{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:50:27Z","timestamp":1775681427752,"version":"3.50.1"},"reference-count":38,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T00:00:00Z","timestamp":1519689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>An unmanned aerial vehicle (UAV) equipped with global positioning systems (GPS) can provide direct georeferenced imagery, mapping an area with high resolution. So far, the major difficulty in wildfire image classification is the lack of unified identification marks, the fire features of color, shape, texture (smoke, flame, or both) and background can vary significantly from one scene to another. Deep learning (e.g., DCNN for Deep Convolutional Neural Network) is very effective in high-level feature learning, however, a substantial amount of training images dataset is obligatory in optimizing its weights value and coefficients. In this work, we proposed a new saliency detection algorithm for fast location and segmentation of core fire area in aerial images. As the proposed method can effectively avoid feature loss caused by direct resizing; it is used in data augmentation and formation of a standard fire image dataset \u2018UAV_Fire\u2019. A 15-layered self-learning DCNN architecture named \u2018Fire_Net\u2019 is then presented as a self-learning fire feature exactor and classifier. We evaluated different architectures and several key parameters (drop out ratio, batch size, etc.) of the DCNN model regarding its validation accuracy. The proposed architecture outperformed previous methods by achieving an overall accuracy of 98%. Furthermore, \u2018Fire_Net\u2019 guarantied an average processing speed of 41.5 ms per image for real-time wildfire inspection. To demonstrate its practical utility, Fire_Net is tested on 40 sampled images in wildfire news reports and all of them have been accurately identified.<\/jats:p>","DOI":"10.3390\/s18030712","type":"journal-article","created":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T14:18:08Z","timestamp":1519741088000},"page":"712","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":173,"title":["Saliency Detection and Deep Learning-Based Wildfire Identification in UAV Imagery"],"prefix":"10.3390","volume":"18","author":[{"given":"Yi","family":"Zhao","sequence":"first","affiliation":[{"name":"AInML Lab, School of Electronics and Control Engineering, Chang\u2019an University, Xi\u2019an 710064, China"}]},{"given":"Jiale","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing 210009, China"}]},{"given":"Xiaohui","family":"Li","sequence":"additional","affiliation":[{"name":"AInML Lab, School of Electronics and Control Engineering, Chang\u2019an University, Xi\u2019an 710064, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5879-9351","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shengyao Intelligence Technology Co. Ltd., Shanghai 201112, China"}]}],"member":"1968","published-online":{"date-parts":[[2018,2,27]]},"reference":[{"key":"ref_1","first-page":"205","article-title":"Integrated System for Forest Fire Early Detection and Management","volume":"110","author":"Skala","year":"2008","journal-title":"Period. Biol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.isprsjprs.2014.02.013","article-title":"Unmanned aerial systems for photogrammetry and remote sensing: A review","volume":"92","author":"Colomina","year":"2014","journal-title":"ISPRS J. Photogramm."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Li, X., Zhao, Y., and Zhang, J. (2016, January 6\u20138). A Hybrid PSO Algorithm Based Flight Path Optimization for Multiple Agricultural UAVs. Proceedings of the International Conference on TOOLS with Artificial Intelligence, San Jose, CA, USA.","DOI":"10.1109\/ICTAI.2016.0110"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Trasvi\u00f1amoreno, C.A., Blasco, R., Marco, \u00c1., Casas, R., and Trasvi\u00f1acastro, A. (2017). Unmanned Aerial Vehicle Based Wireless Sensor Network for Marine-Coastal Environment Monitoring. Sensors, 17.","DOI":"10.3390\/s17030460"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Gonzalez, L.F., Montes, G., Puig, E., Johnson, S., Mengersen, K., and Gaston, K.J. (2016). Unmanned Aerial Vehicles (UAVs) and Artificial Intelligence Revolutionizing Wildlife Monitoring and Conservation. Sensors, 16.","DOI":"10.3390\/s16010097"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3557","DOI":"10.3390\/s8053557","article-title":"Assessment of Unmanned Aerial Vehicles Imagery for Quantitative Monitoring of Wheat Crop in Small Plots","volume":"8","author":"Lelong","year":"2008","journal-title":"Sensors"},{"key":"ref_7","first-page":"169","article-title":"Forest Fire Modeling and Early Detection using Wireless Sensor Networks","volume":"7","author":"Hefeeda","year":"2009","journal-title":"Ad Hoc Sens. Wirel. Netw."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1540","DOI":"10.1016\/j.rse.2009.03.004","article-title":"Characterizing boreal forest wildfire with multi-temporal landsat and lidar data","volume":"113","author":"Wulder","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3057","DOI":"10.1080\/01431160050144956","article-title":"Satellite detection of Canadian boreal forest fires: Development and application of the algorithm","volume":"21","author":"Li","year":"2000","journal-title":"Int. J. Remote Sens."},{"key":"ref_10","first-page":"745806","article-title":"Development of the Compact InfraRed Camera (CIRC) for wildfire detection","volume":"8","author":"Katayama","year":"2009","journal-title":"SPIE Opt. Eng. Appl."},{"key":"ref_11","unstructured":"Jakovcevic, T., Braovic, M., Stipanicev, D., and Krstinic, D. (2011, January 4\u20136). Review of wildfire smoke detection techniques based on visible spectrum video analysis. Proceedings of the International Symposium on Image & Signal Processing & Analysis, Dubrovnik, Croatia."