Vehicle recognition pipeline via DeepSort on aerial image datasets
Open accessThe DOI matches its Crossref record; 103 of the 106 references it cites were found in a registry or an index.
Abstract
Introduction: Unmanned aerial vehicles (UAVs) are widely used in various computer vision applications, especially in intelligent traffic monitoring, as they are agile and simplify operations while boosting efficiency. However, automating these procedures is still a significant challenge due to the difficulty of extracting foreground (vehicle) information from complex traffic scenes. Methods: This paper presents a unique method for autonomous vehicle surveillance that uses FCM to segment aerial images. YOLOv8, which is known for its ability to detect tiny objects, is then used to detect vehicles. Additionally, a system that utilizes ORB features is employed to support vehicle recognition, assignment, and recovery across picture frames. Vehicle tracking is accomplished using DeepSORT, which elegantly combines Kalman filtering with deep learning to achieve precise results. Results: Our proposed model demonstrates remarkable performance in vehicle identification and tracking with precision of 0.86 and 0.84 on the VEDAI and SRTID datasets, respectively, for vehicle detection. Discussion: For vehicle tracking, the model achieves accuracies of 0.89 and 0.85 on the VEDAI and SRTID datasets, respectively.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures











Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Simple online and realtime tracking
Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7533003 · Cited by 4,433
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
Du, D., Qi, Y., Yu, H., Yang, Y., Duan, K., Li, G., Zhang, W., Huang, Q., & Tian, Q. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_23 · Cited by 1,099
Wang, G., Chen, Y., An, P., Hong, H., Hu, J., & Huang, T. (2023) · Sensors · doi:10.3390/s23167190 · Cited by 915 · cited 1×
“YOLOv8 is utilized for vehicle recognition and radiates as an excellent single-shot detector capable of identifying, segmenting, and classifying with fewer training parameters (Chen et al., 2023b; Wang et al., 2023).”
MethodDBSCAN: Past, present and future
Rehman, S. U., Asghar, S., Fong, S., & Sarasvady, S. (2014) · The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014) · doi:10.1109/icadiwt.2014.6814687 · Cited by 606 · cited 1×
“DBSCAN, or density-based spatial clustering, is a popular method in machine learning and data analysis (Khan et al., 2014; Deng et al., 2022).”
MethodVideo object tracking using adaptive Kalman filter
Weng, S.-K., Kuo, C.-M., & Tu, S.-K. (2006) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2006.03.004 · Cited by 323 · cited 1×
“While various image-based solutions have been developed, obstacles exist in expanding their capabilities, especially in dynamic contexts where backdrop and objects are in flux (Weng et al., 2006; Di et al., 2023; Dai et al., 2024).”
BackgroundSmall Object Detection Algorithm Based on Improved YOLOv8 for Remote Sensing
Yi, H., Liu, B., Zhao, B., & Liu, E. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3339235 · Cited by 310 · cited 1×
“The SPPF module at the backbone’s end employs three consecutive 5 × 5 Maxpools before concatenation in each layer to reliably identify objects of varied sizes with lightweight efficiency (Sun et al., 2019; Li S. et al., 2023; Yi et al., 2024).”
BackgroundUAV-Assisted Task Offloading in Vehicular Edge Computing Networks
Dai, X., Xiao, Z., Jiang, H., & Lui, J. C. S. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3259394 · Cited by 284
A survey of density based clustering algorithms
Bhattacharjee, P., & Mitra, P. (2021) · Frontiers of Computer Science · doi:10.1007/s11704-019-9059-3 · Cited by 271 · cited 1×
“It uses data density and closeness to its advantage to detect variable-sized and irregularly formed clusters within complicated datasets (Bhattacharjee and Mitra, 2020; Liu et al., 2023).”
BackgroundBus-Trajectory-Based Street-Centric Routing for Message Delivery in Urban Vehicular Ad Hoc Networks
Sun, G., Zhang, Y., Liao, D., Yu, H., Du, X., & Guizani, M. (2018) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2018.2828651 · Cited by 270
Research works printed but not linked: 11
- Alotaibi, M., Alhussein, M., Alqhtani, A., and Alghamdi, M. (2020). CNN: vehicle tracking in aerial images using a convolutional neural network. IEEE Access 8, 164725-164734. doi: 10.1109/ACCESS.2020.3026861 · doi:10.1109/access.2020.3026861
- Cao, J., Cholakkal, H., Anwer, R. M., Khan, F. S., Pang, Y., and Shao, L. (2020). "D2DET: towards high quality object detection and instance segmentation" in Proceedings of the IEEE/CVF Conf. On computer vision and pattern recognition (Seattle, WA), 11482-11491.
- Cao, X., Yang, X., and Xu, W. (2022). Affinity network for multi-view object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 44, 1702-1715. doi: 10.1109/TPAMI.2021.3067218 · doi:10.1109/tpami.2021.3067218
- Hinz, S., Lenhart, D., and Leitloff, J. (2006). "Detection and tracking of vehicles low framerate aerial image GIS integration car detection car tracking calculation of traffic parameters" in Image, International Society for Photogrammetry and Remote Sensing (ISPRS) (Rochester, NY).
