{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:34:29Z","timestamp":1781109269833,"version":"3.54.1"},"reference-count":36,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T00:00:00Z","timestamp":1675814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Sichuan Science and Technology Program","award":["2023YFG0320"],"award-info":[{"award-number":["2023YFG0320"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Forest fires can destroy forest and inflict great damage to the ecosystem. Fortunately, forest fire detection with video has achieved remarkable results in enabling timely and accurate fire warnings. However, the traditional forest fire detection method relies heavily on artificially designed features; CNN-based methods require a large number of parameters. In addition, forest fire detection is easily disturbed by fog. To solve these issues, a lightweight YOLOX-L and defogging algorithm-based forest fire detection method, GXLD, is proposed. GXLD uses the dark channel prior to defog the image to obtain a fog-free image. After the lightweight improvement of YOLOX-L by GhostNet, depth separable convolution, and SENet, we obtain the YOLOX-L-Light and use it to detect the forest fire in the fog-free image. To evaluate the performance of YOLOX-L-Light and GXLD, mean average precision (mAP) was used to evaluate the detection accuracy, and network parameters were used to evaluate the lightweight effect. Experiments on our forest fire dataset show that the number of the parameters of YOLOX-L-Light decreased by 92.6%, and the mAP increased by 1.96%. The mAP of GXLD is 87.47%, which is 2.46% higher than that of YOLOX-L; and the average fps of GXLD is 26.33 when the input image size is 1280 \u00d7 720. Even in a foggy environment, the GXLD can detect a forest fire in real time with a high accuracy, target confidence, and target integrity. This research proposes a lightweight forest fire detection method (GXLD) with fog removal. Therefore, GXLD can detect a forest fire with a high accuracy in real time. The proposed GXLD has the advantages of defogging, a high target confidence, and a high target integrity, which makes it more suitable for the development of a modern forest fire video detection system.<\/jats:p>","DOI":"10.3390\/s23041894","type":"journal-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T04:21:59Z","timestamp":1675830119000},"page":"1894","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Real-Time Forest Fire Detection by Ensemble Lightweight YOLOX-L and Defogging Method"],"prefix":"10.3390","volume":"23","author":[{"given":"Jiarun","family":"Huang","sequence":"first","affiliation":[{"name":"School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhili","family":"He","sequence":"additional","affiliation":[{"name":"Glasgow College, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwei","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3530-5333","authenticated-orcid":false,"given":"Hongguo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1007\/s11676-017-0383-x","article-title":"The impact of climate change on fire risk in Daxing\u2019anling, China","volume":"28","author":"Tian","year":"2017","journal-title":"J. For. Res."},{"key":"ref_2","unstructured":"(2022, March 23). Management, Fire and Rescue Department Ministry of Emergency, The Emergency Management Department Released the Basic Information of National Natural Disasters in 2021, Available online: https:\/\/www.119.gov.cn\/gk\/sjtj\/2022\/26527.shtml."},{"key":"ref_3","first-page":"1","article-title":"Forest fire risk zone mapping from satellite imagery and GIS","volume":"4","author":"Rajeev","year":"2002","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_4","first-page":"7024","article-title":"Forest fire monitoring using wireless sensor networks\u2014A survey","volume":"6","author":"Ali","year":"2016","journal-title":"Int. J. Electrochem. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Karagianni, A., and Lazaridou, M. (2017, January 20\u201323). Remote sensing techniques in monitoring areas affected by forest fire. Proceedings of the 5th International Conference on Remote Sensing and Geoinformation of the Environment (RSCy), Paphos, Cyprus.","DOI":"10.1117\/12.2277700"},{"key":"ref_6","first-page":"303","article-title":"Video smoke detection: A literature survey","volume":"23","author":"Shi","year":"2018","journal-title":"J. Image Graph."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zheng, X., Chen, F., Lou, L., Cheng, P., and Huang, Y. (2022). Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network. Remote Sens., 14.","DOI":"10.3390\/rs14030536"},{"key":"ref_8","first-page":"41","article-title":"Analysis of invulnerability of wireless fire-alarming network and methods of improving it","volume":"24","author":"Fu","year":"2014","journal-title":"China Saf. Ence J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"105346","DOI":"10.1016\/j.ssci.2021.105346","article-title":"Planning remote sensing emergency services: Bridging the gap between remote sensing science and emergency practice in China","volume":"141","author":"Zheng","year":"2021","journal-title":"Saf. Sci."},{"key":"ref_10","first-page":"40","article-title":"Video based fire detection systems on forest and wildland using convolutional neural network","volume":"36","author":"Philippe","year":"2019","journal-title":"J. Donghua Univ. (Engl. Ed.)"