A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Detection of Landslide Based on Convolutional Neural Networks
Human activities are one of the main causes of geological disasters. From the perspective of visual observation, the degree of environmental damage can be reflected by detecting the exposed area of vegetation in the image along the road. In order to verify the applicability of the deep learning method in the detection of landslide, the EfficientDet model is applied to objects detection. This objects detection model is based on convolutional neural networks. A data set of landslide is established. The training samples are marked by labelme software. The object detection of landslide is carried out by EfficientDet model. The result of Precision, Recall, F1, AP, Average training time of each epoch (s) and FPS are 0.8158, 0.3240, 0.46, 0.5132, 27.17s, 12.2, respectively. The method can detect landslide objects well.
Detection of Landslide Based on Convolutional Neural Networks
Human activities are one of the main causes of geological disasters. From the perspective of visual observation, the degree of environmental damage can be reflected by detecting the exposed area of vegetation in the image along the road. In order to verify the applicability of the deep learning method in the detection of landslide, the EfficientDet model is applied to objects detection. This objects detection model is based on convolutional neural networks. A data set of landslide is established. The training samples are marked by labelme software. The object detection of landslide is carried out by EfficientDet model. The result of Precision, Recall, F1, AP, Average training time of each epoch (s) and FPS are 0.8158, 0.3240, 0.46, 0.5132, 27.17s, 12.2, respectively. The method can detect landslide objects well.
Detection of Landslide Based on Convolutional Neural Networks
Zhang, Heng (author) / Chen, Xiaohu (author) / Song, Zhizhong (author) / Zhan, Weijie (author) / Lei, Huiguang (author)
2022-11-25
5229402 byte
Conference paper
Electronic Resource
English
Comparative analysis of five convolutional neural networks for landslide susceptibility assessment
| Online Contents | 2023
Convolutional neural networks based droplet detection method
| Wiley | 2022
Landslide displacement prediction by using Bayesian optimization–temporal convolutional networks
| Springer Verlag | 2024
Landslide displacement prediction by using Bayesian optimization–temporal convolutional networks
| Springer Verlag | 2024