{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T11:06:14Z","timestamp":1784718374070,"version":"3.55.0"},"reference-count":30,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Small objects in video streams occupy a small proportion in the image; the texture and shape information they carry is limited, making it difficult to continuously track and identify. To solve this problem, a method for continuous tracking and recognition of small objects in the video stream based on YOLO and spatio-temporal context memory network is proposed. A backbone network based on the improved YOLOv8 model is introduced, and the multi-scale visual features of small objects are extracted at different levels of the video stream using the wavelet pooling module. A mixed attention module enhances the feature response in the spatially significant pixel regions, generating weighted multi-scale visual features. The neck network processes these weighted features through a spatio-temporal context memory network to extract multi-scale spatio-temporal features. Then, a bidirectional feature pyramid module fuses these multi-scale spatio-temporal features. The head network processes the fused features to output continuous recognition results for small objects. Experiments show that the proposed method successfully extracts the spatiotemporal features of small objects from video stream data sets dominated by small objects. Under different conditions of small object occlusion rates, this method achieves a success rate of continuous tracking and recognition of small objects over 0.93.<\/jats:p>","DOI":"10.3390\/s26144639","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T10:48:28Z","timestamp":1784717308000},"page":"4639","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Continuous Tracking and Recognition of Small Objects in Video Streams Based on YOLO and Spatio-Temporal Contextual Memory Networks"],"prefix":"10.3390","volume":"26","author":[{"given":"Chengyuan","family":"Pang","sequence":"first","affiliation":[{"name":"Equipment Management and Unmanned Aerial Vehicle Engineering School, Air Force Engineering University, Xi\u2019an 710051, China"},{"name":"National Key Laboratory of Unmanned Aerial Vehicle Technology, Xi\u2019an 710051, China"},{"name":"The Youth Innovation Team of Shaanxi University, Xi\u2019an 710051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongpu","family":"Li","sequence":"additional","affiliation":[{"name":"Equipment Management and Unmanned Aerial Vehicle Engineering School, Air Force Engineering University, Xi\u2019an 710051, China"},{"name":"National Key Laboratory of Unmanned Aerial Vehicle Technology, Xi\u2019an 710051, China"},{"name":"The Youth Innovation Team of Shaanxi University, Xi\u2019an 710051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4711-3991","authenticated-orcid":false,"given":"Le","family":"Ru","sequence":"additional","affiliation":[{"name":"Equipment Management and Unmanned Aerial Vehicle Engineering School, Air Force Engineering University, Xi\u2019an 710051, China"},{"name":"National Key Laboratory of Unmanned Aerial Vehicle Technology, Xi\u2019an 710051, China"},{"name":"The Youth Innovation Team of Shaanxi University, Xi\u2019an 710051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Sun","sequence":"additional","affiliation":[{"name":"Equipment Management and Unmanned Aerial Vehicle Engineering School, Air Force Engineering University, Xi\u2019an 710051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxu","family":"Chen","sequence":"additional","affiliation":[{"name":"Equipment Management and Unmanned Aerial Vehicle Engineering School, Air Force Engineering University, Xi\u2019an 710051, China"},{"name":"National Key Laboratory of Unmanned Aerial Vehicle Technology, Xi\u2019an 710051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e70020","DOI":"10.1111\/exsy.70020","article-title":"Cutting-edge deep learning methods for image-based object detection in autonomous driving: In-depth survey","volume":"42","author":"Saeedizadeh","year":"2025","journal-title":"Expert Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1515\/jag-2023-0011","article-title":"Classification and object detection with image assisted total station and machine learning","volume":"17","author":"Zschiesche","year":"2023","journal-title":"J. Appl. Geod."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3120","DOI":"10.3390\/s24103120","article-title":"UAV path optimization for angle-only self-localization and target tracking based on the bayesian fisher information matrix","volume":"24","author":"Dogancay","year":"2024","journal-title":"Sensors"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/s10489-024-06224-0","article-title":"A data-centric framework for combating domain shift in underwater object detection with image enhancement","volume":"55","author":"Folkman","year":"2025","journal-title":"Appl. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1177\/0020720920983524","article-title":"Improved YOLOv3 with duplex FPN for object detection based on deep learning","volume":"62","author":"Shin","year":"2025","journal-title":"Int. J. Electr. Eng. Educ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"643","DOI":"10.14429\/dsj.74.19576","article-title":"An efficient visual tracking system based on extreme learning machine in the defence and military sector","volume":"74","author":"Rathore","year":"2024","journal-title":"Def. Sci. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"130327","DOI":"10.1016\/j.neucom.2025.130327","article-title":"Enhancing tiny object detection using Guided Object Inference Slicing (GOIS): An efficient dynamic adaptive framework for fine-tuned and non-fine-tuned deep learning models","volume":"640","author":"Muzammul","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"127193","DOI":"10.1016\/j.eswa.2025.127193","article-title":"Advanced data association technique using integrated track splitting filter for multi-target tracking in clutter and occlusion","volume":"277","author":"Memon","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3307","DOI":"10.1007\/s00500-025-10634-8","article-title":"Enhancing coordinated target tracking: Innovative particle filters with meta-heuristic integration and advanced model validation","volume":"29","author":"Das","year":"2025","journal-title":"Soft Comput."