Abstract | ||
---|---|---|
Most existing works in fire detection literature use available detectors like Faster RCNN, SSD, YOLO, etc. to localize the fire in images. These approaches work well but require object-level annotation for training, which is created manually and is very expensive. In this paper, we explore the weakly supervised fire detection task (WSFD) in which only the image-level annotation is given. We propose an approach based on class activation map (CAM). The CAM-based approach firstly trains a deep neural network as the classifier for identifying fire and non-fire images. For a fire image in the inference stage, it uses the classifier to create a CAM and then further generates the bounding boxes according to the CAM. To evaluate the effectiveness of our approach, we collect and construct a benchmark dataset named WS-FireNet and conduct comprehensive experiments on it. The experiment results show that in a way the performance of our approach is satisfactory. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICEBE52470.2021.00035 | 2021 IEEE International Conference on e-Business Engineering (ICEBE) |
Keywords | DocType | ISBN |
Weakly Supervised,Fire Detection,CAM,Deep Neural Network | Conference | 978-1-6654-4419-4 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lvlong Lai | 1 | 0 | 0.68 |
Jian Chen | 2 | 42 | 8.66 |
Huichou Huang | 3 | 1 | 2.04 |
Wu Qingyao | 4 | 259 | 33.46 |