CoChat

Vehicle recognition pipeline via DeepSort on aerial image datasets

Open access

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3389/fnbot.2024.1430155

Cites

103 of 103 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Flowchart demonstrating the proposed traffic surveillance system proposed system architecture.
Figure 1 Flowchart demonstrating the proposed traffic surveillance system proposed system architecture.CC BY · PubMed Central
Figure 2 Defogging results over the (A) original image of VEDAI dataset (B) defogged image (C) original image of SRTID dataset (D) defogged image.
Figure 2 Defogging results over the (A) original image of VEDAI dataset (B) defogged image (C) original image of SRTID dataset (D) defogged image.CC BY · PubMed Central
Figure 3 Pre-processed image using gamma correction over the (A) VEDAI dataset (B) SRTID dataset.
Figure 3 Pre-processed image using gamma correction over the (A) VEDAI dataset (B) SRTID dataset.CC BY · PubMed Central
Figure 4 Segmentation using FCM over (A) VEDAI dataset and (B) SRTID dataset.
Figure 4 Segmentation using FCM over (A) VEDAI dataset and (B) SRTID dataset.CC BY · PubMed Central
Figure 5 Segmentation using DBSCAN over (A) VEDAI dataset and (B) SRTID dataset.
Figure 5 Segmentation using DBSCAN over (A) VEDAI dataset and (B) SRTID dataset.CC BY · PubMed Central
Figure 6 Vehicle Detection over (A) VEDAI and (B) SRTID datasets marked with red boxes via the YOLOv8 algorithm.
Figure 6 Vehicle Detection over (A) VEDAI and (B) SRTID datasets marked with red boxes via the YOLOv8 algorithm.CC BY · PubMed Central
Figure 7 ID assignment and restoration: (A) ID assigned to each vehicle based on ORB features; (B) features matching across frames; (C) ID restored for the same vehicle in succeeding frame.
Figure 7 ID assignment and restoration: (A) ID assigned to each vehicle based on ORB features; (B) features matching across frames; (C) ID restored for the same vehicle in succeeding frame.CC BY · PubMed Central
Figure 8 Density estimation by using vehicle count displayed at the left corner of each image.
Figure 8 Density estimation by using vehicle count displayed at the left corner of each image.CC BY · PubMed Central
Figure 9 Steps of vehicle tracking using DeepSORT algorithm.
Figure 9 Steps of vehicle tracking using DeepSORT algorithm.CC BY · PubMed Central
Figure 10 Tracking results using DeepSORT tracker across the image frames (A) Vehicle dectection only (B). Multiple-object detection (0 = Vehicles, 1 = Bike, 2 = Pedestrians in frames).
Figure 10 Tracking results using DeepSORT tracker across the image frames (A) Vehicle dectection only (B). Multiple-object detection (0 = Vehicles, 1 = Bike, 2 = Pedestrians in frames).CC BY · PubMed Central
Figure 11 Tracking performance comparison of DeepSORT and ByteTrack across datasets.
Figure 11 Tracking performance comparison of DeepSORT and ByteTrack across datasets.CC BY · PubMed Central

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 10

  1. Alotaibi, 2020, CNN: vehicle tracking in aerial images using a convolutional neural network, IEEE Access, 8, 164725, 10.1109/access.2020.3026861 · doi:10.1109/access.2020.3026861
  2. Cao, 2020, D2DET: towards high quality object detection and instance segmentation, 11482
  3. Cao, 2022, Affinity network for multi-view object detection, IEEE Transactions on Pattern Analysis and Machine Intelligence., 44, 1702, 10.1109/tpami.2021.3067218 · doi:10.1109/tpami.2021.3067218
  4. Hinz, 2006, Detection and tracking of vehicles low framerate aerial image GIS integration car detection car tracking calculation of traffic parameters
  5. Kim, 2021, Hybrid approach for vehicle detection in VAID using YOLOv5 and R-FCN, J. Adv. Transport. Syst., 28, 412, 10.1007/s11554-021-01078-5 · doi:10.1007/s11554-021-01078-5
  6. Kumar, 2023, Efficient vehicle detection in UAVDT dataset using YOLOv6 and deep SORT, IEEE Trans. Intell. Transport. Syst., 34, 405, 10.1109/tits.2022.3184512 · doi:10.1109/tits.2022.3184512
  7. Li, 2018, Yolov3: a real-time vehicle tracking system based on deep learning, IEEE Access, 6, 9135
  8. Liu, 2019, Vehicle detection in aerial images using RetinaNet and correlation filter tracking, J. Remote Sens. Technol., 10, 134, 10.1016/j.jrst.2019.04.003 · doi:10.1016/j.jrst.2019.04.003
  9. Nguyen, 2018, A combined approach for vehicle detection using YOLOv2 and traditional feature-based methods, Mach. Learn. Remote Sens., 8, 89, 10.1016/j.mlsr.2018.03.003 · doi:10.1016/j.mlsr.2018.03.003
  10. Zhang, 2020, Advanced vehicle detection in aerial images using YOLOv3 and R-FCN, J. Real-Time Image Process., 17, 77, 10.1007/s11554-019-00843-4 · doi:10.1007/s11554-019-00843-4

Cited by

See all 21

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
Venue
Frontiers in Neurorobotics
Published
2024-08-16
Volume
18
Pages
1430155-1430155
ISSN
1662-5218 (ISSN-L)
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
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.