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Tao, C., Zhang, J., and Wang, P. (2016, January 3\u20134). Smoke detection based on deep convolutional neural networks. Proceedings of the 2016 International Conference on Industrial Informatics\u2014Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII), Wuhan, China.","DOI":"10.1109\/ICIICII.2016.0045"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"18174","DOI":"10.1109\/ACCESS.2018.2812835","article-title":"Convolutional neural networks based fire detection in surveillance videos","volume":"6","author":"Muhammad","year":"2018","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Filonenko, A., Kurnianggoro, L., and Jo, K. (2017, January 17\u201319). Comparative study of modern convolutional neural networks for smoke detection on image data. Proceedings of the 10th International Conference on Human System Interactions (HSI), Ulsan, Republic of Korea.","DOI":"10.1109\/HSI.2017.8004998"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Dunnings, A., and Breckon, T. (2018, January 7\u201310). Experimentally defined convolutional neural network architecture variants for non-temporal real-time fire detection. Proceedings of the 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece.","DOI":"10.1109\/ICIP.2018.8451657"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"18429","DOI":"10.1109\/ACCESS.2017.2747399","article-title":"A deep normalization and convolutional neural network for image smoke detection","volume":"5","author":"Yin","year":"2017","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Han, S., Farfard, A., Kerekes, J., Gartley, M., Lentilucci, E., Savakis, A., Law, C., Parhan, J., Turek, M., and Fieldhouse, K. (2017, January 10\u201311). Efficient generation of image chips for training deep learning networks. Proceedings of the Conference on Automatic Target Recognition XXVII, Anaheim, CA, USA.","DOI":"10.1117\/12.2261702"},{"key":"ref_17","unstructured":"Information Center of State Forestry Administration of China (2016). Technical Code for Video Monitoring System of Forest Fire Prevention, State Forestry Administration of China. LY\/T 2581-2016."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jiang, W., and Lv, S. (2020, January 22). Inference acceleration model of branched neural network based on distributed deployment in fog computing. Proceedings of the Lecture Notes in Computer Science, Guangzhou, China.","DOI":"10.1007\/978-3-030-60029-7_45"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.1109\/LGRS.2019.2951626","article-title":"A color enhancement scene estimation approach for single image haze removal","volume":"17","author":"Dharejo","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2610","DOI":"10.1109\/JSTARS.2020.2998517","article-title":"A Novel UAV Sensing Image Defogging Method","volume":"13","author":"Gao","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_21","unstructured":"(2022, January 23). Administration, National Forestry and Grassland, Seven Typical Cases of Forest Fire Notified to Alert, Available online: http:\/\/www.forestry.gov.cn\/slga\/4596\/20220323\/093002638499145.html."},{"key":"ref_22","unstructured":"(2021, October 14). Science, National Laboratory of Fire, University of Science and Technology of China. Available online: http:\/\/smoke.ustc.edu.cn\/datasets.htm."},{"key":"ref_23","unstructured":"(2021, October 13). VisFire, Bilkent EE Signal Processing Group. Available online: http:\/\/signal.ee.bilkent.edu.tr\/VisiFire\/Demo\/."},{"key":"ref_24","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). YOLOX: Exceeding YOLO series in 2021. arXiv."},{"key":"ref_25","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (May, January 30). mixup: Beyond empirical risk minimization. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_26","unstructured":"Bochkovskiy, A., Wang, C., and Liao, H. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_27","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., and Xu, C. (2020, January 14\u201319). GhostNet: More features from cheap operations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Electr Network, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (2019, January 27). Searching for MobileNetV3. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., and Berg, A. (2016, January 8\u201316). SSD: Single shot multiBox detector. Proceedings of the 14th European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_31","first-page":"1098","article-title":"Target detection based on bidirectional feature fusion and attention mechanism","volume":"16","author":"Zhao","year":"2021","journal-title":"Intell. Syst."},{"key":"ref_32","unstructured":"Fa, B., Yin, Y., and Fu, C. (2009, January 20\u201322). The bidirectional associative memory neural network based on fault tree and its application to inverter\u2019s fault diagnosis. Proceedings of the IEEE International Conference on Intelligent Computing & Intelligent Systems, Shanghai, China."},{"key":"ref_33","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, L., and Polosukhin, I. (2017, January 4). Attention is all you need. Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhong, X., Gong, O., Huang, W., Li, L., and Xia, H. (2019, January 22\u201325). Squeeze-and-excitation wide residual networks in image classification. Proceedings of the 26th IEEE International Conference on Image Processing (ICIP), Taipei, China.","DOI":"10.1109\/ICIP.2019.8803000"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1109\/TPAMI.2010.168","article-title":"Single image haze removal using dark channel prior","volume":"33","author":"He","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Fan, R., and Pei, M. (2021, January 25\u201328). Lightweight Forest Fire Detection Based on Deep Learning. Proceedings of the IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), Eelctr Network, Gold Coast, Australia.","DOI":"10.1109\/MLSP52302.2021.9596409"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/4\/1894\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:28:00Z","timestamp":1760120880000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/4\/1894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,8]]},"references-count":36,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["s23041894"],"URL":"https:\/\/doi.org\/10.3390\/s23041894","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,8]]}}}