Fully Synthetic Videos and the Random-Background-Pasting Method for Flame Segmentation
Video-based flame detection (VFD) aims to recognize fire events by using image features. Flame segmentation is an essential task in VFD, providing suspected regions for feature analysis and object recognition. However, the lack of positive flame samples makes it difficult to train deep-learning-base...
Main Authors: | Yang Jia, Zixu Mao, Xinmeng Zhang, Yaxi Kuang, Yanping Chen, Qixing Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/11/2492 |
Similar Items
-
SIMPL: Generating Synthetic Overhead Imagery to Address Custom Zero-Shot and Few-Shot Detection Problems
by: Yang Xu, et al.
Published: (2022-01-01) -
Background memory-assisted zero-shot video object segmentation for unmanned aerial and ground vehicles
by: Kimin Yun, et al.
Published: (2023-10-01) -
Background subtraction for night videos
by: Hongpeng Pan, et al.
Published: (2021-06-01) -
FlameTransNet: Advancing Forest Flame Segmentation with Fusion and Augmentation Techniques
by: Beiqi Chen, et al.
Published: (2023-09-01) -
Preparation of Flame-Retardant Polyurethane and Its Applications in the Leather Industry
by: Shaolin Lu, et al.
Published: (2021-05-01)