Semi-supervised wildfire smoke detection based on smoke-aware consistency
Visualitza/Obre
Cita com:
hdl:2117/383725
Tipus de documentArticle
Data publicació2022-11-08
EditorFrontiers Media SA
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement 4.0 Internacional
Abstract
The semi-transparency property of smoke integrates it highly with the background contextual information in the image, which results in great visual differences in different areas. In addition, the limited annotation of smoke images from real forest scenarios brings more challenges for model training. In this paper, we design a semi-supervised learning strategy, named smokeaware consistency (SAC), to maintain pixel and context perceptual consistency in different backgrounds. Furthermore, we propose a smoke detection strategy with triple classification assistance for smoke and smoke-like object discrimination. Finally, we simplified the LFNet fire-smoke detection network to LFNet-v2, due to the proposed SAC and triple classification assistance that can perform the functions of some specific module. The extensive experiments validate that the proposed method significantly outperforms state-of-the-art object detection algorithms on wildfire smoke datasets and achieves satisfactory performance under challenging weather conditions.
CitacióWang, C. [et al.]. Semi-supervised wildfire smoke detection based on smoke-aware consistency. "Frontiers in plant science", 8 Novembre 2022, vol. 13, núm. 980425, p. 1-17.
ISSN1664-462X
Versió de l'editorfrontiersin.org/articles/10.3389/fpls.2022.980425/full
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
fpls-13-980425.pdf | 11,97Mb | Visualitza/Obre |