Abstract
Due to the diversity of the shape and texture of flame, and interference objects that similar to flame in color, detecting the position of flame from images is a difficult task. To enable generic object detection methods to achieve better performance in flame detection tasks, a color-guided anchoring strategy is proposed that uses color features of the flame to limit the location of the anchor. To solve the problem of high false alarm rate when directly using generic object detection methods in flame detection, a global information-guided flame detection method is proposed, this strategy uses a parallel network to generate image global information. We use these two methods to improve Faster R-CNN (Regions with Convolutional Neural Network features) to perform the fire detection process in a guided manner. Experiments on the BoWFire dataset show that our method improved detection speed by 10.1% compared with the original Faster R-CNN. In addition, the false alarm rate is decreased by 21.5%, and the overall accuracy of detection is increased by 9.3%. Experiments on PascalVOC and Corsician datasets further demonstrate the robustness of the proposed methods.
Highlights
Every year, fire causes enormous damage to human society
Our experiments indicate that the colorguided anchoring strategy can improve the flame detection speed of Faster R-convolutional neural network (CNN) by 10.1%, and the use of global information can reduce the false alarm rate by 20% compared with the original Faster R-CNN
The first method is a novel color-guided anchoring strategy, which is an easy-to-implement method to improve the efficiency of Faster R-CNN in flame detection
Summary
Fire causes enormous damage to human society. Forest fires take the lives of many firefighters, causing serious impacts on the local environment and ecology. The multi-class object detection method of Faster R-CNN [6] is improved for the single-class flame detection task based on two aspects. We use the image characteristics of the flame itself to guide the anchoring process, instead of using the original dense anchoring strategy, thereby improving the efficiency and accuracy of flame detection. The Faster R-CNN is trained by local image patterns, it cannot fully understand the global information of the image To solve this problem, we propose a flame detection method guided by the global information of the image provided by a parallel CNN. The global information is combined with the detection result of the Faster R-CNN to generate the final detection result, which efficiently reduces the false alarm rate. One is a color-guided deep model using a sparse anchoring strategy to improve efficiency, and the other is a color + global information guided deep model using additional global information to reduce the false alarm rate. (2) The original Faster R-CNN is used for benchmark. (3) The annotation files for two public datasets are prepared
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
