CoChat
Sign Up
Cited by 55Advanced Neural Network ApplicationsAutonomous Vehicle Technology and SafetyDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Enhanced YOLOv5: An Efficient Road Object Detection Method

Open access
Chen, Hao, Chen, Zhan, Yu, Hang·2023·Sensors
DOI 10.3390/s23208355PMC PMC10611198
Open this paper in CoChat — free accountOpen PDF

Abstract

Accurate identification of road objects is crucial for achieving intelligent traffic systems. However, developing efficient and accurate road object detection methods in complex traffic scenarios has always been a challenging task. The objective of this study was to improve the target detection algorithm for road object detection by enhancing the algorithm's capability to fuse features of different scales and levels, thereby improving the accurate identification of objects in complex road scenes. We propose an improved method called the Enhanced YOLOv5 algorithm for road object detection. By introducing the Bidirectional Feature Pyramid Network (BiFPN) into the YOLOv5 algorithm, we address the challenges of multi-scale and multi-level feature fusion and enhance the detection capability for objects of different sizes. Additionally, we integrate the Convolutional Block Attention Module (CBAM) into the existing YOLOv5 model to enhance its feature representation capability. Furthermore, we employ a new non-maximum suppression technique called Distance Intersection Over Union (DIOU) to effectively address issues such as misjudgment and duplicate detection when significant overlap occurs between bounding boxes. We use mean Average Precision (mAP) and Precision (P) as evaluation metrics. Finally, experimental results on the BDD100K dataset demonstrate that the improved YOLOv5 algorithm achieves a 1.6% increase in object detection mAP, while the P value increases by 5.3%, effectively improving the accuracy and robustness of road object recognition.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.3390/s23208355

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 10 The BiFPN feature fusion process.
Figure 10 The BiFPN feature fusion process.CC BY · PubMed Central
Figure 1 Structural diagram of the YOLOv5 network.
Figure 1 Structural diagram of the YOLOv5 network.CC BY · PubMed Central
Figure 2 CBS convolutional layer.
Figure 2 CBS convolutional layer.CC BY · PubMed Central
Figure 3 Schematic diagram of the C3 module.
Figure 3 Schematic diagram of the C3 module.CC BY · PubMed Central
Figure 4 Schematic diagram of the SPPF module.
Figure 4 Schematic diagram of the SPPF module.CC BY · PubMed Central
Figure 5 Schematic diagram of the FPN fusion structure.
Figure 5 Schematic diagram of the FPN fusion structure.CC BY · PubMed Central
Figure 6 Schematic diagram of the PANet fusion structure.
Figure 6 Schematic diagram of the PANet fusion structure.CC BY · PubMed Central
Figure 7 Schematic diagram of the detection process. (a) Anchor box. (b) Real box.
Figure 7 Schematic diagram of the detection process. (a) Anchor box. (b) Real box.CC BY · PubMed Central
Figure 8 Structural diagram of the improved YOLOv5 network.
Figure 8 Structural diagram of the improved YOLOv5 network.CC BY · PubMed Central
Figure 9 Structural diagram of the BiFPN fusion structure.
Figure 9 Structural diagram of the BiFPN fusion structure.CC BY · PubMed Central
Figure 11 Structural diagram of the CBAM module.
Figure 11 Structural diagram of the CBAM module.CC BY · PubMed Central
Figure 12 Structural diagram of channel attention mechanism.
Figure 12 Structural diagram of channel attention mechanism.CC BY · PubMed Central
Figure 13 Structural diagram of the spatial attention mechanism.
Figure 13 Structural diagram of the spatial attention mechanism.CC BY · PubMed Central
Figure 14 Definition of IOU.
Figure 14 Definition of IOU.CC BY · PubMed Central
Figure 15 Structural diagram of DIoU.
Figure 15 Structural diagram of DIoU.CC BY · PubMed Central
Figure 16 Various road traffic flows in the Bdd100k dataset. (a) Free flow. (b) Mixed flow. (c) Congested flow. (d) Slow flow.
Figure 16 Various road traffic flows in the Bdd100k dataset. (a) Free flow. (b) Mixed flow. (c) Congested flow. (d) Slow flow.CC BY · PubMed Central
Figure 17 Before and after PR curve comparison. (a) Before PR curve comparison. (b) After PR curve comparison.
Figure 17 Before and after PR curve comparison. (a) Before PR curve comparison. (b) After PR curve comparison.CC BY · PubMed Central
Figure 18 Comparison of road object detection results based on mixed flow in different light conditions.
Figure 18 Comparison of road object detection results based on mixed flow in different light conditions.CC BY · PubMed Central
Figure 19 Comparison of road object detection results based on mixed flow in rainy conditions. (a) YOLOv5 original algorithm. (b) The proposed algorithm.
Figure 19 Comparison of road object detection results based on mixed flow in rainy conditions. (a) YOLOv5 original algorithm. (b) The proposed algorithm.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

Show all 34 references

Research works printed but not linked: 8

  1. Sifre, L. (2014). Rigid-Motion Scattering for Image Classifification. [Ph.D. Thesis, École Polytechnique].
  2. Liu, S., Huang, D., and Wang, Y. (2019). Learning spatial fusion for single-shot object detection. arXiv.
  3. Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and LeCun, Y. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv.
  4. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
  5. Bochkovskiy, A., Wang, C., and Liao, H. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
  6. Terven, J., and Cordova-Esparza, D. (2023). A Comprehensive Review of YOLO: From YOLOv1 and Beyond. arXiv.
  7. Zagoruyko, S., and Komodakis, N. (2016). Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv.
  8. Küppers, F., Haselhoff, A., Kronenberger, J., and Schneider, J. (2022). Deep Neural Networks and Data for Automated Driving: Robustness, Uncertainty Quantification, and Insights Towards Safety, Springer.

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Chen, H., Chen, Z., & Yu, H.
Affiliations
Tianjin Chengjian University (CN)
Corresponding author
Chen, Zhan
ORCID
Venue
Sensors
Publisher
MDPI AG
Published
2023-10-10
Volume
23
Issue
20
Pages
8355
ISSN
1424-8220 (ISSN-L)
DOI
10.3390/s23208355
PMC
PMC10611198
OpenAlex
W4387494972
Cited by
49
References
34
Citations by year
2026: 5 · 2025: 23 · 2024: 21
FWCI
4.45
Type
journal article
Language
en
Open access
Licence
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
traffic object detection, YOLOv5, BiFPN, CBAM, multi-scale feature fusion, intelligent transportation systems, bounding box overlap

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