BoucaNet: A CNN-Transformer for Smoke Recognition on Remote Sensing Satellite Images

• Published in: Fire (Basel, Switzerland) Vol. 6; no. 12; p. 455
• Main Authors: Ghali, Rafik, Akhloufi, Moulay A.
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2023
• Subjects: Accuracy; BoucaNet; Codes; Datasets; Deep learning; Dust; False alarms; Fire damage; Fire fighting; Fog; Forest & brush fires; Haze; Neural networks; Property damage; Remote sensing; Satellite imagery; satellite images; Smoke; smoke recognition; System effectiveness; Canada
• ISSN: 2571-6255; 2571-6255
• DOI: 10.3390/fire6120455

Fire accidents cause alarming damage. They result in the loss of human lives, damage to property, and significant financial losses. Early fire ignition detection systems, particularly smoke detection systems, play a crucial role in enabling effective firefighting efforts. In this paper, a novel DL (Deep Learning) method, namely BoucaNet, is introduced for recognizing smoke on satellite images while addressing the associated challenging limitations. BoucaNet combines the strengths of the deep CNN EfficientNet v2 and the vision transformer EfficientFormer v2 for identifying smoke, cloud, haze, dust, land, and seaside classes. Extensive results demonstrate that BoucaNet achieved high performance, with an accuracy of 93.67%, an F1-score of 93.64%, and an inference time of 0.16 seconds compared with baseline methods. BoucaNet also showed a robust ability to overcome challenges, including complex backgrounds; detecting small smoke zones; handling varying smoke features such as size, shape, and color; and handling visual similarities between smoke, clouds, dust, and haze.