{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:46:04Z","timestamp":1776786364232,"version":"3.51.2"},"reference-count":64,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T00:00:00Z","timestamp":1666051200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2022,11,30]]},"abstract":"<jats:p>\n            Fire-related incidents continue to be reported as a leading cause of life and property destruction. Automated fire detection and localization (AFDL) systems have grown in importance with the evolution of applied robotics, especially because use of robots in disaster situations can lead to avoidance of human fatality. The importance of AFDL on resource-constrained devices has further grown, as most unmanned vehicles (drones or ground vehicles) are battery operated with limited computational capacity, the disaster situations cannot guarantee uninterrupted communication with high-end resources in the cloud, and yet faster response time is a prime necessity. Traditional computer vision\u2013based techniques require hand-engineered features on a case-by-case basis.\n            <jats:italic>Deep Learning<\/jats:italic>\n            \u2013based classifiers perform well for fire\/no-fire classification due to the availability of large datasets for training; however, a dearth of good fire localization datasets renders the localization performance below par. We have tried to address both problems with a multi-task learned cascaded model that triggers localization workflow only if the presence of fire is detected, through a strong classifier trained on available large fire datasets. This presents only fire images to a relatively weaker localization model, reducing false positives, false negatives, and thereby improving overall AFDL accuracy. The multi-task learning (MTL) approach for end-to-end training of a stitched classifier and object localizer model on diverse datasets enabled us to build a strong fire classifier and feature extractor. It also resulted in a single unified model, capable of running on \u201con-board\u201d compute infrastructure without compromising on accuracy.\n          <\/jats:p>\n          <jats:p>To achieve the target inference rate for the AFDL deployment, we have investigated the effect of quantization and compression due to hardware acceleration on an MTL model. This article presents an approach to automate the hardware-software co-design to find the optimum parameter partitioning for a given MTL problem, especially when some parts of the model are hardware accelerated. We present combined evaluation results showing that our methodology and the corresponding AFDL model strikes a balance between the frames inferred per second and several accuracy metrics. We report fire localization accuracy in terms of mean average precision (object detection), which has not been done earlier for embedded AFDL systems.<\/jats:p>","DOI":"10.1145\/3510027","type":"journal-article","created":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T18:01:53Z","timestamp":1643220113000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Accelerated Fire Detection and Localization at Edge"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5052-4476","authenticated-orcid":false,"given":"Arijit","family":"Mukherjee","sequence":"first","affiliation":[{"name":"TCS Research, Kolkata, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8809-494X","authenticated-orcid":false,"given":"Jayeeta","family":"Mondal","sequence":"additional","affiliation":[{"name":"TCS Research, Kolkata, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3988-1445","authenticated-orcid":false,"given":"Swarnava","family":"Dey","sequence":"additional","affiliation":[{"name":"TCS Research, Kolkata, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,18]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Marty Ahrens and Ben Evarts. 2020. Fire Loss in the United States During 2019. Retrieved from https:\/\/go.nfpa.org\/l\/14662\/2021-05-24\/8hkgts."},{"key":"e_1_3_2_3_2","unstructured":"Marty Ahrens and Birgitte Messerschmidt. 2021. Fire Safety in the United States since 1980. Retrieved from https:\/\/go.nfpa.org\/l\/14662\/2021-05-24\/8hkgts."},{"key":"e_1_3_2_4_2","first-page":"235\u2014243","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS\u201916)","author":"Bilen Hakan","year":"2016","unstructured":"Hakan Bilen and Andrea Vedaldi. 2016. Integrated perception with recurrent multi-task neural networks. In Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS\u201916). Curran Associates Inc., 235\u2014243."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2010.2045813"},{"key":"e_1_3_2_6_2","unstructured":"Ahrens Brushlinsky and Wagner Sokolov. 2021. World Fire Statistics Centre of Fire Statistics. Retrieved from https:\/\/ctif.org\/sites\/default\/files\/2021-06\/CTIF_Report26_KOREA.pdf."