Improved YOLO-V3 with DenseNet for Multi-Scale Remote Sensing Target Detection
Open accessThe 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.
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
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 1×
“The other ones are one-stage target detection algorithms including SSD (Single Shot Multibox Detector) [31–33], DSSD (Deconvolution Single Shot Multibox Detector) [34], FSSD (Feature Fusion Single Shot Multibox Detector) [35], YOLO [36], YOLO-V2 [37], and YOLO-V3 [38].”
BackgroundRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
(2016) · Cited by 31,590
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
AugFPN: Improving Multi-Scale Feature Learning for Object Detection
Guo, C., Fan, B., Zhang, Q., Xiang, S., & Pan, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01261 · Cited by 588 · cited 3×
“Abbreviations: The abbreviations in this paper are as follows: YOLO You Only Look Once CV Computer Version SVM Support Vector Machine HOG Histograms of Oriented Gradients DPM Deformable Parts Model IOU Intersection over Union FC Full Connected Layer FCN Full Convolutional Network CNN Convolutional Neural Network GT Gr…”
MethodYOLO v3-Tiny: Object Detection and Recognition using one stage improved model
Adarsh, P., Rathi, P., & Kumar, M. (2020) · 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs48705.2020.9074315 · Cited by 545 · cited 1×
“At present, numerous state-of-the-art target detection models with higher speed are proposed based on YOLO such as YOLO-V3 tiny [39] and TF-YOLO [40].”
Background
Research works printed but not linked: 4
- Shen, 2017, Building Detection from High Resolution Remote Sensing Imagery Based on a Deformable Part Model, Geomat. Inf. Sci. Wuhan Univ., 42, 1285
- Li, X., Shang, M., Qin, H., and Chen, L. (2015). Fast Accurate Fish Detection and Recognition of Underwater Images with Fast R-CNN, IEEE.
- 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.
- Bochkovskiy, A., Chien-Yao, W., and Liao, H.Y.M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv.
Cited by
Items 101–141 of 141
Improved YOLOv5 Algorithm for Oriented Object Detection of Aerial Image
Yang, G., Wang, M., Zhou, Q., Li, J., Zhou, S., & Lu, Y. (2024) · Sensors and Materials · doi:10.18494/sam5136 · Cited by 2
Yu, X., Xiang, W., Lu, Y., Han, K., & Yang, Y. W. (2025) · Remote Sensing · doi:10.3390/rs17173042 · Cited by 3
SwinT-SRGAN: Swin Transformer Enhanced Generative Adversarial Network for Image Super-Resolution
Liu, Q., Chen, L., Sun, Y., & Liu, L. (2025) · Electronics · doi:10.3390/electronics14173511 · Cited by 2
Wang, J., Liu, J., Wang, K., Pan, Z., Wang, Z., Chen, C., Yao, Y., & Li, T. (2025) · Measurement · doi:10.1016/j.measurement.2025.119614 · Cited by 2
Forest Pest Detection Method Based on DenseNet and Pyramid Pooling
Yin, X., Song, Y., He, T., Song, B., & Li, G. (2021) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc54389.2021.9674332 · Cited by 3
“To make up for the simple network structure[11], DenseNet is regarded as the feature extraction network of YOLOv3-tiny to enhance the feature extraction capability of the network and enable the network to extract high semantic features of images[12],[13] .”
MethodRecognition model for coated red clover seeds using YOLOv5s optimized with an attention module
Zhang, X., Xuan, C., & Hou, Z. (2023) · International journal of agricultural and biological engineering · doi:10.25165/j.ijabe.20231606.7773 · Cited by 7
Peng, S. (2024) · Service Oriented Computing and Applications · doi:10.1007/s11761-024-00401-2 · Cited by 2
“[8].”
Musci, M., Carvalho, C. V. D. A., Serrão, G. D. M. P., Ferreira, M. V. E. N. B., Guerra, M. D. P., & Cardoso, A. M. (2024) · Revista de Gestão Social e Ambiental · doi:10.24857/rgsa.v18n9-109 · Cited by 2
DDM-YOLOv8s for Small Object Detection in Remote Sensing Images
Xi, Y., Qu, D., & Du, L. (2024) · International Conference on Machine Learning and Natural Language Processing (MLNLP) · doi:10.1109/mlnlp63328.2024.10800055 · Cited by 2
“…feature weight [5] ; Through DenseConnection, enhance information transmission and sharing between levels, and expand the reuse range of features [6] ; Optimize the anchor frame mechanism [7] , loss function [8] ; Using adaptive pruning compression algorithm to improve reasoning speed [9];…”
MSFE-Net: Multi-Scale Feature Enhancement Network for Remote Sensing Object Detection
Yuan, K., Li, X., Ren, Y., Zhang, L., Liu, W., & Li, E. (2025) · Applied Artificial Intelligence · doi:10.1080/08839514.2025.2514324 · Cited by 5
“Xu and Wu (2020) integrated DenseNet (Huang et al. 2017) with YOLOv3 (Redmon and Farhadi 2018) to enhance multi-scale feature extraction for remote sensing targets.”
