{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:29:33Z","timestamp":1773772173303,"version":"3.50.1"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730351","type":"print"},{"value":"9783031730368","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73036-8_14","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:07:30Z","timestamp":1732093650000},"page":"236-256","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Caltech Aerial RGB-Thermal Dataset in\u00a0the\u00a0Wild"],"prefix":"10.1007","author":[{"given":"Connor","family":"Lee","sequence":"first","affiliation":[]},{"given":"Matthew","family":"Anderson","sequence":"additional","affiliation":[]},{"given":"Nikhil","family":"Ranganathan","sequence":"additional","affiliation":[]},{"given":"Xingxing","family":"Zuo","sequence":"additional","affiliation":[]},{"given":"Kevin","family":"Do","sequence":"additional","affiliation":[]},{"given":"Georgia","family":"Gkioxari","sequence":"additional","affiliation":[]},{"given":"Soon-Jo","family":"Chung","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"14_CR1","unstructured":"Ackerman, E.: Blade strike on landing ends mars helicopter\u2019s epic journey (2024). https:\/\/spectrum.ieee.org\/mars-helicopter-ingenuity-end-mission"},{"issue":"10","key":"14_CR2","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1177\/0278364917728574","volume":"36","author":"M Bloesch","year":"2017","unstructured":"Bloesch, M., Burri, M., Omari, S., Hutter, M., Siegwart, R.: Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback. Int. J. Robot. Rese. 36(10), 1053\u20131072 (2017)","journal-title":"Int. J. Robot. Rese."},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Bondi, E., et\u00a0al.: Birdsai: a dataset for detection and tracking in aerial thermal infrared videos. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1747\u20131756 (2020)","DOI":"10.1109\/WACV45572.2020.9093284"},{"issue":"9","key":"14_CR4","doi-asserted-by":"publisher","first-page":"6844","DOI":"10.1109\/TGRS.2019.2909026","volume":"57","author":"KL Brodie","year":"2019","unstructured":"Brodie, K.L., Bruder, B.L., Slocum, R.K., Spore, N.J.: Simultaneous mapping of coastal topography and bathymetry from a lightweight multicamera UAS. IEEE Trans. Geosci. Remote Sens. 57(9), 6844\u20136864 (2019). https:\/\/doi.org\/10.1109\/TGRS.2019.2909026","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"14_CR5","unstructured":"Cai, H., Gan, C., Han, S.: EfficientVit: enhanced linear attention for high-resolution low-computation visual recognition. arXiv preprint arXiv:2205.14756 (2022)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Cai, W., Jin, K., Hou, J., Guo, C., Wu, L., Yang, W.: VDD: varied drone dataset for semantic segmentation. arXiv preprint arXiv:2305.13608 (2023)","DOI":"10.2139\/ssrn.4902735"},{"key":"14_CR7","unstructured":"Center, A.F.S.: A dataset for machine learning algorithm development from 2010-06-15 to 2010-08-15. NOAA National Centers for Environmental Information (2019)"},{"key":"14_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"14_CR9","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"14_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/978-3-030-03398-9_30","volume-title":"Pattern Recognition and Computer Vision","author":"Yu Chen","year":"2018","unstructured":"Chen, Yu., Wang, Y., Lu, P., Chen, Y., Wang, G.: Large-scale structure from motion with semantic constraints of aerial images. In: Lai, J.-H., et al. (eds.) PRCV 2018. LNCS, vol. 11256, pp. 347\u2013359. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-03398-9_30"},{"issue":"3","key":"14_CR11","doi-asserted-by":"publisher","first-page":"934","DOI":"10.1109\/TITS.2018.2791533","volume":"19","author":"Y Choi","year":"2018","unstructured":"Choi, Y., et al.: Kaist multi-spectral day\/night data set for autonomous and assisted driving. IEEE Trans. Intell. Transp. Syst. 19(3), 934\u2013948 (2018)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Deevi, S.A., Lee, C., Gan, L., Nagesh, S., Pandey, G., Chung, S.J.: Rgb-x object detection via scene-specific fusion modules. