Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index; 1 of the 7 sources its claims cite were checked for support.

Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack

Open access

Abstract

Vehicle detection and tracking technology plays a crucial role in Intelligent Transportation Systems. However, due to factors such as complex scenarios, diverse scales, and occlusions, issues like false detections, missed detections, and identity switches frequently occur. To address these problems, this paper proposes a multi-object vehicle detection and tracking algorithm based on CDS-YOLOv8 and improved ByteTrack. For vehicle detection, the Context-Guided (CG) module is introduced during the downsampling process to enhance feature extraction capabilities in complex scenarios. The Dilated Reparam Block (DRB) is reconstructed to tackle multi-scale issues, and Soft-NMS replaces the traditional NMS to improve performance in densely populated vehicle scenarios. For vehicle tracking, the state vector and covariance matrix of the Kalman filter are improved to better handle the nonlinear movement of vehicles, and Gaussian Smoothed Interpolation (GSI) is introduced to fill in trajectory gaps caused by detection misses. Experiments conducted on the UA-DETRAC dataset show that the improved algorithm increases detection performance, with mAP@0.5 and mAP@0.5:0.95 improving by 9% and 8.8%, respectively. In terms of tracking performance, mMOTA improves by 6.7%. Additionally, comparative experiments with mainstream detection and two-stage tracking algorithms demonstrate the superior performance of the proposed algorithm.

Overview

CoChat Summary

TL;DR

The paper proposes CDS-YOLOv8, which adds Context-Guided downsampling, a reconstructed Dilated Reparam Block in C2f, and Soft-NMS, plus an improved ByteTrack with a modified Kalman filter and Gaussian Smoothed Interpolation. On UA-DETRAC, it reports detection mAP@0.5 and mAP@0.5:0.95 improvements of 9% and 8.8%, and tracking mMOTA improvement of 6.7%.

Key findings

  • Detector ablation: baseline YOLOv8-S reached 64.2% mAP@0.5, 46.6% mAP@0.5:0.95, and 28.8 G Flops; final CDS-YOLOv8 reached 73.2% mAP@0.5, 55.4% mAP@0.5:0.95, and 26.6 G Flops, with P +10.6%, R +3.7%, mAP@0.5 +9%, mAP@0.5:0.95 +8.8%, and Flops reduced by 2.2 G.
  • Detector comparison: CDS-YOLOv8 reported 73.2% mAP@0.5 and 55.4% mAP@0.5:0.95 at 26.6 G Flops, surpassing YOLOv9-S (65.1%, 48.0%, 39.6 G) and YOLOv8-L (71.6%, 51.4%, 165.7 G), with improvements of 1.6% and 4% over YOLOv8-L in mAP@0.5 and mAP@0.5:0.95.
  • Tracker ablation: final CDS-YOLOv8 + ByteTrack + improved KF + GSI achieved 80.3% mIDF1, 530 IDS, and 73.9% mMOTA, versus YOLOv8s + ByteTrack at 76.9% mIDF1, 855 IDS, and 67.2% mMOTA; overall mIDF1 +3.4%, IDS −325, mMOTA +6.7%.
  • Tracker comparison: improved ByteTrack reported 80.3% mIDF1, 530 IDS, and 73.9% mMOTA, compared with BoT-SORT at 78.6%, 727, and 72.9%; the paper notes its method does not use ReID.

Methods

  • Dataset: UA-DETRAC, with 10 h of video at 25 fps, over 140,000 frames and 1.21 million annotated boxes; training set 60 sequences/83,791 images and test set 40 sequences/56,340 images. After excluding unlabeled images and sampling every 10th frame, 8209 images were used for training and 5617 for evaluation; tracking used 40 test video sequences.
  • Model: YOLOv8-S baseline; CG module introduced during downsampling; reconstructed DRB integrated with C2f; Soft-NMS replaces traditional NMS. Tracking uses ByteTrack as base, with improved Kalman filter state vector using center coordinates, width, and height plus time-varying Q and R, and GSI using Gaussian Process Regression/RBF to fill trajectory gaps; unmatched tracklets are deleted after more than 30 frames.
  • Training/evaluation: RTX 4090, Core i9-9900K @ 3.60 GHz, Windows 10, PyTorch 1.31.1, CUDA 11.6, Python 3.8; 200 epochs, batch size 32, no pre-trained weights. Detection metrics: P, R, mAP@0.5, mAP@0.5:0.95; tracking metrics: MOTA, IDF1, IDS.

Limitations

  • The paper does not explicitly state limitations; it only states future work will explore infrared images, radar, and other modalities.
  • Evident from the text: all reported experiments use only the UA-DETRAC dataset, with no cross-dataset or real-world deployment validation reported.
  • Evident from the text: no runtime, FPS, or speed measurements are reported, despite claims about balancing tracking speed and accuracy and about ReID reducing operating speed.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/electronics13153033

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

1 Valid · 1 Not valid · 6 Not checked · 47 Own results and interpretations

19 more claims

Create a free account to see all 55 claims and every source verdict.

See all claims — free account
  • It may state two separate claims as one. 29
  • Probably not a substantial claim. 7

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Show all 37 references

Cited by

Metadata

Authors
You, L., Chen, Y., Xiao, C., Sun, C., & Li, R.
Affiliations
China West Normal University (CN)
Corresponding author
Chen, Yajun
Venue
Electronics
Publisher
MDPI AG
Published
2024-08-01
Volume
13
Issue
15
Pages
3033
ISSN
2079-9292 (ISSN-L)
OpenAlex
W4401211089
Cited by
42
References
37
Citations by year
2026: 24 · 2025: 14 · 2024: 4
FWCI
5.85
Type
journal article
Language
en
Open access
Locations
Electronics (publishedVersion, cc-by)
Funders
China West Normal University (463177)
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 detection, multi-target tracking, YOLOv8, ByteTrack, multi-scale feature extraction, Soft-NMS, Kalman filter, occlusion handling, identity switching, intelligent transportation systems, UA-DETRAC

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-09-28, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

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.