YOLO-SF: YOLO for Fire Segmentation Detection

• Published in: IEEE access Vol. 11; pp. 111079 - 111092
• Main Authors: Cao, Xianghong, Su, Yixuan, Geng, Xin, Wang, Yongdong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; CBAM; Computational modeling; Computer networks; Feature extraction; Fire detection; Fires; Image color analysis; Image enhancement; Image segmentation; Instance segmentation; MobileViTv2; Model accuracy; Modules; Object detection; Object recognition; Spatial data; varifocal loss

Owing to the problems of missed detection, false detection, and low accuracy of the current fire detection algorithm, a segmentation detection algorithm, YOLO-SF, is proposed. This algorithm combines instance segmentation technology with the YOLOv7-Tiny object detection algorithm to improve its accu...