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7366\u20137375 (2024)","DOI":"10.1109\/WACV57701.2024.00720"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Delaune, J., Hewitt, R., Lytle, L., Sorice, C., Thakker, R., Matthies, L.: Thermal-inertial odometry for autonomous flight throughout the night. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1122\u20131128. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8968238"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Doer, C., Trommer, G.F.: Radar visual inertial odometry and radar thermal inertial odometry: Robust navigation even in challenging visual conditions. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 331\u2013338. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636799"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"issue":"3","key":"14_CR16","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng, D., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans. Intell. Transp. Syst. 22(3), 1341\u20131360 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"14_CR17","unstructured":"Teledyne flir adas dataset. https:\/\/www.flir.com\/oem\/adas\/adas-dataset-form\/. Accessed 27 Oct 2023"},{"issue":"9","key":"14_CR18","doi-asserted-by":"publisher","first-page":"2672","DOI":"10.3390\/s20092672","volume":"20","author":"S Fountas","year":"2020","unstructured":"Fountas, S., Mylonas, N., Malounas, I., Rodias, E., Hellmann Santos, C., Pekkeriet, E.: Agricultural robotics for field operations. Sensors 20(9), 2672 (2020)","journal-title":"Sensors"},{"key":"14_CR19","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s00138-013-0570-5","volume":"25","author":"R Gade","year":"2014","unstructured":"Gade, R., Moeslund, T.B.: Thermal cameras and applications: a survey. Mach. Vis. Appl. 25, 245\u2013262 (2014)","journal-title":"Mach. Vis. Appl."},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Gan, L., Lee, C., Chung, S.J.: Unsupervised RGB-to-thermal domain adaptation via multi-domain attention network. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 6014\u20136020. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160872"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Geneva, P., Eckenhoff, K., Lee, W., Yang, Y., Huang, G.: OpenVins: a research platform for visual-inertial estimation. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 4666\u20134672. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196524"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Ha, Q., Watanabe, K., Karasawa, T., Ushiku, Y., Harada, T.: MFNet: towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5108\u20135115. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206396"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"He, M., Rajkumar, R.R.: Using thermal vision for extended VINs-mono to localize vehicles in large-scale outdoor road environments. In: 2021 IEEE Intelligent Vehicles Symposium (IV), pp. 953\u2013960. IEEE (2021)","DOI":"10.1109\/IV48863.2021.9575326"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Howard, A., et\u00a0al.: Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"14_CR26","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"2834","DOI":"10.1007\/978-981-16-9492-9_278","volume-title":"Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021)","author":"T Hua","year":"2022","unstructured":"Hua, T., Pei, L., Li, T., Wu, Q., Wang, R., Yu, W.: I2-SLAM: fusing Infrared camera and\u00a0IMU for\u00a0simultaneous localization and\u00a0mapping. In: Wu, M., Niu, Y., Gu, M., Cheng, J. (eds.) ICAUS 2021. LNEE, vol. 861, pp. 2834\u20132844. Springer, Singapore (2022). https:\/\/doi.org\/10.1007\/978-981-16-9492-9_278"},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01219-9_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Huang","year":"2018","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179\u2013196. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_11"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Jia, X., Zhu, C., Li, M., Tang, W., Zhou, W.: LLVIP: a visible-infrared paired dataset for low-light vision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3496\u20133504 (2021)","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Jong, A., Yu, M., Dhrafani, D., Kailas, S., Moon, B., Sycara, K., Scherer, S.: Wit-UAS: a wildland-fire infrared thermal dataset to detect crew assets from aerial views. