Research on flame classification and recognition based on object detection and similarity fusion

doi:10.19682/j.cnki.1005-8885.2021.0020

中国邮电高校学报(英文版) ›› 2021, Vol. 28 ›› Issue (5): 59-67.doi: 10.19682/j.cnki.1005-8885.2021.0020

• Artificial Intelligence • 上一篇下一篇

Research on flame classification and recognition based on object detection and similarity fusion

何欣¹,周军华²,廖中华²,翟翔²,孙司远¹

1. 北京邮电大学
2.

收稿日期:2020-09-21 修回日期:2020-12-23 出版日期:2021-10-31 发布日期:2021-10-29
通讯作者: 何欣 E-mail:hexin_cynthia@bupt.edu.cn
基金资助:
可编程绿色边缘网络架构及智能资源优化研究

Research on flame classification and recognition based on object detection and similarity fusion

Received:2020-09-21 Revised:2020-12-23 Online:2021-10-31 Published:2021-10-29
Contact: Xin HE E-mail:hexin_cynthia@bupt.edu.cn

摘要/Abstract

摘要：

The color, shape, and other appearance characteristics of the flame emitted by different flame engines are different. In order to make a preliminary judgment on the category of the device to which it belongs through studying exterior characteristics of the flame, this paper uses the flame of matches, lighters, and candles to simulate different types of flames. It is hoped that the flames can be located and classified by detecting the characteristics of flames using the object detection algorithm. First, different types of fire are collected for the dataset of experiments. The mmDetection toolbox is then used to build several different object detection frameworks, in which the dataset can be trained and tested. The object detection model suitable for this kind of problem is obtained through the evaluation index analysis. The model is ResNet50-based faster-region-convolutional neural network ( Faster R- CNN), whose mean average-precision ( mAP) is 93.6% . Besides, after clipping the detected flames through object detection, a similarity fusion algorithm is used to aggregate and classify the three types of flames. Finally, the color components are analyzed to obtain the red, green, blue ( RGB) color histograms of the three flames.

关键词:

flame classification, object detection, similarity fusion

Abstract:

Key words:

flame classification, object detection, similarity fusion

参考文献

1. Chen E J, Tang X H, Fu B W. A modified pedestrian retrieval method based on Faster R-CNN with integration of pedestrian detection and re-identification. Proceedings of the 2018 International Conference on Audio, Language and Image Processing ( ICALIP’18), 2018, Jul 16 - 17, Shanghai, China. Piscataway, NJ, USA: IEEE, 2018: 63 - 66

2. Winarno E, Hadikurniawati W, Al Amin I H, et al. Anti-cheating presence system based on 3WPCA-dual vision face recognition. Proceedings of the 4th International Conference on Electrical Engineering, Computer Science and Informatics ( EECSI’17 ), 2017, Sept 19 - 21, Yogyakarta, Indonesia. Piscataway, NJ, USA: IEEE, 2017: 1 - 5

3. Masuda S, Kaeri Y, Manabe Y, et al. Scene recognition method by bag of objects based on object detector. Proceedings of the 2018 Joint 10th International Conference on Soft Computing and Intelligent Systems ( SCIS’18 ) and 19th International Symposium on Advanced Intelligent Systems ( ISIS’18 ), 2018, Dec 5 - 8, Toyama, Japan. Piscataway, NJ, USA: IEEE, 2018: 321 - 324

4. Yu N G, Chen Y. Video flame detection method based on two- stream convolutional neural network. Proceedings of the IEEE 8th Joint International Information Technology and Artificial Intelligence Conference ( ITAIC’19 ), 2019, May 24 - 26, Chongqing, China. Piscataway, NJ, USA: IEEE, 2019: 482 - 486

5. Liu Y Y. Design and implementation of recognition algorithm based on four-band infrared flame detector. Proceedings of the 2018 Chinese Control and Decision Conference ( CCDC’18), 2018, Jun 9 - 11, Shenyang, China. Piscataway, NJ, USA: IEEE, 2018: 5639 - 5643

6. Han T, Lin B W. Research on flame image recognition method in natural scene. Proceedings of the 2016 IEEE International Conference on Information and Automation ( ICIA’16), 2016, Aug 1 - 3, Ningbo, China. Piscataway, NJ, USA: IEEE, 2016: 1776 - 1780

7. Ouyang J N, Bu L P, Yang Z K, et al. An early flame identification method based on edge gradient feature. Proceedings of the 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference ( IMCEC’18 ), 2018, May 25 - 27, Xi’an, China. Piscataway, NJ, USA: IEEE, 2018: 642 - 646

8. Chung Y L, Chung H Y, Chou C W. Efficient flame recognition method based on a deep convolutional neural network and image processing. Proceedings of the IEEE 8th Global Conference on Consumer Electronics ( GCCE’19 ), 2019, Oct 15 - 18, Osaka, Japan, Piscataway, NJ, USA: IEEE, 2019: 573 - 574

9. Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137 - 1149

10. Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318 - 327

11. Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector. Proceedings of the 14th European Conference on Computer Vision ( ECCV’16 ), 2016, Oct 8 - 16, Amsterdam, Netherlands. LNCS 9905. Berlin, Germany: Springer, 2016: 21 - 37

12. Rublee E, Rabaud V, Konolige K, et al. ORB: an efficient alternative to SIFT or SURF. Proceedings of the 2011 International Conference on Computer vision, 2011, Nov 6 - 13, Barcelona, Spain. Piscataway, NJ, USA: IEEE, 2011: 2564 - 2571

13. Rosten E, Drummond T. Machine learning for high-speed corner detection. Proceedings of the 9th European Conference on Computer Vision ( ECCV’06 ): Part I, 2006, May 7 - 13, Graz, Austria. LNCS 3951. Berlin, Germany: Springer, 2006: 430 - 443

14. Calonder M, Lepetit V, Strecha C, et al. BRIEF: binary robust independent elementary features. Proceedings of the 9th European Conference on Computer Vision ( ECCV’10): Part IV, 2010, Sept 5 - 11, Heraklion, Greece. LNCS 6314. Berlin, Germany: Springer, 2010: 778 - 792

Research on flame classification and recognition based on object detection and similarity fusion

Research on flame classification and recognition based on object detection and similarity fusion

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价