Abstract
In this paper, we propose a deep convolutional neural network for camera based wildfire detection. We train the neural network via transfer learning and use window based analysis strategy to increase the fire detection rate. To achieve computational efficiency, we calculate frequency response of the kernels in convolutional and dense layers and eliminate those filters with low energy impulse response. Moreover, to reduce the storage for edge devices, we compare the convolutional kernels in Fourier domain and discard similar filters using the cosine similarity measure in the frequency domain. We test the performance of the neural network with a variety of wildfire video clips and the pruned system performs as good as the regular network in daytime wild fire detection, and it also works well on some night wild fire video clips.
Highlights
Wildfire detection is of utmost importance to combat the unprecedented scale of wildfires happening all over the world
In this work, we propose to use transfer learning from MobileNet-V2 [36] for forest fire detection
We prune and slim the convolutional and dense layers according to frequency response of kernels using Fourier analysis in order to accelerate the inference of the neural network and save storage
Summary
Wildfire detection is of utmost importance to combat the unprecedented scale of wildfires happening all over the world. Transfer learning is a very efficient method and it is widely used in recognition tasks because of its advantage that we only need to train only the final several layers instead of the whole network. We prune and slim the convolutional and dense layers according to frequency response of kernels using Fourier analysis in order to accelerate the inference of the neural network and save storage. After testing the performance on daytime surveillance and obtaining a very good result, we further tested our system system with night events, and it works on many video clips
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