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 11464\u201311471. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10341683"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Khattak, S., Papachristos, C., Alexis, K.: Keyframe-based direct thermal\u2013inertial odometry. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 3563\u20133569. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793927"},{"issue":"4","key":"14_CR32","doi-asserted-by":"publisher","first-page":"6497","DOI":"10.1109\/LRA.2021.3093652","volume":"6","author":"YH Kim","year":"2021","unstructured":"Kim, Y.H., Shin, U., Park, J., Kweon, I.S.: MS-UDA: multi-spectral unsupervised domain adaptation for thermal image semantic segmentation. IEEE Robot. Autom. Lett. 6(4), 6497\u20136504 (2021). https:\/\/doi.org\/10.1109\/LRA.2021.3093652","journal-title":"IEEE Robot. Autom. Lett."},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Lee, C., Frennert, J.G., Gan, L., Anderson, M., Chung, S.J.: Online self-supervised thermal water segmentation for aerial vehicles. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7734\u20137741. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10342016"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Lee, D.G., Jeon, M.H., Cho, Y., Kim, A.: Edge-guided multi-domain RGB-to-TIR image translation for training vision tasks with challenging labels. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 8291\u20138298. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161210"},{"issue":"7","key":"14_CR36","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1109\/TNNLS.2020.3009373","volume":"32","author":"C Li","year":"2020","unstructured":"Li, C., Xia, W., Yan, Y., Luo, B., Tang, J.: Segmenting objects in day and night: edge-conditioned CNN for thermal image semantic segmentation. IEEE Trans. Neural Networks Learn. Syst. 32(7), 3069\u20133082 (2020)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Riders: radar-infrared depth estimation for robust sensing. arXiv preprint arXiv:2402.02067 (2024)","DOI":"10.1109\/TITS.2024.3432996"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Liang, M., Hu, J., Bao, C., Feng, H., Deng, F., Lam, T.L.: Explicit attention-enhanced fusion for RGB-thermal perception tasks. IEEE Robot. Autom. Lett. (2023)","DOI":"10.1109\/LRA.2023.3272269"},{"key":"14_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135811 (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"14_CR42","unstructured":"Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"14_CR45","doi-asserted-by":"publisher","unstructured":"Lyu, Y., Vosselman, G., Xia, G.S., Yilmaz, A., Yang, M.Y.: UaVid: a semantic segmentation dataset for UAV imagery. ISPRS J. Photogrammetry and Remote Sensing 165, 108 \u2013 119 (2020). https:\/\/doi.org\/10.1016\/j.isprsjprs.2020.05.009, http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0924271620301295","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"14_CR46","unstructured":"Mehta, S., Rastegari, M.: Separable self-attention for mobile vision transformers. arXiv preprint arXiv:2206.02680 (2022)"},{"key":"14_CR47","unstructured":"Mostegel, C., Maurer, M., Heran, N., Pestana\u00a0Puerta, J., Fraundorfer, F.: Semantic drone dataset (2019). http:\/\/dronedataset.icg.tugraz.at\/. Accessed 27 Oct 2023"},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Nigam, I., Huang, C., Ramanan, D.: Ensemble knowledge transfer for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1499\u20131508. IEEE (2018)","DOI":"10.1109\/WACV.2018.00168"},{"issue":"1\u20132","key":"14_CR49","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1177\/02783649231153020","volume":"42","author":"S Nirgudkar","year":"2023","unstructured":"Nirgudkar, S., DeFilippo, M., Sacarny, M., Benjamin, M., Robinette, P.: MassMind: massachusetts maritime infrared dataset. Int. J. Robot. Res. 42(1\u20132), 21\u201332 (2023)","journal-title":"Int. J. Robot. Res."