{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:06:09Z","timestamp":1771653969428,"version":"3.50.1"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Natural Science Foundation of China Basic Science Center Program","award":["Grant 62388101"],"award-info":[{"award-number":["Grant 62388101"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11760-025-04965-0","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T11:28:53Z","timestamp":1769772533000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A UAV Detection in Complex Environments Method Based on Cross-Modal Fusion of Infrared and Visible images"],"prefix":"10.1007","volume":"20","author":[{"given":"Ershen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayue","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tengli","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pingping","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"La","family":"Na","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuming","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"issue":"1","key":"4965_CR1","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/s00530-024-01622-3","volume":"31","author":"J Qu","year":"2025","unstructured":"Qu, J., Li, Q., Pan, J., Sun, M., Lu, X., Zhou, Y., Zhu, H.: Ss-yolov8: small-size object detection algorithm based on improved yolov8 for uav imagery. Multimedia Syst. 31(1), 42 (2025)","journal-title":"Multimedia Syst."},{"key":"4965_CR2","unstructured":"Tian, Y., Ye, Q., Doermann, D.: Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524 (2025)"},{"key":"4965_CR3","doi-asserted-by":"crossref","unstructured":"Rothmeier, T., Wachtel, D., Dem\u00a0Bussche-H\u00fcnnefeld, T., Huber, W.: I had a bad day: Challenges of object detection in bad visibility conditions. In: 2023 IEEE Intelligent Vehicles Symposium (IV), pp. 1\u20136 (2023). IEEE","DOI":"10.1109\/IV55152.2023.10186674"},{"issue":"8","key":"4965_CR4","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s11760-025-04214-4","volume":"19","author":"J Chu","year":"2025","unstructured":"Chu, J., Wu, J., Zhang, W., Wei, X.: Wbs-yolov8: A lightweight infrared object detection algorithm for nighttime autonomous driving. SIViP 19(8), 619 (2025)","journal-title":"SIViP"},{"key":"4965_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Dai, Z., Pan, C., Zhang, G., Xu, J.: Noc-yolo: An exploration to enhance small-target vehicle detection accuracy in aerial infrared images. Infrared Physics & Technology, 105905 (2025)","DOI":"10.1016\/j.infrared.2025.105905"},{"issue":"12","key":"4965_CR6","doi-asserted-by":"publisher","first-page":"24330","DOI":"10.1109\/TITS.2022.3203715","volume":"23","author":"J Shen","year":"2022","unstructured":"Shen, J., Zhou, W., Liu, N., Sun, H., Li, D., Zhang, Y.: An anchor-free lightweight deep convolutional network for vehicle detection in aerial images. IEEE Trans. Intell. Transp. Syst. 23(12), 24330\u201324342 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"4965_CR7","doi-asserted-by":"crossref","unstructured":"Gomaa, A., Saad, O.M.: Residual channel-attention (rca) network for remote sensing image scene classification. Multimedia Tools and Applications, 1\u201325 (2025)","DOI":"10.1007\/s11042-024-20546-8"},{"key":"4965_CR8","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.inffus.2019.07.011","volume":"54","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Liu, Y., Sun, P., Yan, H., Zhao, X., Zhang, L.: Ifcnn: A general image fusion framework based on convolutional neural network. Information Fusion 54, 99\u2013118 (2020)","journal-title":"Information Fusion"},{"issue":"3","key":"4965_CR9","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s11554-025-01691-1","volume":"22","author":"P Yan","year":"2025","unstructured":"Yan, P., Sun, H., Zhao, Y., Wang, P., Wu, Z.: Multispectral imaging and enhanced yolov10n for efficient coal gangue detection in complex mining environments. J. Real-Time Image Proc. 22(3), 111 (2025)","journal-title":"J. Real-Time Image Proc."},{"issue":"1","key":"4965_CR10","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s00371-023-02773-6","volume":"40","author":"Y Cai","year":"2024","unstructured":"Cai, Y., Zhou, W., Zhang, L., Yu, L., Luo, T.: Dhfnet: Dual-decoding hierarchical fusion network for rgb-thermal semantic segmentation. Vis. Comput. 40(1), 169\u2013179 (2024)","journal-title":"Vis. Comput."