{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:35:02Z","timestamp":1781714102839,"version":"3.54.5"},"reference-count":33,"publisher":"National Library of Serbia","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ComSIS","COMPUT SCI INF SYST","COMPUT SCI INFORM SY","COMPUTER SCI INFORM","COMSIS J"],"published-print":{"date-parts":[[2025]]},"abstract":"<jats:p>Object detection is an important computer vision task, which is developed from image classification task. The difference is that it is no longer only to classify a single type of object in an image, but to complete the classification and positioning of multiple objects that may exist in an image at the same time. Classification refers to assigning category labels to the object, and positioning refers to determining the vertex coordinates of the peripheral rectangular box of the object. Therefore, object detection is more challenging and has broader application prospects, such as automatic driving, face recognition, pedestrian detection, medical detection etc,. Object detection can also be used as the research basis for more complex computer vision task such as image segmentation, image description, object tracking and action recognition. In traditional object detection, the feature utilization rate is low and it is easy to be affected by other environmental factors. Hence, this paper proposes a multimodal deep learning-based feature fusion for object detection in remote sensing images. In the new model, cascade RCNN is the backbone network. Parallel cascade RCNN network is utilized for feature fusion to enhance feature expression ability. In order to solve the problem of different segmentation shapes and sizes, the central part of the network adopts multi-coefficient cascaded hollow convolution to obtain multi-receptive field features without using pooling mode and preserving image information. Meanwhile, an improved selfattention combined receptive field strategy is used to obtain both low-level features with marginal details and high-level features with global semantics. Finally, we conduct experiments on DOTA set including ablation experiments and comparison experiments. The experimental results show that the mean Average Precision (mAP) and other indexes have been greatly improved, and its performance is better than the state-of-the-art detection algorithms. It has a good application prospect in the remote sensing image object detection task.<\/jats:p>","DOI":"10.2298\/csis241110011y","type":"journal-article","created":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T12:43:27Z","timestamp":1738673007000},"page":"327-344","source":"Crossref","is-referenced-by-count":2,"title":["Multimodal deep learning-based feature fusion for object detection in remote sensing images"],"prefix":"10.2298","volume":"22","author":[{"given":"Shoulin","family":"Yin","sequence":"first","affiliation":[{"name":"College of Information and Communication Engineering, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qunming","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-informatics, Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liguo","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information and Communications Engineering, Dalian Minzu University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1946-0384","authenticated-orcid":false,"given":"Mirjana","family":"Ivanovic","sequence":"additional","affiliation":[{"name":"Faculty of Sciences, University of Novi Sad, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Li","sequence":"additional","affiliation":[{"name":"Software College, Shenyang Normal University Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1078","reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"Y. Pi, N. D. Nath, H. A. Behzadan, Convolutional neural networks for object detection in aerial imagery for disaster response and recovery, Advanced Engineering Informatics, vol. 43, pp. 101009, 2020.","DOI":"10.1016\/j.aei.2019.101009"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"M. R. Marshall et al., \u201d3-D Object Tracking in Panoramic Video and LiDAR for Radiological Source Object Attribution and Improved Source Detection,\u201d IEEE Transactions on Nuclear Science, vol. 68, no. 2, pp. 189-202, Feb. 2021, doi: 10.1109\/TNS.2020.3047646.","DOI":"10.1109\/TNS.2020.3047646"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"S. Yin, L. Wang, M. Shafiq, L. Teng, A. A. Laghari and M. F. Khan, \u201dG2Grad-CAMRL: An Object Detection and Interpretation Model Based on Gradient-Weighted Class Activation Mapping and Reinforcement Learning in Remote Sensing Images,\u201d IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 3583-3598, 2023, doi: 10.1109\/JSTARS.2023.3241405","DOI":"10.1109\/JSTARS.2023.3241405"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"Y. Tao, Z. Zongyang, Z. Jun, C. Xinghua