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1827","DOI":"10.1016\/j.dsp.2013.07.003","article-title":"Video fire detection\u2014Review","volume":"23","author":"Dimitropoulos","year":"2013","journal-title":"Digit. Signal Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"527","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"ref_14","first-page":"87","article-title":"Image processing based forest fire detection","volume":"2","author":"Vipin","year":"2012","journal-title":"Int. J. Emerg. Technol. Adv. Eng."},{"key":"ref_15","first-page":"202","article-title":"An Intelligent System for Effective Forest Fire Detection Using Spatial Data","volume":"7","author":"Angayarkkani","year":"2010","journal-title":"Int. J. Comput. Sci. Inf. Secur."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yuan, C., Liu, Z., and Zhang, Y. (2015, January 9\u201312). UAV-based forest fire detection and tracking using image processing techniques. Proceedings of the International Conference on Unmanned Aircraft Systems IEEE, Denver, CO, USA.","DOI":"10.1109\/ICUAS.2015.7152345"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.patrec.2005.06.015","article-title":"Computer vision based method for real-time fire and flame detection","volume":"27","author":"Cetin","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.firesaf.2008.07.006","article-title":"Fire detection based on vision sensor and support vector machines","volume":"44","author":"Byoung","year":"2009","journal-title":"Fire Saf. J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1064","DOI":"10.1049\/iet-ipr.2014.0935","article-title":"Benchmarking of wildland fire colour segmentation algorithms","volume":"9","author":"Toulouse","year":"2015","journal-title":"Image Process. IET"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23\u201328). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1139\/cjfr-2014-0347","article-title":"A survey on technologies for automatic forest fire monitoring, detection","volume":"45","author":"Yuan","year":"2015","journal-title":"Can. J. For. Res."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kim, S., Lee, W., Park, Y.S., Lee, H.W., and Lee, Y.T. (2017, January 13\u201315). Forest fire monitoring system based on aerial image. Proceedings of the International Conference on Information and Communication Technologies for Disaster Management, Vienna, Austria.","DOI":"10.1109\/ICT-DM.2016.7857214"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"He","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision IEEE, San Tiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_25","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20138). ImageNet classification with deep convolutional neural networks. Proceedings of the International Conference on Neural Information Processing Systems, Lake Tahoe, CA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Rahtu, E. (2010, January 5\u201311). Segmenting Salient Objects from Images and Videos. Proceedings of the 11th European Conference on Computer Vision, Heraklion, Greece.","DOI":"10.1007\/978-3-642-15555-0_27"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shellamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. (2014, January 3\u20137). Caffe: Convolutional Architecture for Fast Feature Embedding. Proceedings of the ACM International Conference on Multimedia, Orlando, FL, USA.","DOI":"10.1145\/2647868.2654889"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Huang, Z.C., Chan, P.P.K., Ng, W.W.Y., and Yeung, D.S. (2010, January 11\u201314). Content-based image retrieval using color moment and Gabor texture feature. Proceedings of the International Conference on Machine Learning and Cybernetics, Qingdao, China.","DOI":"10.1109\/ICMLC.2010.5580566"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2668","DOI":"10.1016\/j.asoc.2012.11.020","article-title":"Two fully-unsupervised methods for MR brain image segmentation using SOM-based strategies","volume":"13","author":"Ortiz","year":"2013","journal-title":"Appl. Soft Comput. J."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.isprsjprs.2013.10.003","article-title":"Automatic representation and reconstruction of DBM from LiDAR data using Recursive Minimum Bounding Rectangle","volume":"93","author":"Kwak","year":"2014","journal-title":"J. Photogramm. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","article-title":"A Model of Saliency-Based Visual Attention for Rapid Scene Analysis","volume":"20","author":"Itti","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhao, Y., and Li, X. (2016, January 15\u201317). Edge-Aware Weighting Enhanced Saliency Segmentation of Pests Images. Proceedings of the International Conference on Computational Science and Computational Intelligence IEEE, Las Vegas, NV, USA.","DOI":"10.1109\/CSCI.2016.0164"},{"key":"ref_33","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"Glorot","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_34","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201324). Rectified Linear Units Improve Restricted Boltzmann Machines. Proceedings of the International Conference on Machine Learning, Haifa, Israel."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Giusti, A., Dan, C.C., Masci, J., Gambardella, L.M., and Schmidhuber, J. (2013, January 15\u201318). Fast image scanning with deep max-pooling convolutional neural networks. Proceedings of the IEEE International Conference on Image Processing, Melbourne, Australia.","DOI":"10.1109\/ICIP.2013.6738831"},{"key":"ref_36","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"T\u00fcske, Z., Tahir, M.A., Schl\u00fcter, R., and Ney, H. (2015, January 19\u201324). Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Brisbane, Australia.","DOI":"10.1109\/ICASSP.2015.7178779"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/3\/712\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:56:42Z","timestamp":1760194602000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/3\/712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,27]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2018,3]]}},"alternative-id":["s18030712"],"URL":"https:\/\/doi.org\/10.3390\/s18030712","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,27]]}}}