},{"key":"14_CR50","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision (2023)"},{"key":"14_CR51","doi-asserted-by":"publisher","unstructured":"Panetta, K., Shreyas\u00a0Kamath, K.M., Rajeev, S., Agaian, S.S.: FTNet: feature transverse network for thermal image semantic segmentation. IEEE Access 9, 145212\u2013145227 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3123066","DOI":"10.1109\/ACCESS.2021.3123066"},{"key":"14_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-58545-7_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Park","year":"2020","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319\u2013345. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19"},{"key":"14_CR53","doi-asserted-by":"publisher","unstructured":"Poudel, R., Liwicki, S., Cipolla, R.: Fast-SCNN: fFast semantic segmentation network. In: Sidorov, K., Hicks, Y. (eds.) Proceedings of the British Machine Vision Conference (BMVC). pp. 187.1\u2013187.12. BMVA Press (2019). https:\/\/doi.org\/10.5244\/C.33.187","DOI":"10.5244\/C.33.187"},{"issue":"4","key":"14_CR54","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1109\/TRO.2018.2853729","volume":"34","author":"T Qin","year":"2018","unstructured":"Qin, T., Li, P., Shen, S.: VINS-mono: a robust and versatile monocular visual-inertial state estimator. IEEE Trans. Rob. 34(4), 1004\u20131020 (2018)","journal-title":"IEEE Trans. Rob."},{"key":"14_CR55","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR56","doi-asserted-by":"crossref","unstructured":"Retief, S.P., Willers, C., Wheeler, M.: Prediction of thermal crossover based on imaging measurements over the diurnal cycle. In: Geo-Spatial and Temporal Image and Data Exploitation III. vol.\u00a05097, pp. 58\u201369. SPIE (2003)","DOI":"10.1117\/12.488358"},{"key":"14_CR57","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695 (June 2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR58","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"issue":"3","key":"14_CR59","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1109\/TRO.2021.3120036","volume":"38","author":"MRU Saputra","year":"2022","unstructured":"Saputra, M.R.U., Lu, C.X., de Gusmao, P.P.B., Wang, B., Markham, A., Trigoni, N.: Graph-based thermal-inertial slam with probabilistic neural networks. IEEE Trans. Rob. 38(3), 1875\u20131893 (2022)","journal-title":"IEEE Trans. Rob."},{"key":"14_CR60","doi-asserted-by":"crossref","unstructured":"Shin, U., Lee, K., Kweon, I.S.: Complementary random masking for RGB-thermal semantic segmentation. In: IEEE International Conference on Robotics and Automation (2024)","DOI":"10.1109\/ICRA57147.2024.10611200"},{"key":"14_CR61","doi-asserted-by":"crossref","unstructured":"Shin, U., Park, J., Kweon, I.S.: Deep depth estimation from thermal image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1043\u20131053 (2023)","DOI":"10.1109\/CVPR52729.2023.00107"},{"key":"14_CR62","doi-asserted-by":"crossref","unstructured":"Shivakumar, S.S., Rodrigues, N., Zhou, A., Miller, I.D., Kumar, V., Taylor, C.J.: Pst900: RGB-thermal calibration, dataset and segmentation network. In: 2020 IEEE international conference on robotics and automation (ICRA), pp. 9441\u20139447. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196831"},{"issue":"6","key":"14_CR63","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1002\/rob.22082","volume":"39","author":"S Speth","year":"2022","unstructured":"Speth, S., et al.: Deep learning with RGB and thermal images onboard a drone for monitoring operations. J. Field Robot. 39(6), 840\u2013868 (2022)","journal-title":"J. Field Robot."},{"key":"14_CR64","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D slam systems. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 573\u2013580. IEEE (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"issue":"3","key":"14_CR65","doi-asserted-by":"publisher","first-page":"2576","DOI":"10.1109\/LRA.2019.2904733","volume":"4","author":"Y Sun","year":"2019","unstructured":"Sun, Y., Zuo, W., Liu, M.: RTFNet: RGB-thermal fusion network for semantic segmentation of urban scenes. IEEE Robot. Autom. Lett. 4(3), 2576\u20132583 (2019). https:\/\/doi.org\/10.1109\/LRA.2019.2904733","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"14_CR66","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1109\/TASE.2020.2993143","volume":"18","author":"Y Sun","year":"2021","unstructured":"Sun, Y., Zuo, W., Yun, P., Wang, H., Liu, M.: FuseSeg: semantic segmentation of urban scenes based on RGB and thermal data fusion. IEEE