- Kim, J., and Park, S. (2021). Hybrid approach for vehicle detection in VAID using YOLOv5 and R-FCN. J. Adv. Transport. Syst. 28, 412-423. doi: 10.1007/s11554-021-01078-5 · doi:10.1007/s11554-021-01078-5
- Kumar, R., and Singh, A. (2023). Efficient vehicle detection in UAVDT dataset using YOLOv6 and deep SORT. IEEE Trans. Intell. Transport. Syst. 34, 405-417. doi: 10.1109/ TITS.2022.3184512 · doi:10.1109/tits.2022.3184512
- Li, F., Zhang, S., Wu, Y., and Huang, L. (2018). Yolov3: a real-time vehicle tracking system based on deep learning. IEEE Access 6, 9135-9143.
- Liu, Z., Wang, X., Yu, B., Xu, X., and Yang, Y. (2019). Vehicle detection in aerial images using RetinaNet and correlation filter tracking. J. Remote Sens. Technol. 10, 134-149. doi: 10.1016/j.jrst.2019.04.003 · doi:10.1016/j.jrst.2019.04.003
- Najiya, K. V., and Archana, M.. (2018). UAV video processing for traffic surveillance with enhanced vehicle detection. In Proceedings of the International Conference on Inventive Communication and Computational Technologies, pp. 662-668.
- Nguyen, T., and Tran, P. (2018). A combined approach for vehicle detection using YOLOv2 and traditional feature-based methods. Mach. Learn. Remote Sens. 8, 89-100. doi: 10.1016/j.mlsr.2018.03.003 · doi:10.1016/j.mlsr.2018.03.003
- Zhang, X. (2020). Advanced vehicle detection in aerial images using YOLOv3 and R-FCN. J. Real-Time Image Process. 17, 77-88. doi: 10.1007/s11554-019-00843-4 · doi:10.1007/s11554-019-00843-4
Cited by
Remote Sensing Image Interpretation: Deep Belief Networks for Multi-Object Analysis
Ahmed, M. W., Alshahrani, A. S., Almjally, A., Mudawi, N. A., Algarni, A. M., Alnowaiser, K., Jalal, A., & Park, J. (2024) · IEEE Access · doi:10.1109/access.2024.3466220 · Cited by 42
“Concatenation combines the distinct characteristics of each feature set into a unified feature vector, providing a comprehensive representation of the image content [87], [88].”
BackgroundSelf-citationTarget detection and classification via EfficientDet and CNN over unmanned aerial vehicles
Yusuf, M. O., Hanzla, M., Mudawi, N. A., Sadiq, T., Alabdullah, B. I., Rahman, H., & Algarni, A. M. (2024) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2024.1448538 · Cited by 31
Self-citationRobust Human Pose Estimation and Action Recognition Over Multi-level Perceptron
Hanzla, M., Wahid, W., & Jalal, A. (2024) · International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE) · doi:10.1109/etecte63967.2024.10823803 · Cited by 16
“Sliding window techniques isolate regions of interest, separating human subjects from background clutter, while Gradient Magnitude Images capture feature variations [33].”
Self-citationUnmanned Aerial Vehicle Classification via YOLOv9 and Recurrent Neural Network
Hanzla, M., Yusuf, M. O., & Jalal, A. (2024) · International Conference on Emerging Technologies · doi:10.1109/icet63392.2024.10935181 · Cited by 12
“YOLOv9 is an efficient single-shot detector with minimal training parameters [40-42].”
Self-citationKıratlı, R., & Eroğlu, A. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01758-z · Cited by 12
“DeepSORT combines deep feature extraction and Kalman filter-based motion prediction, while EKF supports nonlinear motion models [19, 20].”
Robust Human Pose Estimation and Action Recognition over Multi-level Perceptron
Hanzla, M., Wahid, W., & Jalal, A. (2024) · International Multi-Topic Conference · doi:10.1109/inmic64792.2024.11004378 · Cited by 9
“This algorithm automatically determines the optimal threshold to separate foreground (human subjects) from background [37-40] by minimizing intra-class variance and maximizing between-class variance.”
Self-citationAutomated Gait Event Detection in Sports: A Novel Approach Using Ant Colony and XGBoost
Wahid, W., Hanzla, M., Rahman, H., & Jalal, A. (2024) · International Conference on Frontiers of Information Technology (FIT) · doi:10.1109/fit63703.2024.10838444 · Cited by 7
Self-citationIntelligent Transportation Surveillance via YOLOv9 and NASNet over Aerial Imagery
Hanzla, M., & Jalal, A. (2025) · International Conference on Advancements in Computational Sciences (ICACS) · doi:10.1109/icacs64902.2025.10937840 · Cited by 8
Self-citationMitra, R., Sourav, M. A. A., Kim, S., Gülmezoğlu, B., & Ceylan, H. (2025) · ASCE International Conference on Transportation and Development (ICTD) · doi:10.1061/9780784486191.027 · Cited by 5
Parachoori, S. K., & Sujatha, K. (2025) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126625504602 · Cited by 2
Shi, S., & Zhang, L. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.105932 · Cited by 2
Multiple Vehicle Detection and Tracking via RetinaNet with KLT Tracker
Yusuf, M. O., Hanzla, M., & Jalal, A. (2024) · International Multi-Topic Conference · doi:10.1109/inmic64792.2024.11004331 · Cited by 2
“CLAHE further improves local contrast by performing histogram equalization within tiny areas (tiles) of the image while restricting contrast amplification, resulting in increased visibility of vehicle details without generating appreciable noise or artifacts [47-50].”
