{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T14:01:48Z","timestamp":1778335308869,"version":"3.51.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s00138-024-01591-7","type":"journal-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T16:02:35Z","timestamp":1723478555000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Active perception based on deep reinforcement learning for autonomous robotic damage inspection"],"prefix":"10.1007","volume":"35","author":[{"given":"Wen","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad R.","family":"Jahanshahi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"1591_CR1","doi-asserted-by":"publisher","DOI":"10.1002\/stc.2964","volume":"29","author":"S Yoon","year":"2022","unstructured":"Yoon, S., Spencer, B.F., Lee, S., Jung, H., Kim, I.: A novel approach to assess the seismic performance of deteriorated bridge structures by employing UAV based damage detection. Struct. Control Health Monit. 29, e2964 (2022)","journal-title":"Struct. Control Health Monit."},{"key":"1591_CR2","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/s13349-020-00395-3","volume":"10","author":"F Potenza","year":"2020","unstructured":"Potenza, F., Rinaldi, C., Ottaviano, E., Gattulli, V.: A robotics and computer-aided procedure for defect evaluation in bridge inspection. J. Civ. Struct. Health Monit. 10, 471\u2013484 (2020)","journal-title":"J. Civ. Struct. Health Monit."},{"key":"1591_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104214","volume":"137","author":"Y Narazaki","year":"2022","unstructured":"Narazaki, Y., Hoskere, V., Chowdhary, G., Spencer, B.F., Jr.: Vision-based navigation planning for autonomous post-earthquake inspection of reinforced concrete railway viaducts using unmanned aerial vehicles. Autom. Constr. 137, 104214 (2022)","journal-title":"Autom. Constr."},{"key":"1591_CR4","doi-asserted-by":"publisher","first-page":"2793","DOI":"10.1007\/s10489-018-01396-y","volume":"49","author":"EE Protopapadakis","year":"2019","unstructured":"Protopapadakis, E.E., Voulodimos, A., Doulamis, A.D., Doulamis, N.D., Stathaki, T.: Automatic crack detection for tunnel inspection using deep learning and heuristic image post-processing. Appl. Intell. 49, 2793\u20132806 (2019)","journal-title":"Appl. Intell."},{"key":"1591_CR5","doi-asserted-by":"publisher","first-page":"54854","DOI":"10.1109\/ACCESS.2018.2872693","volume":"6","author":"W Jing","year":"2018","unstructured":"Jing, W., Goh, C.F., Rajaraman, M., Gao, F., Park, S., Liu, Y., Shimada, K.: A computational framework for automatic online path generation of robotic inspection tasks via coverage planning and reinforcement learning. IEEE Access 6, 54854\u201354864 (2018)","journal-title":"IEEE Access"},{"key":"1591_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2022.101849","volume":"55","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Peng, T., Wang, W., Luo, M.: High-efficient view planning for surface inspection based on parallel deep reinforcement learning. Adv. Eng. Inform. 55, 101849 (2023)","journal-title":"Adv. Eng. Inform."},{"key":"1591_CR7","doi-asserted-by":"publisher","first-page":"2030","DOI":"10.3390\/s21062030","volume":"21","author":"C Landgraf","year":"2021","unstructured":"Landgraf, C., Meese, B., Pabst, M., Martius, G., Huber, M.F.: A reinforcement learning approach to view planning for automated inspection tasks. Sensors 21, 2030 (2021)","journal-title":"Sensors"},{"key":"1591_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-021-01252-z","volume":"33","author":"P Gospodneti\u0107","year":"2022","unstructured":"Gospodneti\u0107, P., Mosbach, D., Rauhut, M., Hagen, H.: Viewpoint placement for inspection planning. Mach. Vis. Appl. 33, 1\u201321 (2022)","journal-title":"Mach. Vis. Appl."},{"key":"1591_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-020-01166-2","volume":"32","author":"JI Vasquez-Gomez","year":"2021","unstructured":"Vasquez-Gomez, J.I., Troncoso, D., Becerra, I., Sucar, E., Murrieta-Cid, R.: Next-best-view regression using a 3d convolutional neural network. Mach. Vis. Appl. 32, 1\u201314 (2021)","journal-title":"Mach. Vis. Appl."},{"key":"1591_CR10","doi-asserted-by":"publisher","first-page":"5325","DOI":"10.1109\/TIM.2019.2959292","volume":"69","author":"F-C Chen","year":"2020","unstructured":"Chen, F.