},{"key":"e_1_3_2_7_2","first-page":"213","volume-title":"Proceedings of the Brazilian Symposium on Databases (SBBD\u201917)","author":"Cazzolato Mirela T.","year":"2017","unstructured":"Mirela T. Cazzolato, L. P. Avalhais, D. Y. Chino, Jonathan S. Ramos, Jessica A. de Souza, Jose F. Rodrigues Jr, and A. J. Traina. 2017. Fismo: A compilation of datasets from emergency situations for fire and smoke analysis. In Proceedings of the Brazilian Symposium on Databases (SBBD\u201917). SBC, Brazil, 213\u2013223."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.firesaf.2008.05.005"},{"key":"e_1_3_2_9_2","first-page":"1707","volume-title":"Proceedings of the International Conference on Image Processing (ICIP\u201904)","volume":"3","author":"Chen Thou-Ho","year":"2004","unstructured":"Thou-Ho Chen, Ping-Hsueh Wu, and Yung-Chuen Chiou. 2004. An early fire-detection method based on image processing. In Proceedings of the International Conference on Image Processing (ICIP\u201904), Vol. 3. IEEE, Singapore, 1707\u20131710."},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Sumanth Chennupati Ganesh Sistu Senthil Yogamani and Samir A. Rawashdeh. 2019. Multinet++: Multi-stream feature aggregation and geometric loss strategy for multi-task learning. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . IEEE Computer Society USA 1200\u20131210.","DOI":"10.1109\/CVPRW.2019.00159"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2015.19"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11758-4_52"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2339592"},{"key":"e_1_3_2_14_2","unstructured":"Angela Fan Pierre Stock Benjamin Graham Edouard Grave R. Gribonval H. J\u00e9gou and Armand Joulin. 2020. Training with quantization noise for extreme model compression. arXiv:2004.07320. Retrieved from https:\/\/arxiv.org\/abs\/2004.07320."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2392531"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/1939171"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1048-0"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-011-0369-1"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_25"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8483118"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1602.07360"},{"key":"e_1_3_2_24_2","unstructured":"Intel. 2018. Intel Neural Compute Stick. Retrieved from https:\/\/software.intel.com\/en-us\/neural-compute-stick."},{"key":"e_1_3_2_25_2","unstructured":"Intel. 2021. Intel Distribution of OpenVino Toolkit. Retrieved from https:\/\/software.intel.com\/en-us\/openvino-toolkit."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_27_2","unstructured":"Arpit Jadon Mohd. Omama Akshay Varshney M. S. Ansari and Rishabh Sharma. 2019. FireNet: A specialized lightweight fire & smoke detection model for real-time iot applications. arXiv:1905.11922. Retrieved from https:\/\/arxiv.org\/abs\/1905.11922."},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Arpit Jadon Akshay Varshney and Mohammad Samar Ansari. 2020. Low-complexity high-performance deep learning model for real-time low-cost embedded fire detection systems. Procedia Computer Science 171 (2020) 418\u2013426. Third International Conference on Computing and Network Communications (CoCoNet\u201919) .","DOI":"10.1016\/j.procs.2020.04.044"},{"key":"e_1_3_2_29_2","volume-title":"Fire Detection Based on Convolutional Neural Networks","author":"Park Sung jae","year":"2019","unstructured":"Sung jae Park. 2019. Fire Detection Based on Convolutional Neural Networks. Technical Report. University of Minnesota."},{"key":"e_1_3_2_30_2","unstructured":"Yangqing Jia Evan Shelhamer Jeff Donahue Sergey Karayev Jonathan Long Ross Girshick Sergio Guadarrama and Trevor Darrell. 2014. Caffe: Convolutional Architecture for Fast Feature Embedding. In Proceedings of the 22nd ACM International Conference on Multimedia (Orlando Florida USA) (MM\u201914) . Association for Computing Machinery New York NY USA 675\u2013678."},{"key":"e_1_3_2_31_2","unstructured":"Norman P. Jouppi and Young. 2017. In-datacenter performance analysis of a tensor processing unit. In Proceedings of the 44th Annual International Symposium on Computer Architecture (Toronto ON Canada) (ISCA\u201917) . Association for Computing Machinery New York NY USA 1\u201312."},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Byoungjun Kim and Joonwhoan Lee. 2019. A video-based fire detection using deep learning models. Applied Sciences 9 14 (2019) 2862.","DOI":"10.3390\/app9142862"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"e_1_3_2_34_2","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1 (Lake Tahoe Nevada) (NIPS\u201912) . Curran Associates Inc. Red Hook NY USA 1097\u20131105."},{"key":"e_1_3_2_35_2","unstructured":"Chetan Kumar G. Suhas B. S. Abhishek Digvijay Gowda KA and R. Prajwal. 2020. Fire Detection Using Deep Learning. International Journal of Progressive Research in Science and Engineering 1 5 (2020) 1\u20135."