Sökning: id:"swepub:oai:DiVA.org:mdh-56384" >
Deep Learning in Re...
Deep Learning in Remote Sensing : An Application to Detect Snow and Water in Construction Sites
-
- Rahman, Hamidur, Doctoral Student, 1984- (författare)
- Mälardalens högskola,Inbyggda system
-
- Ahmed, Mobyen Uddin, Dr, 1976- (författare)
- Mälardalens högskola,Inbyggda system
-
- Begum, Shahina, 1977- (författare)
- Mälardalens högskola,Inbyggda system
-
visa fler...
-
- Fridberg, Mats (författare)
- Mälardalens högskola
-
- Hoflin, Adam (författare)
- Mälardalens högskola
-
visa färre...
-
(creator_code:org_t)
- 2021
- 2021
- Engelska.
-
Ingår i: Proceedings - 2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021. - 9781665434102 ; , s. 52-56
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- It is important for a construction and property development company to know weather conditions in their daily operation. In this paper, a deep learning-based approach is investigated to detect snow and rain conditions in construction sites using drone imagery. A Convolutional Neural Network (CNN) is developed for the feature extraction and performing classification on those features using machine learning (ML) algorithms. Well-known existing deep learning algorithms AlexNet and VGG16 models are also deployed and tested on the dataset. Results show that smaller CNN architecture with three convolutional layers was sufficient at extracting relevant features to the classification task at hand compared to the larger state-of-the-art architectures. The proposed model reached a top accuracy of 97.3% in binary classification and 96.5% while also taking rain conditions into consideration. It was also found that ML algorithms,i.e., support vector machine (SVM), logistic regression and k-nearest neighbors could be used as classifiers using feature maps extracted from CNNs and a top accuracy of 90% was obtained using SVM algorithms.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Support vector machines;Deep learning;Training;Rain;Machine learning algorithms;Snow;Feature extraction;Classification;deep learning;convolutional neural networks
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas