A Deep Learning Approach to Vegetation Images Recognition in Buildings: a Hyperparameter Tuning Case Study
- 12 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 19 (12), 2062-2070
- https://doi.org/10.1109/tla.2021.9480148
Abstract
Deep Learning methods have important applications in digital image processing. However, the literature lacks further studies that propose machine learning models to images classification in civil construction area. For example, the vegetation recognition on facades can be relevant in identifying the degradation and abandonment of buildings. Thus, the objective of this paper is to propose an Convolutional Neural Networks (CNN) approach to vegetation images recognition in buildings. For this, a database with urban images (low altitude) captured by a drone in Zurich (Switzerland) was adopted. In addition, a rigorous hyperparameters tuning methodology for the CNN model is presented. After adjusting the hyperparameters and the final model, the system achieved 90% of accuracy in the test stage. It should also be noted that CNN correctly classified 97.8% of the positive class (with vegetation on the facade) in test images.Keywords
This publication has 21 references indexed in Scilit:
- Performance Analysis of Different Optimizers for Deep Learning-Based Image RecognitionInternational Journal of Pattern Recognition and Artificial Intelligence, 2019
- DETECTION OF BUILDING ROOFS AND FACADES FROM AERIAL LASER SCANNING DATA USING DEEP LEARNINGThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2019
- Automated Machine LearningPublished by Springer Science and Business Media LLC ,2019
- Evaluation of CNNs for land cover classification in high-resolution airborne imagesPublished by SPIE-Intl Soc Optical Eng ,2018
- Building Extraction From LiDAR Data Applying Deep Convolutional Neural NetworksIEEE Geoscience and Remote Sensing Letters, 2018
- Tomato crop disease classification using pre-trained deep learning algorithmProcedia Computer Science, 2018
- Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced SegmentationsLecture Notes in Computer Science, 2017
- The Zurich urban micro aerial vehicle datasetThe International Journal of Robotics Research, 2017
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural NetworksRemote Sensing, 2016