Storm-Drain and Manhole Detection Using the RetinaNet Method
Open Access
- 10 August 2020
- Vol. 20 (16), 4450
- https://doi.org/10.3390/s20164450
Abstract
As key-components of the urban-drainage system, storm-drains and manholes are essential to the hydrological modeling of urban basins. Accurately mapping of these objects can help to improve the storm-drain systems for the prevention and mitigation of urban floods. Novel Deep Learning (DL) methods have been proposed to aid the mapping of these urban features. The main aim of this paper is to evaluate the state-of-the-art object detection method RetinaNet to identify storm-drain and manhole in urban areas in street-level RGB images. The experimental assessment was performed using 297 mobile mapping images captured in 2019 in the streets in six regions in Campo Grande city, located in Mato Grosso do Sul state, Brazil. Two configurations of training, validation, and test images were considered. ResNet-50 and ResNet-101 were adopted in the experimental assessment as the two distinct feature extractor networks (i.e., backbones) for the RetinaNet method. The results were compared with the Faster R-CNN method. The results showed a higher detection accuracy when using RetinaNet with ResNet-50. In conclusion, the assessed DL method is adequate to detect storm-drain and manhole from mobile mapping RGB images, outperforming the Faster R-CNN method. The labeled dataset used in this study is available for future research.Keywords
This publication has 24 references indexed in Scilit:
- Deep learning for smart manufacturing: Methods and applicationsJournal of Manufacturing Systems, 2018
- An integrated assessment of urban flooding mitigation strategies for robust decision makingEnvironmental Modelling & Software, 2017
- Feature Pyramid Networks for Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Modeling flood reduction effects of low impact development at a watershed scaleJournal of Environmental Management, 2016
- Deep learning for visual understanding: A reviewNeurocomputing, 2016
- Detection of Manhole Covers in High-Resolution Aerial Images of Urban Areas by Combining Two MethodsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Automated Extraction of Urban Road Facilities Using Mobile Laser Scanning DataIEEE Transactions on Intelligent Transportation Systems, 2015
- Automated Detection of Road Manhole and Sewer Well Covers From Mobile LiDAR Point CloudsIEEE Geoscience and Remote Sensing Letters, 2014
- Impacts of impervious surface on watershed hydrology: A reviewUrban Water Journal, 2005