},{"key":"4965_CR11","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","volume":"82","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Ma, J.: Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network. Information Fusion 82, 28\u201342 (2022)","journal-title":"Information Fusion"},{"key":"4965_CR12","doi-asserted-by":"crossref","unstructured":"Tang, Z., Xu, T., Li, H., Wu, X.J., Zhu, X., Kittler, J.: Exploring fusion strategies for accurate rgbt visual object tracking (2022)","DOI":"10.1016\/j.inffus.2023.101881"},{"key":"4965_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127888","volume":"594","author":"J Cheng","year":"2024","unstructured":"Cheng, J., Feng, C., Xiao, Y., Cao, Z.: Late better than early: A decision-level information fusion approach for rgb-thermal crowd counting with illumination awareness. Neurocomputing 594, 127888 (2024)","journal-title":"Neurocomputing"},{"key":"4965_CR14","first-page":"1","volume":"71","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Chen, Y., Shao, W., Li, H., Zhang, L.: Swinfuse: A residual swin transformer fusion network for infrared and visible images. IEEE Trans. Instrum. Meas. 71, 1\u201312 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1","key":"4965_CR15","doi-asserted-by":"publisher","first-page":"17493","DOI":"10.1038\/s41598-025-02111-x","volume":"15","author":"OF Hassan","year":"2025","unstructured":"Hassan, O.F., Ibrahim, A.F., Gomaa, A., Makhlouf, M., Hafiz, B.: Real-time driver drowsiness detection using transformer architectures: a novel deep learning approach. Sci. Rep. 15(1), 17493 (2025)","journal-title":"Sci. Rep."},{"key":"4965_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105190","volume":"149","author":"X Zhang","year":"2024","unstructured":"Zhang, X., Song, Y., Song, T., Yang, D., Ye, Y., Zhou, J., Zhang, L.: Ldconv: Linear deformable convolution for improving convolutional neural networks. Image Vis. Comput. 149, 105190 (2024)","journal-title":"Image Vis. Comput."},{"key":"4965_CR17","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, B., Guo, X., Zhu, W., He, J., Liu, X., Yuan, J.: Deyolo: Dual-feature-enhancement yolo for cross-modality object detection. In: International Conference on Pattern Recognition, pp. 236\u2013252 (2025). Springer","DOI":"10.1007\/978-3-031-78447-7_16"},{"key":"4965_CR18","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., Zhang, L.: Dynamic head: Unifying object detection heads with attentions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7373\u20137382 (2021)","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"4965_CR19","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J.: DETRs Beat YOLOs on Real-time Object Detection (2024). arXiv:2304.08069","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"4965_CR20","unstructured":"Wan, D., Lu, R., Fang, Y., Lang, X., Shu, S., Chen, J., Shen, S., Xu, T., Ye, Z.: Yolov11-rgbt: Towards a comprehensive single-stage multispectral object detection framework. arXiv preprint arXiv:2506.14696 (2025)"},{"key":"4965_CR21","unstructured":"Qingyun, F., Dapeng, H., Zhaokui, W.: Cross-modality fusion transformer for multispectral object detection. arXiv e-prints (2021)"},{"key":"4965_CR22","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.inffus.2022.03.007","volume":"83\u201384","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Zhang, H., Jiang, X., Ma, J.: Piafusion: A progressive infrared and visible image fusion network based on illumination aware. Information Fusion 83\u201384, 79\u201392 (2022)","journal-title":"Information Fusion"},{"key":"4965_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913","volume":"145","author":"J Shen","year":"2024","unstructured":"Shen, J., Chen, Y., Liu, Y., Zuo, X., Fan, H., Yang, W.: Icafusion: Iterative cross-attention guided feature fusion for multispectral object detection. Pattern Recogn. 145, 109913 (2024)","journal-title":"Pattern Recogn."},{"key":"4965_CR24","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 (2021)","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"4965_CR25","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., Kweon, I.S.: Multispectral pedestrian detection: Benchmark dataset and baseline. IEEE (2013)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04965-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04965-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04965-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T05:26:16Z","timestamp":1771651576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04965-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":25,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["4965"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04965-0","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]},"assertion":[{"value":"30 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2026","order":4,"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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest\/Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}},{"value":"The authors declare no competing interests.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"69"}}