-C., Jahanshahi, M.R.: NB-FCN: real-time accurate crack detection in inspection videos using deep fully convolutional network and parametric data fusion. IEEE Trans. Instrum. Meas. 69, 5325\u20135334 (2020)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"1591_CR11","doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., Valentin, J.P.C., Nie\u00dfner, M.: ViewAL: active learning with viewpoint entropy for semantic segmentation. In: CVPR, pp. 9430\u20139440 (2019)","DOI":"10.1109\/CVPR42600.2020.00945"},{"key":"1591_CR12","doi-asserted-by":"crossref","unstructured":"Kundu, A., Yin, X., Fathi, A., Ross, D.A., Brewington, B., Funkhouser, T.A., Pantofaru, C.: Virtual multi-view fusion for 3d semantic segmentation. arXiv:2007.13138 (2020)","DOI":"10.1007\/978-3-030-58586-0_31"},{"key":"1591_CR13","unstructured":"Chaplot, D.S., Dalal, M., Gupta, S., Malik, J., Salakhutdinov, R.: Seal: self-supervised embodied active learning using exploration and 3d consistency. In: Neural Information Processing Systems (2021)"},{"key":"1591_CR14","doi-asserted-by":"crossref","unstructured":"McCormac, J., Handa, A., Davison, A.J., Leutenegger, S.: Semanticfusion: dense 3d semantic mapping with convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4628\u20134635 (2016)","DOI":"10.1109\/ICRA.2017.7989538"},{"key":"1591_CR15","doi-asserted-by":"crossref","unstructured":"Hermans, A., Floros, G., Leibe, B.: Dense 3d semantic mapping of indoor scenes from RGB-d images. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 2631\u20132638 (2014)","DOI":"10.1109\/ICRA.2014.6907236"},{"key":"1591_CR16","doi-asserted-by":"crossref","unstructured":"Zhao, C., Sun, L., Stolkin, R.: A fully end-to-end deep learning approach for real-time simultaneous 3d reconstruction and material recognition. In: 2017 18th International Conference on Advanced Robotics (ICAR), pp. 75\u201382 (2017)","DOI":"10.1109\/ICAR.2017.8023499"},{"key":"1591_CR17","doi-asserted-by":"crossref","unstructured":"Jeong, J., Yoon, T.S., Park, J.B.: Multimodal sensor-based semantic 3d mapping for a large-scale environment. arXiv:1802.10271 (2018)","DOI":"10.1016\/j.eswa.2018.03.051"},{"key":"1591_CR18","doi-asserted-by":"crossref","unstructured":"He, Y., Chiu, W.-C., Keuper, M., Fritz, M.: STD2P: RGBD semantic segmentation using spatio-temporal data-driven pooling. In: CVPR, pp. 7158\u20137167 (2017)","DOI":"10.1109\/CVPR.2017.757"},{"key":"1591_CR19","doi-asserted-by":"crossref","unstructured":"Johns, E., Leutenegger, S., Davison, A.J.: Pairwise decomposition of image sequences for active multi-view recognition. In: CVPR, pp. 3813\u20133822 (2016)","DOI":"10.1109\/CVPR.2016.414"},{"key":"1591_CR20","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1111\/mice.12890","volume":"38","author":"AB Khajwal","year":"2022","unstructured":"Khajwal, A.B., Cheng, C.-S., Noshadravan, A.: Post-disaster damage classification based on deep multi-view image fusion. Comput. Aided Civ. Infrastruct. Eng. 38, 528\u2013544 (2022)","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"key":"1591_CR21","doi-asserted-by":"crossref","unstructured":"Kumawat, S., Raman, S.: LP-3DCNN: unveiling local phase in 3d convolutional neural networks. In: CVPR, pp. 4898\u20134907 (2019)","DOI":"10.1109\/CVPR.2019.00504"},{"key":"1591_CR22","doi-asserted-by":"crossref","unstructured":"Su, J.-C., Gadelha, M., Wang, R., Maji, S.: A deeper look at 3d shape classifiers. In: ECCV Workshops (2018)","DOI":"10.1007\/978-3-030-11015-4_49"},{"key":"1591_CR23","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497 (2014)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1591_CR24","unstructured":"Vaswani, A., Shazeer, N.M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: NIPS (2017)"},{"key":"1591_CR25","doi-asserted-by":"publisher","first-page":"966","DOI":"10.1109\/5.5968","volume":"76","author":"R Bajcsy","year":"1988","unstructured":"Bajcsy, R.: Active perception. Proc. IEEE 76, 966\u20131005 (1988)","journal-title":"Proc. IEEE"},{"key":"1591_CR26","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3D ShapeNets: a deep representation for volumetric shapes. In: CVPR, pp. 1912\u20131920 (2015)"},{"key":"1591_CR27","doi-asserted-by":"crossref","unstructured":"Hu, P., Heilbron, F.C., Wang, O., Lin, Z.L., Sclaroff, S., Perazzi, F.: Temporally distributed networks for fast video semantic segmentation. In: CVPR, pp. 8815\u20138824 (2020)","DOI":"10.1109\/CVPR42600.2020.00884"},{"key":"1591_CR28","doi-asserted-by":"crossref","unstructured":"Ammirato, P., Poirson, P., Park, E., Kosecka, J., Berg, A.C.: A dataset for developing and benchmarking active vision. In: ICRA, pp. 1378\u20131385 (2017)","DOI":"10.1109\/ICRA.2017.7989164"},{"issue":"7","key":"1591_CR29","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.1109\/TPAMI.2018.2840991","volume":"41","author":"D Jayaraman","year":"2018","unstructured":"Jayaraman, D., Grauman, K.: End-to-end policy learning for active visual categorization. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1601\u20131614 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1591_CR30","doi-asserted-by":"crossref","unstructured":"Yang, J., Ren, Z., Xu, M., Chen, X., Crandall, D.J., Parikh, D., Batra, D.: Embodied amodal recognition: learning to move to perceive objects. In: ICCV, pp. 2040\u20132050 (2019)","DOI":"10.1109\/ICCV.2019.00213"},{"key":"1591_CR31","doi-asserted-by":"crossref","unstructured":"Kotar, K., Mottaghi, R.: Interactron: embodied adaptive object detection. In: CVPR, pp. 14840\u201314849 (2022)","DOI":"10.1109\/CVPR52688.2022.01444"},{"key":"1591_CR32","doi-asserted-by":"crossref","unstructured":"Chaplot, D.S., Jiang, H., Gupta, S., Gupta, A.K.: Semantic curiosity for active visual learning. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58539-6_19"},{"key":"1591_CR33","doi-asserted-by":"crossref","unstructured":"Nilsson, D., Pirinen, A., G\u00e4rtner, E., Sminchisescu, C.: Embodied visual active learning for semantic segmentation. In: AAAI (2020)","DOI":"10.1609\/aaai.v35i3.16338"},{"key":"1591_CR34","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)"},{"key":"1591_CR35","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. arXiv:1505.04597 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1591_CR36","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587 (2017)"},{"key":"1591_CR37","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.neucom.2019.01.036","volume":"338","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Yao, J., Lu, X., Xie, R., Li, L.: DeepCrack: a deep hierarchical feature learning architecture for crack segmentation. Neurocomputing 338, 139\u2013153 (2019)","journal-title":"Neurocomputing"},{"key":"1591_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103176","volume":"114","author":"A Ji","year":"2020","unstructured":"Ji, A., Xue, X., Wang, Y., Luo, X., Xue, W.: An integrated approach to automatic pixel-level crack detection and quantification of asphalt pavement. Autom. Constr. 114, 103176 (2020)","journal-title":"Autom. Constr."},{"key":"1591_CR39","doi-asserted-by":"publisher","first-page":"8016","DOI":"10.1109\/TIE.2019.2945265","volume":"67","author":"W Choi","year":"2020","unstructured":"Choi, W., Cha, Y.: SDDNet: Real-time crack segmentation. IEEE Trans. Ind. Electron. 67, 8016\u20138025 (2020)","journal-title":"IEEE Trans. Ind. Electron."},{"key":"1591_CR40","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 (2017)"},{"key":"1591_CR41","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M.I., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. In: CoRR (2015)"},{"key":"1591_CR42","doi-asserted-by":"publisher","first-page":"04022039","DOI":"10.1061\/(ASCE)CP.1943-5487.0001045","volume":"36","author":"E Bianchi","year":"2022","unstructured":"Bianchi, E., Hebdon, M.H.: Development of extendable open-source structural inspection datasets. J. Comput. Civ. Eng. 36, 04022039 (2022)","journal-title":"J. Comput. Civ. Eng."},{"key":"1591_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2021.107850","volume":"160","author":"Y Narazaki","year":"2021","unstructured":"Narazaki, Y., Hoskere, V., Yoshida, K., Spencer, B.F., Fujino, Y.: Synthetic environments for vision-based structural condition assessment of Japanese high-speed railway viaducts. Mech. Syst. Signal Process. 160, 107850 (2021)","journal-title":"Mech. Syst. Signal Process."},{"key":"1591_CR44","doi-asserted-by":"publisher","first-page":"532","DOI":"10.3390\/s22020532","volume":"22","author":"V Hoskere","year":"2022","unstructured":"Hoskere, V., Narazaki, Y., Spencer, B.F.: Physics-based graphics models in 3d synthetic environments as autonomous vision-based inspection testbeds. Sensors 22, 532 (2022)","journal-title":"Sensors"},{"key":"1591_CR45","unstructured":"Houdini: SideFX Software (2021). https:\/\/www.sidefx.com\/products\/houdini\/"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01591-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-024-01591-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01591-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T04:04:54Z","timestamp":1726027494000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-024-01591-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":45,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["1591"],"URL":"https:\/\/doi.org\/10.1007\/s00138-024-01591-7","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"110"}}