YOLOv3-DPFIN: A Dual-Path Feature Fusion Neural Network for Robust Real-Time Sonar Target Detection
The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Real-time detection of sonar target plays a vital role in the underwater research field. Conventionaldeep learning methods need large quantities of sonar images as the sample for model training, and they cannot ensure detection speed and feature extraction ability simultaneously. For sonar dataset with small effective sample and low Signal-to-Noise Ratios (SNR), an improved YOLOv3 algorithm for real-time detection called as YOLOv3-DPFIN is proposed. The objective of the proposed YOLOv3-DPFIN is to accomplish the accurate detection of noise-intensive multi-category sonar targets with minimum time consumption. The proposed model conducts efficient feature extraction via the Dual-Path Network (DPN) module and the fusion transition module, and adopts a dense connection method to improve multi-scale prediction, which can complete precise object classification and location. The experimental results show that the algorithm achieves 84.4% mAP75 with 56fps on a Nvidia Titan Xp, when testing on the sonar dataset and using the new VOC2012 mAP standard, which can meet the requirement of robust real-time detection for both raw and noised sonar targets. Moreover, the precision and speed of the proposed YOLOv3-DPFIN are superior to the original YOLOv3 model and state-of-the-art improved SSD models.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“Additionally, with the advent of ResNet [25], DenseNet [8], and DPN [26] networks, the neural networks are greatly deepened, which makes the feature extraction capability of convolutional neural networks more compelling.”
BackgroundMethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“For example, LeNet [19], AlexNet [20], VGG-Nets [21], and GoogLeNet [22]–[24] have performed well in various fields.”
BackgroundImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“For example, LeNet [19], AlexNet [20], VGG-Nets [21], and GoogLeNet [22]–[24] have performed well in various fields.”
BackgroundFaster 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 · cited 1×
“Representative algorithms include RCNN [1], Fast RCNN [2], Faster RCNN [3], and Mask RCNN [4].”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 1×
“Representative algorithms include RCNN [1], Fast RCNN [2], Faster RCNN [3], and Mask RCNN [4].”
MethodGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“For example, LeNet [19], AlexNet [20], VGG-Nets [21], and GoogLeNet [22]–[24] have performed well in various fields.”
BackgroundYou 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×
“Representative algorithms are YOLO [5], SSD [6].”
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Rich 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
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939 · cited 1×
“…to assess the detection performance, this paper compares YOLOv3-DPFIN, YOLOv3, YOLOv3-Tiny, SSD with Mobilenet_v1 [29], SSD with ResNet-50 + FPN [30], and SSDLite with Mobilenet_v2 [31]on the test set of MNSD and SRSD, all the above models are real-time networks with high parameter efficiency or…”
MethodHe, 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
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
YOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892 · cited 1×
“YOLOv2 [18] removes the fully connected layer and uses anchor boxes like RPN networks to improve the speed and precision.”
MethodMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · cited 1×
“Secondly, in order to assess the detection performance, this paper compares YOLOv3-DPFIN, YOLOv3, YOLOv3-Tiny, SSD with Mobilenet_v1 [29], SSD with ResNet-50 + FPN [30], and SSDLite with Mobilenet_v2 [31]on the test set of MNSD and SRSD, all the above models are real-time networks with high…”
MethodYOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141 · cited 3×
“YOLOv3 [7] draws on the pyramid feature map of SSD and the residual block of Resnet to propose the Darknet-53, which improves the object detection precision while ensuring the speed, especially for small target.”
BackgroundInfluentialA Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)
Khanam, Z., Achari, V. P. S., Boukhennoufa, I., Jindal, A., & Singh, A. K. (2024) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.ng-res.2024.2 · Cited by 14,040
Aggregated Residual Transformations for Deep Neural Networks
Xie, S., Girshick, R., Dollar, P., Tu, Z., & He, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.634 · Cited by 12,465 · cited 1×
“DPN (Dual Path Network) draws on ResNeXt [27] and DenseNet, using cross-layer connection and dense connection to realize Dual Path Network, which makes full use of features and improves the effect of image classification.”
MethodInception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · cited 1×
“For example, LeNet [19], AlexNet [20], VGG-Nets [21], and GoogLeNet [22]–[24] have performed well in various fields.”
BackgroundDSSD : Deconvolutional Single Shot Detector
Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017) · arXiv · doi:10.48550/arxiv.1701.06659 · Cited by 1,624 · cited 1×
“Profiting from powerful deep convolutional neural networks, many one-stage object detection networks such as SSD, DSSD [16], DSOD [17], and YOLO demonstrate outstanding object recognition capability.”
BackgroundDSOD: Learning Deeply Supervised Object Detectors from Scratch
Shen, Z., Liu, Z., Li, J., Jiang, Y.-G., Chen, Y., & Xue, X. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.212 · Cited by 646 · cited 1×
“Profiting from powerful deep convolutional neural networks, many one-stage object detection networks such as SSD, DSSD [16], DSOD [17], and YOLO demonstrate outstanding object recognition capability.”
BackgroundChen, Y., Li, J., Xiao, H., Jin, X., Yan, S., & Feng, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.01629 · Cited by 397 · cited 3×
“Additionally, with the advent of ResNet [25], DenseNet [8], and DPN [26] networks, the neural networks are greatly deepened, which makes the feature extraction capability of convolutional neural networks more compelling.”