Self-citationRed Light, Real-Time — AI-Powered Traffic Monitoring System
Muralisridharan, B., Mokshith, G., Nair, M. C., Velvizhi, R., & Dharani, V. (2026) · International Conference on Visual Analytics and Data Visualization (ICVADV) · doi:10.1109/icvadv67766.2026.11469766 · Cited by 1
“Wang and Yang [8] introduced multi-target pedestrian tracking pipelines with a strong focus on improvement in the accuracy of pedestrian tracking, and Hanzla et al. [9] showed the use of DeepSORT for vehicle recognition from aerial images.”
Intelligent Remote Sensing Vehicle Classification using YOLOv8 and Probabilistic Neural Network
Hanzla, M., Yusuf, M. O., & Jalal, A. (2024) · International Conference on IT and Industrial Technologies (ICIT) · doi:10.1109/icit63607.2024.10860028
Self-citationSquareTrack: A Novel Approach for Tracking Pigs in Commercial Swine Farming
Souza, J. S., Bedin, E., Maeda, V. D. A., Porto, J. V. D. A., Pistori, H., & Matsubara, E. T. (2026) · IEEE Access · doi:10.1109/access.2026.3700062
“DeepSORT [8] improves tracking by integrating appearance-based features for object re-identification; however, it uses a single threshold for detection.”
Floc detection and tracking based on improved YOLOv11n and DeepSORT
Shi, S., Li, H., & Tang, C. (2025) · International Conference on Image Processing, Object Detection, and Tracking (IPODT) · doi:10.1117/12.3092845
“…enhances the original framework by incorporating cascade matching and trajectory validation mechanisms that use threshold-based criteria to confirm trajectories, where only those meeting minimum observation counts and high matching quality are validated, significantly reducing mismatches [12] .”
Jumah, Z. H., & Chyaid, A. M. (2026) · African Journal Of Applied Research · doi:10.26437/mqagpa72
“Meanwhile, multi-object tracking has developed from motion-based methods such as SORT to the most popular DeepSORT algorithm (Hanzla et al., 2024) , which incorporates appearance embeddings to alleviate ID switches and enhance long-term identity retention in crowded traffic scenes, given their…”
An Optimized Deep Learning Framework for Vehicle Type Detection in Remote Sensing Images
Umamaheswari, R., & Avanija, J. (2026) · Contemporary Computing Innovations Conference (CCIC) · doi:10.1109/ccic68129.2026.11486239
“The standard object detectors usually have no or few abilities of generalizing to different classes of vehicles and particularly in congested and heterogeneous settings [6] .”
Zhao, L., Gao, J. Z., Mehta, Y., Ashok, A., Desharaju, D., Srinivasan, P., & Manchikanti, S. (2026) · Smart Cities · doi:10.3390/smartcities9100170
Evaluation of Deep Learning Architectures for Vehicle Recognition in Cloud-Based Systems
sirotia, R. D. N. (2024) · International Journal of Advanced Research and Multidisciplinary Trends (IJARMT)
Real Time Nighttime Object Recognition and Tracking Using YOLOv8 and DeepSORT
Nasution, M. I. A., Soraya, A., Sadikin, M., Soeheri, & Nst, M. A. E. (2026) · International Conference on Creative Communication and Innovative Technology (ICCIT) · doi:10.1109/iccit70127.2026.11748962
Metadata
- Authors
- Hanzla, M., Yusuf, M. O., Al Mudawi, N., Sadiq, T., Almujally, N. A., Rahman, H., Alazeb, A., & Algarni, A.
- Affiliations
- Air University (PK)
- University of Agder (NO)
- Princess Nourah bint Abdulrahman University (SA)
- Najran University (SA)
- Northern Border University (SA)
- Corresponding author
- Sadiq, Touseef
- Rahman, Hameedur
- ORCID
- Venue
- Frontiers in Neurorobotics
- Publisher
- Frontiers Media SA
- Published
- 2024-08-16
- Volume
- 18
- Pages
- 1430155-1430155
- ISSN
- 1662-5218 (ISSN-L)
- PMC
- PMC11362136
- OpenAlex
- W4401649156
- Cited by
- 18
- References
- 106
- Citations by year
- 2026: 5 · 2025: 5 · 2024: 8
- FWCI
- 2.52
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Neurorobotics (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Najran University (PNURSP2024R410)
- Northern Border University (NBU-FFR-2024-)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- vehicle identification, vehicle tracking, DeepSORT, aerial images, unmanned aerial vehicles, traffic monitoring, fuzzy c-means segmentation, YOLOv8, ORB features, multi-target tracking, VEDAI dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.