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_37_2","first-page":"22","article-title":"Story of an eyewitness: The San Francisco earthquake","volume":"37","author":"London Jack","year":"1906","unstructured":"Jack London. 1906. Story of an eyewitness: The San Francisco earthquake. Collier\u2019s Week. 37 (1906), 22\u201326.","journal-title":"Collier\u2019s Week."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"e_1_3_2_39_2","unstructured":"The Mohamed Bin Zayed International Robotics Challenge (MBZIRC). 2020. The Challenge 2020. Retrieved July 14 2021 from https:\/\/www.mbzirc.com\/challenge\/2020."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Martin Mueller Peter Karasev Ivan Kolesov and Allen Tannenbaum. 2013. Optical flow estimation for flame detection in videos. IEEE Transactions on Image Processing 22 7 (2013) 2786\u20132797.","DOI":"10.1109\/TIP.2013.2258353"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.04.083"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2830099"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2812835"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2897594"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/VNIS.1994.396866"},{"key":"e_1_3_2_47_2","unstructured":"NVIDIA. 2020. Jetson Nano Developer Kit.Retrieved July 14 2021 from https:\/\/developer.nvidia.com\/embedded\/jetson-nano-developer-kit."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.3390\/app9010108"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCRD.2011.5764295"},{"key":"e_1_3_2_50_2","unstructured":"Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An incremental improvement. arXiv:1804.02767. Retrieved from https:\/\/arxiv.org\/abs\/1804.02767."},{"key":"e_1_3_2_51_2","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1 (Montreal Canada) (NIPS\u201915) . MIT Press Cambridge MA USA 91\u201399."},{"key":"e_1_3_2_52_2","unstructured":"Jay T. Petrillo Rita F. Fahy and Joseph L. Molis. 2020. Firefighter Fatalities in the US\u20142019. Retrieved from https:\/\/www.nfpa.org\/\/-\/media\/Files\/News-and-Research\/Fire-statistics-and-reports\/Emergency-responders\/osFFF.pdf."},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.firesaf.2010.03.001"},{"key":"e_1_3_2_54_2","unstructured":"Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv:1706.05098. Retrieved from https:\/\/arxiv.org\/abs\/1706.05098."},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Steve Rudz Khaled Chetehouna A. Hafiane H\u00e9l\u00e8ne Laurent and Olivier S\u00e9ro-Guillaume. 2013. Investigation of a novel image segmentation method dedicated to forest fire applications. Measurement Science and Technology 24 7 Article 075403 (2013) 8 pages.","DOI":"10.1088\/0957-0233\/24\/7\/075403"},{"key":"e_1_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov and Liang-Chieh Chen. 2018. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition . IEEE 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3326992"},{"key":"e_1_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Sudhakar Sengan Varadarajan Vijayakumar C. Sathiya Kumar V. Priya Logesh Ravi and V. Subramaniyaswamy. 2020. Unmanned Aerial Vehicle (UAV) based Forest Fire Detection and monitoring for reducing false alarms in forest-fires. Computer Communications 149 C (2020) 1\u201316.","DOI":"10.1016\/j.comcom.2019.10.007"},{"key":"e_1_3_2_59_2","first-page":"101","volume-title":"Advances and Trends in Artificial Intelligence. Artificial Intelligence Practices","author":"Sharma Jivitesh","year":"2021","unstructured":"Jivitesh Sharma, Ole-Christoffer Granmo, and Morten Goodwin. 2021. Emergency analysis: Multitask learning with deep convolutional neural networks for fire emergency scene parsing. In Advances and Trends in Artificial Intelligence. Artificial Intelligence Practices. Springer International Publishing, Cham, 101\u2013112."},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65172-9_16"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1409.1556"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.3390\/ai1020010"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGNCC.2016.7829074"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.2991\/ifmeita-16.2016.105"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510027","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3510027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:24Z","timestamp":1750191144000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510027"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,18]]},"references-count":64,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,11,30]]}},"alternative-id":["10.1145\/3510027"],"URL":"https:\/\/doi.org\/10.1145\/3510027","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,18]]},"assertion":[{"value":"2021-07-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-30","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}