Aircraft Target Detection in Satellite Remote Sensing Images Based on Improved YOLOv5
Liu, Z., Gao, Y., Wang, L., & Du, Q. (2022) · International Conference on Cyber-Physical Social Intelligence (ICCSI) · doi:10.1109/iccsi55536.2022.9970631 · Cited by 2
“Reference [9] proposed to use DenseNet to improve YOLOv3 [7], and the comprehensive performance indications for remote sensing images were improved by improving the structure of the Backbone.”
MethodA new method based on YOLOv5 for remote sensing object detection
Chen, H., Tan, S., Xie, Z., & Liu, Z. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055729 · Cited by 2
“For example, Lang et al. [5] proposed a lightweight detection algorithm that can be deployed on edge devices through the channel attention mechanism, and solved large variant in object scales through generating the optimal anchor by differential evolution.”
BackgroundImproved YOLOv5 Network Method for Remote Sensing Image Based Ground Objects RecognitionPreprint
Xue, J., Shandong University of Science and Technology, Zheng, Y., Dongye, C., Wang, P., & Yasir, M. (2022) · Research Square · doi:10.21203/rs.3.rs-1224458/v1 · Cited by 2
Silva, J. C. P., Nogueira, F. D. C., Honório, D. D. D. C., Shiguemori, E. H., & Pássaro, A. (2024) · Journal of Aerospace Technology and Management · doi:10.1590/jatm.v16.1353 · Cited by 1
Do, M.-T., Ha, M.-H., Le, M., & Tzyh-Chiang, O. (2025) · EAI Endorsed Transactions on Industrial Networks and Intelligent Systems · doi:10.4108/eetinis.v12i4.8279 · Cited by 1
“Further developments, such as incorporating DenseNet into YOLOv3, improved detection accuracy at the expense of increased complexity and reduced speed [8].”
Artificial intelligence for remote sensing and climate monitoring
Tang, H., Bhatti, U. A., Li, D., Lisi, D., Liu, J., & Bhatti, M. A. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-24712-5.00004-x · Cited by 2
A DenseNet-YOLOv8 Fusion Model for Intelligent Parasite Egg Detection and Classification
Zia, M. B., Zhou, X., Gururajan, R., & Chan, K. C. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6786-7_23 · Cited by 1
Bo, S., Wei, Z., Lu, Y., Hao, X., Wang, Y., & Zhou, P. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01946-5 · Cited by 1
Convolution Neural Network Approach for Satellite Object Detection and Recognition
Suganthi, M., & Akila, C. (2023) · International Conference on Networks, Multimedia and Information Technology (NMITCON) · doi:10.1109/nmitcon58196.2023.10276192 · Cited by 1
“High-level information extracted from pictures may be employed by unmanned aerial vehicles (UAVs) are increasingly employed in the core function of defensive systems, target detection, and then given to decision support systems [1].”
BackgroundImproved YOLOv5 Object Detection Algorithm for Remote Sensing Images
Duan, X., & Huang, W. D. (2023) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv59470.2023.10329114 · Cited by 1
“Reference [8] advocated using DenseNet [9] to increase YOLOv3 and the detection accuracy of remote sensing images by strengthening the structure in Backbone.”
MethodImproved YOLOv7 UAV image small target detection algorithm
Bo, W. Y., Zhi, 刘. L., & Bo, W. Y. (2023) · doi:10.1145/3638584.3638651 · Cited by 1
“Xu et al [4] proposed to introduce methods such as dense connected network in the feature extraction network of YOLOv3, which efficiently extracts the feature information of the image and solves the problems arising from the insufficient extraction of feature information, but the method is unable…”
MethodLaboratory Dangerous Operation Behavior Detection System Based on Deep Learning Algorithm
Zhang, D. (2024) · International Journal of Digital Crime and Forensics · doi:10.4018/ijdcf.340934 · Cited by 1
Detection and Recognition of Poppy in UAV Imagery Based on Deep Neural Networks
Yao, B., & Wang, W. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10958055 · Cited by 2
“For instance, Xu et al. [14] introduced the DenseNet network to enhance YOLOv3's performance by expanding detection scales to four levels, which improved the mean average precision (mAP) of the RSOD remote sensing dataset from 77.10% to 88.73%, achieving significant advancements, especially in…”
InfluentialUnutmaz, B., & Erer, I. (2022) · Conference on Information Sciences and Systems · doi:10.1109/ciss53076.2022.9751159 · Cited by 1
Sedelnikov, A. V., Skidanov, R. V., Manukyan, L. A., Ivanushkin, M. A., & Mordanov, M. (2024) · Preprints.org · doi:10.20944/preprints202407.1899.v1 · Cited by 1
A Multi-target Edge Service Approach to Real-time Image Object Detection
Xin, T., Li, S., Zhao, T., Xia, W., & Zhao, L. (2020) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid51228.2020.00104
“Traditional approaches to object detection [18,19,20] need to locate the Bounding-box of the object.”