Trans. Autom. Sci. Eng. 18(3), 1000\u20131011 (2021). https:\/\/doi.org\/10.1109\/TASE.2020.2993143","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"14_CR67","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1038\/s41597-023-02066-6","volume":"10","author":"J Suo","year":"2023","unstructured":"Suo, J., Wang, T., Zhang, X., Chen, H., Zhou, W., Shi, W.: Hit-UAV: a high-altitude infrared thermal dataset for unmanned aerial vehicle-based object detection. Sci. Data 10, 227 (2023)","journal-title":"Sci. Data"},{"key":"14_CR68","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"14_CR69","doi-asserted-by":"crossref","unstructured":"Ustun, B., Kaya, A.K., Ayerden, E.C., Altinel, F.: Spectral transfer guided active domain adaptation for thermal imagery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 449\u2013458 (2023)","DOI":"10.1109\/CVPRW59228.2023.00051"},{"issue":"16","key":"14_CR70","doi-asserted-by":"publisher","first-page":"5397","DOI":"10.3390\/s21165397","volume":"21","author":"J Vargas","year":"2021","unstructured":"Vargas, J., Alsweiss, S., Toker, O., Razdan, R., Santos, J.: An overview of autonomous vehicles sensors and their vulnerability to weather conditions. Sensors 21(16), 5397 (2021)","journal-title":"Sensors"},{"key":"14_CR71","doi-asserted-by":"crossref","unstructured":"Vertens, J., Z\u00fcrn, J., Burgard, W.: HeatNet: bridging the day-night domain gap in semantic segmentation with thermal images. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8461\u20138468. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341192"},{"key":"14_CR72","doi-asserted-by":"crossref","unstructured":"VS, V., Poster, D., You, S., Hu, S., Patel, V.M.: Meta-UDA: unsupervised domain adaptive thermal object detection using meta-learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1412\u20131423 (2022)","DOI":"10.1109\/WACV51458.2022.00375"},{"key":"14_CR73","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"14_CR74","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"14_CR75","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"14_CR76","doi-asserted-by":"publisher","unstructured":"Xiong, H., Cai, W., Liu, Q.: MCNet: multi-level correction network for thermal image semantic segmentation of nighttime driving scene. Infrared Phys. Technol. 103628 (2021). https:\/\/doi.org\/10.1016\/j.infrared.2020.103628","DOI":"10.1016\/j.infrared.2020.103628"},{"key":"14_CR77","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"14_CR78","doi-asserted-by":"crossref","unstructured":"Yun, S., et al.: STheReO: stereo thermal dataset for research in odometry and mapping. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3857\u20133864. IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9981857"},{"key":"14_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Delivering arbitrary-modal semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"14_CR80","doi-asserted-by":"crossref","unstructured":"Zhao, S., Wang, P., Zhang, H., Fang, Z., Scherer, S.: TP-TIO: a robust thermal-inertial odometry with deep thermalpoint. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4505\u20134512. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341716"},{"key":"14_CR81","doi-asserted-by":"publisher","unstructured":"Zhou, W., Liu, J., Lei, J., Yu, L., Hwang, J.N.: GMNet: graded-feature multilabel-learning network for RGB-thermal urban scene semantic segmentation. IEEE Trans. Image Process. 30, 7790\u20137802 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3109518","DOI":"10.1109\/TIP.2021.3109518"},{"key":"14_CR82","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"issue":"11","key":"14_CR83","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2021","unstructured":"Zhu, P., et al.: Detection and tracking meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7380\u20137399 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73036-8_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T16:17:42Z","timestamp":1733069862000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73036-8_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031730351","9783031730368"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73036-8_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}