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.patrec.2023.05.031","article-title":"SOLARNet: A single stage regression based framework for efficient and robust object recognition in aerial images","volume":"172","author":"Saini","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"127447","DOI":"10.1016\/j.eswa.2025.127447","article-title":"SO-YOLOv8: A novel deep learning-based approach for small object detection with YOLO beyond COCO","volume":"280","author":"Iqra","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.infrared.2023.104703","article-title":"YOLO-CIR: The network based on YOLO and ConvNeXt for infrared object detection","volume":"131","author":"Zhou","year":"2023","journal-title":"Infrared Phys. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s11554-024-01604-8","article-title":"Real-time detection of coal mine safety helmet based on improved YOLOv8","volume":"22","author":"Li","year":"2025","journal-title":"J. Real-Time Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wu, H., Tian, T., Geng, Q., and Li, H. (2025). STC-DeepLAINet: A Transformer-GCN Hybrid Deep Learning Network for Large-Scale LAI Inversion by Integrating Spatio-Temporal Correlations. Remote Sens., 17.","DOI":"10.3390\/rs17244047"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lu, Y., Du, C., Li, X., Liang, S., Zhang, Q., and Zhao, Z.A. (2025). High-Precision Defect Detection Approach Based on BiFDRep-YOLOv8n for Small Target Defects in Photovoltaic Modules. Energies, 18.","DOI":"10.3390\/en18092299"},{"key":"ref_16","first-page":"4789","article-title":"Temporal noise suppression for small target detection in infrared image sequences","volume":"126","author":"Zhao","year":"2015","journal-title":"Opt. Z. Licht Elektron. J. Light-Electronopt."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Poster, D., Hu, S., and Nasrabadi, N.M. (2023). Long-range thermal target detection in data-limited settings using restricted receptive fields. Sensors, 23.","DOI":"10.3390\/s23187806"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"10835","DOI":"10.1007\/s00521-025-10978-0","article-title":"A novel human action recognition using grad-cam visualization with gated recurrent units","volume":"37","author":"Jayamohan","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"127942","DOI":"10.1016\/j.neucom.2024.127942","article-title":"Efficient tick-shape networks of full-residual point-depth-point blocks for image classification","volume":"596","author":"Nguyen","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8357","DOI":"10.1007\/s11227-023-05717-y","article-title":"Terahertz video-based hidden object detection using YOLOv5m and mutation-enabled salp swarm algorithm for enhanced accuracy and faster recognition","volume":"80","author":"Jayachitra","year":"2024","journal-title":"J. Supercomput."},{"key":"ref_21","first-page":"226","article-title":"Object detection algorithm for indoor switchgear components in substations based on improved YOLOv5s","volume":"66","author":"Changdong","year":"2024","journal-title":"Insight Non-Destr. Test. Cond. Monit."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MMUL.2025.3578241","article-title":"An Object Detection Algorithm of Literatures\u2019 Key Information Based on Optimized Cascade R-CNN","volume":"32","author":"Wang","year":"2025","journal-title":"IEEE Multimed."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/JSAS.2025.3650472","article-title":"A lightweight algorithm for detecting abnormal interactive behaviors of bid evaluation personnel based on improved yolov11n","volume":"3","author":"Su","year":"2026","journal-title":"IEEE J. Sel. Areas Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1007\/s12530-022-09446-0","article-title":"MiniNet: A concise CNN for image forgery detection","volume":"14","author":"Tyagi","year":"2023","journal-title":"Evol. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/MIS.2022.3215779","article-title":"Convolutional neural network-assisted adaptive sampling for sparse feature detection in image and video data","volume":"38","author":"Lahoti","year":"2023","journal-title":"IEEE Intell. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1080\/17686733.2023.2294598","article-title":"IR-GAN: Improved generative adversarial networks for infrared breast image segmentation","volume":"22","author":"Raghavan","year":"2025","journal-title":"Quant. Infrared Thermogr. J."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1007\/s11760-025-03883-5","article-title":"Multi-target detection method for driving area of mine driverless rail locomotives based on lightweight network","volume":"19","author":"Wang","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kodipaka, V., Marques, L., Corteso, R., and Ara\u00fajo, H. (2024). Aph-yolov7t: A yolo attention prediction head forsearch and rescue withdrones. Robot 2023: Sixth Iberian Robotics Conference, Springer.","DOI":"10.1007\/978-3-031-59167-9_22"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1109\/OJCS.2025.3535081","article-title":"Quantum computing-accelerated kalman filtering for satellite clusters: Algorithms and comparative analysis","volume":"6","author":"Prakash","year":"2025","journal-title":"IEEE Open J. Comput. Soc."},{"key":"ref_30","first-page":"15","article-title":"Real-time detection and motion analysis of bubbles in gas\u2013liquid two-phase flow via YOLO v11 and DeepSORT","volume":"37","author":"Zhang","year":"2025","journal-title":"Phys. Fluids"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4639\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T10:56:36Z","timestamp":1784717796000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":30,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144639"],"URL":"https:\/\/doi.org\/10.3390\/s26144639","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]}}}