BackgroundClassification of License Plate Images from Real-Time Vehicles Using Generative Adversarial Network
Rajesh Sharma, R. (2021) · Bioscience Biotechnology Research Communications · doi:10.21786/bbrc/14.7.51
Analysis of object detection models and their sampling features for Time series Forecasting MethodsPreprint
Mani, P. (2022) · Research Square · doi:10.21203/rs.3.rs-1914139/v1
Based on the improved YOLOv3 remote sensing target detection algorithm
Feng, H., & Wang, Z. (2022) · International Conference on Networks, Communications and Information Technology (CNCIT) · doi:10.1109/cncit56797.2022.00014
“Xu[6] introduced densenet into YOLOv3 feature extraction network instead of partial residual connection, and formed a feature extraction network together with residual connection network to detect remote sensing targets.”
BackgroundMethodEnhancing YOLOv3-tiny for Mask Detection in Natural Scenes
Cheng, X., Wang, J., & Goh, S. K. (2022) · IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC) · doi:10.1109/icftic57696.2022.10075285
“3) and (4) [14].”
Apeh, S. T., Ajao, L. A., Nyitamen, D. S., Robbinson, C. L., & Wamdeo, E. (2024) · Research Square · doi:10.21203/rs.3.rs-4150504/v1
Lightweight remote sensing object detection algorithm for spaceborne edge computation
Dong, X., Xing, F., Chen, B., Sun, T., & Liang, W. Y. (2024) · International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP) · doi:10.1117/12.3029616
“Xu et al. [4-6] conducted various improvements on YOLO, adopted a densely connected network to enhance feature extraction capability, and introduced the concept of multi-receptive field fusion and a series of feature enhancement modules, all leading to improved accuracy on remote sensing datasets…”
BackgroundAutomatic Fruit Detection Based on Robotic Vision
Chen, Y., Yao, R., Liu, H., Liu, B., & Liu, M. (2024) · International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE) · doi:10.1109/icbase63199.2024.10762508
An Expert System for Army Vehicle Detection and Classification Utilizing YOLOv8
Babu, N. A., Rupa, C., Rishika, G. N. V., Naveena, M., & Sekhar, M. M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-3287-9_15
AK-YOLOv9: Improved Object Detection for Pollutants in Rivers Discharging into the Sea
Wen, L., Wu, M., Lai, J., Lu, L., & Liu, X. (2025) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3083/1/012003
On‐Orbit Fast Small Target Detection Method Based on the Improved YOLOv5 Model
Li, Q., & Zhu, Z. (2025) · International Journal of Aerospace Engineering · doi:10.1155/ijae/5533761
“Xu D et al. used DenseNet (Densely Connected Network) to enhance the feature extraction capability of YOLOv3, and improved its mAP by 12.12% for small target detection such as airplanes [15].”
InfluentialLiang, C., Zhang, J., Yin, D., Guo, X., & Chao, B. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae31a7
“Its advantages in feature extraction, multi-scale object recognition, and real-time performance have made it a key factor in overcoming the limitations of traditional inspection methods [7, 8].”
EagleEye-DETR: a novel detector for small objects in remote sensing images
Liang, Y., Wang, L., chen, P., Guan, J., Li, J., He, G., & Chen, H. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae3cfe
Research on Performance Improvement of Deep Learning Models for Small Target Detection
Qiu, C., Liang, H., & Huang, Q. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347193
“Nonetheless, its high computational complexity limits its performance in real-time applications[12].”
Chahba, M., Zarboubi, M., Bellout, A., ba, A. A., Hmache, F., Dliou, A., Saddik, A., & Bouharroud, R. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-18857-1_33
Lu, Y., Manaf, S. A., Aris, T. N. M., & Manshor, N. B. (2026) · Remote Sensing Letters · doi:10.1080/2150704x.2026.2667243
“YOLOv3 introduced multi-scale prediction to improve detection of small and medium-sized objects, making it suitable for real-time applications in remote sensing (Xu and Wu 2020).”
Metadata
- Authors
- Xu, D., & Wu, Y.
- Affiliations
- Nanjing University of Aeronautics and Astronautics (CN)
- Corresponding author
- Wu, Yiquan
- ORCID
- Wu, Yiquan
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2020-07-31
- Volume
- 20
- Issue
- 15
- Pages
- 4276
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC7435986
- 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
- gold
- doi.org
- Licence
- 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.