mareedu Naga
AU - Narayanan, Mathiyazhagan
AU - Rajinikanth, Venkatesan
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - Satellite image (SI) supported earth observation and environmental monitoring is one of the prime tasks. Recently, the artificial intelligence (AI)-based SI examination is widely discussed in the literature. This research aims to develop a DL-technique to detect desert and mountain from the chosen SI database. Various stages in this DL-approach includes; image collection and resizing, feature extraction using a chosen DL-model, feature reduction and serial features concatenation, classification, and implementing threefold cross validation to confirm the performance. In this work, the DenseNet-variants-based approach is considered to extract the image features and then a 50% feature reduction is executed to reduce the deep features. The reduced deep features from two chose models are integrated serially to get a new feature vector, and this feature vector is then considered to detect the desert/mountain from the chosen SI-data. The outcome of this comparison confirms that the proposed approach provides 100% accuracy when Random Forest (RF)-based classification is executed.
AB - Satellite image (SI) supported earth observation and environmental monitoring is one of the prime tasks. Recently, the artificial intelligence (AI)-based SI examination is widely discussed in the literature. This research aims to develop a DL-technique to detect desert and mountain from the chosen SI database. Various stages in this DL-approach includes; image collection and resizing, feature extraction using a chosen DL-model, feature reduction and serial features concatenation, classification, and implementing threefold cross validation to confirm the performance. In this work, the DenseNet-variants-based approach is considered to extract the image features and then a 50% feature reduction is executed to reduce the deep features. The reduced deep features from two chose models are integrated serially to get a new feature vector, and this feature vector is then considered to detect the desert/mountain from the chosen SI-data. The outcome of this comparison confirms that the proposed approach provides 100% accuracy when Random Forest (RF)-based classification is executed.
KW - Classification
KW - DenseNet
KW - Fusion
KW - Land
KW - Satellite image
UR - https://www.scopus.com/pages/publications/105011264151
U2 - 10.1007/978-981-96-5223-5_14
DO - 10.1007/978-981-96-5223-5_14
M3 - Conference contribution
AN - SCOPUS:105011264151
SN - 9789819652228
T3 - Lecture Notes in Networks and Systems
SP - 161
EP - 169
BT - Innovations in Communication Networks
A2 - Bhateja, Vikrant
A2 - Abdul Hameed, Vazeerudeen
A2 - Udgata, Siba K.
A2 - Azar, Ahmad Taher
PB - Springer Science and Business Media Deutschland GmbH
T2 - 5th International Conference on Data Engineering and Communication Technology, ICDECT 2024
Y2 - 28 September 2024 through 29 September 2024
ER -