Next Article in Journal
K-Band Low Phase Noise VCO Based on Q-Boosted Switched Inductor
Next Article in Special Issue
Real-Time Object Detection in Remote Sensing Images Based on Visual Perception and Memory Reasoning
Previous Article in Journal
A New Quadratic Binary Harris Hawk Optimization for Feature Selection
Previous Article in Special Issue
Efficient Implementation of 2D and 3D Sparse Deconvolutional Neural Networks with a Uniform Architecture on FPGAs
Open AccessArticle

Detection of Wildfire Smoke Images Based on a Densely Dilated Convolutional Network

by Tingting Li 1,2, Enting Zhao 1,2, Junguo Zhang 1,2,* and Chunhe Hu 1,2,*
1
School of Technology, Beijing Forestry University, Beijing 100083, China
2
Key Lab of State Forestry and Grassland Administration for Forestry Equipment and Automation, Beijing 100083, China
*
Authors to whom correspondence should be addressed.
Electronics 2019, 8(10), 1131; https://doi.org/10.3390/electronics8101131
Received: 29 August 2019 / Revised: 3 October 2019 / Accepted: 5 October 2019 / Published: 7 October 2019
Recently, many researchers have attempted to use convolutional neural networks (CNNs) for wildfire smoke detection. However, the application of CNNs in wildfire smoke detection still faces several issues, e.g., the high false-alarm rate of detection and the imbalance of training data. To address these issues, we propose a novel framework integrating conventional methods into CNN for wildfire smoke detection, which consisted of a candidate smoke region segmentation strategy and an advanced network architecture, namely wildfire smoke dilated DenseNet (WSDD-Net). Candidate smoke region segmentation removed the complex backgrounds of the wildfire smoke images. The proposed WSDD-Net achieved multi-scale feature extraction by combining dilated convolutions with dense block. In order to solve the problem of the dataset imbalance, an improved cross entropy loss function, namely balanced cross entropy (BCE), was used instead of the original cross entropy loss function in the training process. The proposed WSDD-Net was evaluated according to two smoke datasets, i.e., WS and Yuan, and achieved a high AR (99.20%) and a low FAR (0.24%). The experimental results demonstrated that the proposed framework had better detection capabilities under different negative sample interferences.
Keywords: wildfire smoke detection; CNN; DenseNet; dense block; candidate smoke region; dilated convolution; cross entropy loss wildfire smoke detection; CNN; DenseNet; dense block; candidate smoke region; dilated convolution; cross entropy loss
MDPI and ACS Style

Li, T.; Zhao, E.; Zhang, J.; Hu, C. Detection of Wildfire Smoke Images Based on a Densely Dilated Convolutional Network. Electronics 2019, 8, 1131.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop