CoChat

Improved YOLO-V3 with DenseNet for Multi-Scale Remote Sensing Target Detection

Open access
Xu, Danqing, Wu, Yiquan · 2020 · Sensors

The DOI matches its Crossref record; 54 of the 55 references it cites were found in a registry or an index.

Abstract

Remote sensing targets have different dimensions, and they have the characteristics of dense distribution and a complex background. This makes remote sensing target detection difficult. With the aim at detecting remote sensing targets at different scales, a new You Only Look Once (YOLO)-V3-based model was proposed. YOLO-V3 is a new version of YOLO. Aiming at the defect of poor performance of YOLO-V3 in detecting remote sensing targets, we adopted DenseNet (Densely Connected Network) to enhance feature extraction capability. Moreover, the detection scales were increased to four based on the original YOLO-V3. The experiment on RSOD (Remote Sensing Object Detection) dataset and UCS-AOD (Dataset of Object Detection in Aerial Images) dataset showed that our approach performed better than Faster-RCNN, SSD (Single Shot Multibox Detector), YOLO-V3, and YOLO-V3 tiny in terms of accuracy. Compared with original YOLO-V3, the mAP (mean Average Precision) of our approach increased from 77.10% to 88.73% in the RSOD dataset. In particular, the mAP of detecting targets like aircrafts, which are mainly made up of small targets increased by 12.12%. In addition, the detection speed was not significantly reduced. Generally speaking, our approach achieved higher accuracy and gave considerations to real-time performance simultaneously for remote sensing target detection.

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 · 10.3390/s20154276

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The network of You Only Look Once (YOLO)-V3.
Figure 1 The network of You Only Look Once (YOLO)-V3.CC BY · PubMed Central
Figure 2 The structure of DenseNet.
Figure 2 The structure of DenseNet.CC BY · PubMed Central
Figure 3 The structure diagram of the feature extraction network.
Figure 3 The structure diagram of the feature extraction network.CC BY · PubMed Central
Figure 4 The Structure of the proposed network.
Figure 4 The Structure of the proposed network.CC BY · PubMed Central
Figure 5 The relationship between the number of clusters and average IOU by K-means clustering.
Figure 5 The relationship between the number of clusters and average IOU by K-means clustering.CC BY · PubMed Central
Figure 6 The final prediction.
Figure 6 The final prediction.CC BY · PubMed Central
Figure 7 The samples of the datasets: (a) the samples of remote sensing object detection (RSOD) dataset and (b) the samples of dataset of object detection in aerial images (UCS-AOD) dataset.
Figure 7 The samples of the datasets: (a) the samples of remote sensing object detection (RSOD) dataset and (b) the samples of dataset of object detection in aerial images (UCS-AOD) dataset.CC BY · PubMed Central
Figure 8 The detection results of the improved You Only Look Once (YOLO)-V3.
Figure 8 The detection results of the improved You Only Look Once (YOLO)-V3.CC BY · PubMed Central
Figure 9 The comparison results of YOLO-V3 and our approach: (a1–a8) The detection results of YOLO-V3; (b1–b8) The detection results of Faster RCNN; (c1–c8) The detection results of our approach.
Figure 9 The comparison results of YOLO-V3 and our approach: (a1–a8) The detection results of YOLO-V3; (b1–b8) The detection results of Faster RCNN; (c1–c8) The detection results of our approach.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: 4

  1. Shen, 2017, Building Detection from High Resolution Remote Sensing Imagery Based on a Deformable Part Model, Geomat. Inf. Sci. Wuhan Univ., 42, 1285
  2. Li, X., Shang, M., Qin, H., and Chen, L. (2015). Fast Accurate Fish Detection and Recognition of Underwater Images with Fast R-CNN, IEEE.
  3. Kaiming, H., Gkioxari, G., Dollar, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.
  4. Bochkovskiy, A., Chien-Yao, W., and Liao, H.Y.M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv.

Cited by

See all 141

Metadata

Authors
Xu, D., & Wu, Y.
Affiliations
Nanjing University of Aeronautics and Astronautics (CN)
Corresponding author
Wu, Yiquan
Venue
Sensors
Publisher
MDPI AG
Published
2020-07-31
Volume
20
Issue
15
Pages
4276
ISSN
1424-8220 (ISSN-L)
OpenAlex
W3046857037
Cited by
141
References
55
Citations by year
2026: 5 · 2025: 21 · 2024: 27 · 2023: 32 · 2022: 32 · 2021: 20 · 2020: 4
FWCI
8.55
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Natural Science Foundation of China (61573183)
  • National Laboratory of Pattern Recognition (201900029)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
Keywords
YOLOv3, DenseNet, multi-scale object detection, feature extraction, aerial images, small object detection, aircraft detection, real-time detection

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.