and Z. Fuqiang, \u201dLow-altitude small-sized object detection using lightweight feature-enhanced convolutional neural network,\u201d Journal of Systems Engineering and Electronics, vol. 32, no. 4, pp. 841-853, Aug. 2021, doi: 10.23919\/JSEE.2021.000073.","DOI":"10.23919\/JSEE.2021.000073"},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"A. Kumar, S. Srivastava, Object detection system based on convolution neural networks using single shot multi-box detector, Procedia Computer Science, vol. 171, pp. 2610-2617, 2020.","DOI":"10.1016\/j.procs.2020.04.283"},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"T. Diwan, G. Anirudh, V. J. Tembhurne, Object detection using YOLO: Challenges, architectural successors, datasets and applications, Multimedia Tools and Applications, vol. 82, no. 6, pp. 9243-9275, 2023.","DOI":"10.1007\/s11042-022-13644-y"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"B. Zhong, K. Ao, Single-stage rotation-decoupled detector for oriented object, Remote Sensing, vol. 12, no. 19, pp. 3262, 2020.","DOI":"10.3390\/rs12193262"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"F. Zhao, J. Li, J. Zhao and J. Feng, \u201dWeakly Supervised Phrase Localization with Multi-scale Anchored Transformer Network,\u201d 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 5696-5705, doi: 10.1109\/CVPR.2018.00597.","DOI":"10.1109\/CVPR.2018.00597"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"D. Cao, S. Yang, A Method based on Faster RCNN Network for Object Detection, Recent Advances in Computer Science and Communications (Formerly: Recent Patents on Computer Science), vol. 15, no. 9, pp. 1239-1244, 2022.","DOI":"10.2174\/2666255815666220301145622"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"B. C. Murthy,F. M. Hashmi, G. A. Keskar, EfficientLiteDet: a real-time pedestrian and vehicle detection algorithm, Machine Vision and Applications, vol. 33, no. 3, pp. 47, 2022.","DOI":"10.1007\/s00138-022-01293-y"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"L. Zhao, S. Li, Object detection algorithm based on improved YOLOv3, Electronics, vol. 9, no. 3, pp. 537, 2020.","DOI":"10.3390\/electronics9030537"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"A. Kumar, S. Srivastava, Object detection system based on convolution neural networks using single shot multi-box detector, Procedia Computer Science, vol. 171, pp. 2610-2617, 2020.","DOI":"10.1016\/j.procs.2020.04.283"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"K. Zhang, Y. Guo, X. Wang, J. Yuan and Q. Ding, \u201dMultiple Feature Reweight DenseNet for Image Classification,\u201d IEEE Access, vol. 7, pp. 9872-9880, 2019, doi: 10.1109\/ACCESS. 2018.2890127.","DOI":"10.1109\/ACCESS.2018.2890127"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"L. Wang, S. Yin, A. Hashem, et al., A novel deep learning-based single shot multibox detector model for object detection in optical remote sensing images,Geoscience Data Journal, 2022. https:\/\/doi.org\/10.1002\/gdj3.162","DOI":"10.1002\/gdj3.162"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"Y. Xiao, X.Wang, P. Zhang, et al., Object detection based on faster R-CNN algorithm with skip pooling and fusion of contextual information, Sensors, vol. 20, no. 19, pp. 5490, 2020.","DOI":"10.3390\/s20195490"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"D. Jiang, G. Li, C. Tan, et al., Semantic segmentation for multiscale target based on object recognition using the improved Faster-RCNN model, Future Generation Computer Systems, vol. 123, pp. 94-104, 2021.","DOI":"10.1016\/j.future.2021.04.019"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"S. Yin and H. Li, \u201dHot Region Selection Based on Selective Search and Modified Fuzzy CMeans in Remote Sensing Images,\u201d IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 5862-5871, 2020, doi: 10.1109\/JSTARS.2020.3025582.","DOI":"10.1109\/JSTARS.2020.3025582"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"G. A. Tsihrintzis, P. M. Johansen and A. J. Devaney, \u201dBuried object detection and location estimation from electromagnetic field measurements,\u201d IEEE Transactions on Antennas and Propagation, vol. 47, no. 11, pp. 1742-1744, Nov. 1999, doi: 10.1109\/8.814957.","DOI":"10.1109\/8.814957"},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"G. Cheng, Y. Si, H. Hong, X. Yao and L. Guo, \u201dCross-Scale Feature Fusion for Object Detection in Optical Remote Sensing Images,\u201d IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 3, pp. 431-435, March 2021, doi: 10.1109\/LGRS.2020.2975541.","DOI":"10.1109\/LGRS.2020.2975541"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"D. Ortego, J. C. SanMiguel and J. M. Martanez, \u201dLong-Term Stationary Object Detection Based on Spatio-Temporal Change Detection,\u201d IEEE Signal Processing Letters, vol. 22, no. 12, pp. 2368-2372, Dec. 2015, doi: 