BackgroundMethodWilliams, D. P. (2016) · 2016 23rd International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr.2016.7900011 · Cited by 118 · cited 1×
“Williams [11].”
Convolutional neural network-based real-time ROV detection using forward-looking sonar image
Kim, J., & Yu, S. (2016) · IEEE/OES Autonomous Underwater Vehicles · doi:10.1109/auv.2016.7778702 · Cited by 90 · cited 1×
“Kim and Yu [12]. applied the deep learning object detection model YOLO to the detection and tracking of sonar targets.”
BackgroundConvolutional Neural Network With Second-Order Pooling for Underwater Target Classification
Cao, X., Togneri, R., Zhang, X., & Yu, Y. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2886368 · Cited by 87 · cited 1×
“[13].”
A Statistically-Based Method for the Detection of Underwater Objects in Sonar Imagery
Abu, A., & Diamant, R. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2912325 · Cited by 78 · cited 1×
“In addition, in [14], [15], a statistically-based method and a sonar image simulator-based algorithm were respectively used for the detection of underwater targets.”
MethodSymbolic Analysis of Sonar Data for Underwater Target Detection
Mukherjee, K., Gupta, S., Ray, A., & Phoha, S. (2011) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2011.2122590 · Cited by 75 · cited 1×
“Mukherjee et al. [10]. used a symbolic pattern analysis method to perform feature extraction and target detection of sonar images.”
MethodSide scan sonar image resolution and automatic object detection, classification and identification
Langner, F., Knauer, C., Jans, W., & Ebert, A. (2009) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceanse.2009.5278183 · Cited by 42
Robust Sonar-Based Underwater Object Recognition Against Angle-of-View Variation
Cho, H., Gu, J., & Yu, S.-C. (2016) · IEEE Sensors Journal · doi:10.1109/jsen.2015.2496945 · Cited by 41 · cited 1×
“In addition, in [14], [15], a statistically-based method and a sonar image simulator-based algorithm were respectively used for the detection of underwater targets.”
Method
Research works printed but not linked: 1
- xue, 2017, An automatic alarm method based on maximum entropy segmentation and feature joint discrimination, Acoustic and Electronic Engineering, 13
Cited by
Hybrid deep learning for detecting lung diseases from X-ray images
Bharati, S., Podder, P., & Mondal, M. R. H. (2020) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2020.100391 · Cited by 404
“[14] for classifying and extracting the feature of the nodules.”
Liang, S., Wu, H., Zhen, L., Hua, Q., Garg, S., Kaddoum, G., Hassan, M. M., & Yu, K. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3158253 · Cited by 367
“6, in order to count the most common box sizes from all ground-truth boxes in the training set, we follow the anchor box [43] mechanism in YOLOV3 to optimize the range of predicted objects and combine them with the prediction of bounding box and add its prior experience for multi-scale prediction.”
MethodUnderwater target detection based on Faster R-CNN and adversarial occlusion network
Zeng, L., Sun, B., & Zhu, D. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104190 · Cited by 221
Automatic Detection of Underwater Small Targets Using Forward-Looking Sonar Images
Zhou, T., Si, J., Wang, L., Xu, C., & Yu, X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3181417 · Cited by 152
“However, it also increases network computing time, impacting real-time performance [12].”
BackgroundIntegrated worker detection and tracking for the safe operation of construction machinery
Son, H., & Kim, C. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.103670 · Cited by 112
Metadata
- Authors
- Kong, W., Hong, J., Jia, M., Yao, J., Cong, W., Hu, H., & Zhang, H.
- Affiliations
- Hangzhou Dianzi University (CN)
- Hangzhou Institute of Applied Acoustics (CN)
- Hangzhou Normal University (CN)
- Harbin Engineering University (CN)
- Venue
- IEEE Sensors Journal
- Published
- 2020-04-01
- Volume
- 20
- Issue
- 7
- Pages
- 3745-3756
- ISSN
- 1530-437X (ISSN-L)
- 1558-1748
- 2379-9153
- OpenAlex
- W2996275178
- Semantic Scholar
- 7950757ee25d963f510d2964c9898ac2b11fd1d8
- Cited by
- 107
- References
- 31
- Citations by year
- 2026: 12 · 2025: 19 · 2024: 21 · 2023: 15 · 2022: 24 · 2021: 14 · 2020: 2
- FWCI
- 5.52
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Sensors Journal (publishedVersion)
- Funders
- National Key Research and Development Program of China for Intergovernmental International Science and Technology Innovation Cooperation Project (2017YFE0116800)
- National Natural Science Foundation of China (61671193)
- Science and Technology Program of Zhejiang Province (2018C04012)
- Harbin Engineering University (SSKF2017001)
- Topics
- Physical Sciences › Earth and Planetary Sciences › Oceanography › Underwater Acoustics Research
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Ocean Engineering › Underwater Vehicles and Communication Systems
- Keywords
- sonar target detection, YOLOv3, dual-path network, feature fusion, real-time object detection, underwater imaging, low signal-to-noise ratio, dense connections, multi-scale prediction, small sample size
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.