10.1109\/LSP.2015.2482598.","DOI":"10.1109\/LSP.2015.2482598"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"C. R. del-Blanco, F. Jaureguizar and N. Garcia, \u201dAn efficient multiple object detection and tracking framework for automatic counting and video surveillance applications,\u201d IEEE Transactions on Consumer Electronics, vol. 58, no. 3, pp. 857-862, August 2012, doi: 10.1109\/TCE.2012.6311328.","DOI":"10.1109\/TCE.2012.6311328"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"X. Yu, J. Yang, Z. Lin, J. Wang, T. Wang and T. Huang, \u201dSubcategory-Aware Object Detection,\u201d IEEE Signal Processing Letters, vol. 22, no. 9, pp. 1472-1476, Sept. 2015, doi: 10.1109\/LSP.2014.2299571.","DOI":"10.1109\/LSP.2014.2299571"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"L. Pan, W. -S. Chu, J. M. Saragih, F. De la Torre and M. Xie, \u201dFast and Robust Circular Object DetectionWith Probabilistic Pairwise Voting,\u201d IEEE Signal Processing Letters, vol. 18, no. 11, pp. 639-642, Nov. 2011, doi: 10.1109\/LSP.2011.2166956.","DOI":"10.1109\/LSP.2011.2166956"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Q. Hu, S. Paisitkriangkrai, C. Shen, A. van den Hengel and F. Porikli, \u201dFast Detection of Multiple Objects in Traffic Scenes With a Common Detection Framework,\u201d IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 4, pp. 1002-1014, April 2016, doi: 10.1109\/TITS.2015.2496795.","DOI":"10.1109\/TITS.2015.2496795"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"Z. -Q. Zhao, P. Zheng, S. -T. Xu and X.Wu, \u201dObject DetectionWith Deep Learning: A Review,\u201d IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3212-3232, Nov. 2019, doi: 10.1109\/TNNLS.2018.2876865.","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref26","doi-asserted-by":"crossref","unstructured":"Y. Lin, H. He, Z. Yin and F. Chen, \u201dRotation-Invariant Object Detection in Remote Sensing Images Based on Radial-Gradient Angle,\u201d IEEE Geoscience and Remote Sensing Letters, vol. 12, no. 4, pp. 746-750, April 2015, doi: 10.1109\/LGRS.2014.2360887.","DOI":"10.1109\/LGRS.2014.2360887"},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"Z. Cai and N. Vasconcelos, \u201dCascade R-CNN: High Quality Object Detection and Instance Segmentation,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 5, pp. 1483-1498, 1 May 2021, doi: 10.1109\/TPAMI.2019.2956516.","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref28","doi-asserted-by":"crossref","unstructured":"Q. Yao, X. Hu and H. Lei, \u201dMultiscale Convolutional Neural Networks for Geospatial Object Detection in VHR Satellite Images,\u201d IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 1, pp. 23-27, Jan. 2021, doi: 10.1109\/LGRS.2020.2967819.","DOI":"10.1109\/LGRS.2020.2967819"},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"J. Ding et al., \u201dObject Detection in Aerial Images: A Large-Scale Benchmark and Challenges,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 11, pp. 7778- 7796, 1 Nov. 2022.","DOI":"10.1109\/TPAMI.2021.3117983"},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"Z. Song, Y. Zhang, Y. Liu, K. Yang and M. Sun, \u201dMSFYOLO: Feature fusion-based detection for small objects,\u201dIEEE Latin America Transactions, vol. 20, no. 5, pp. 823-830, May 2022, doi: 10.1109\/TLA.2022.9693567.","DOI":"10.1109\/TLA.2022.9693567"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"X. Dong, R. Fu, Y. Gao, Y. Qin, Y. Ye and B. Li, \u201dRemote Sensing Object Detection Based on Receptive Field Expansion Block,\u201d IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 8020605, doi: 10.1109\/LGRS.2021.3110584.","DOI":"10.1109\/LGRS.2021.3110584"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"Z. Wu, J. Wen, Y. Xu, J. Yang and D. Zhang, \u201dMultiple Instance Detection Networks With Adaptive Instance Refinement,\u201d IEEE Transactions on Multimedia, vol. 25, pp. 267-279, 2023, doi: 10.1109\/TMM.2021.3125130.","DOI":"10.1109\/TMM.2021.3125130"},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"X. Dong et al., \u201dMultiscale Deformable Attention and Multilevel Features Aggregation for Remote Sensing Object Detection,\u201d IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 6510405, doi: 10.1109\/LGRS.2022.3178479.","DOI":"10.1109\/LGRS.2022.3178479"}],"container-title":["Computer Science and Information Systems"],"original-title":[],"language":"en","deposited":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T09:27:48Z","timestamp":1741166868000},"score":1,"resource":{"primary":{"URL":"https:\/\/doiserbia.nb.rs\/Article.aspx?ID=1820-02142500011Y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.2298\/csis241110011y","relation":{},"ISSN":["1820-0214","2406-1018"],"issn-type":[{"value":"1820-0214","type":"print"},{"value":"2406-1018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}