Marine ship detection and classification based on YOLOv5 model

Zhang, Xuan; Yan, Ming; Zhu, Daqi; Guan, Yang

doi:10.1088/1742-6596/2181/1/012025

Cited by 18 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But its detection accuracy is not high. Zhang et al (2022) used the obtained marine vessel data to replace the CSP-DarkNet module in YOLOv5 with CSP-DenseNet to classify six types of vessel data and improve the detection accuracy. Kim et al (2022) solved the problem of class imbalance through methods such as Copy and Paste, and enhanced the image with Mix-up, so as to solve the previous data problem and obtain better experimental results, but this did not provide a fundamental improvement to YOLOv5.…”

Section: Target Detection Resultsmentioning

confidence: 99%

“…The identification of fishing vessels type and operation status are often based on the drawn fishing vessels trajectory map, which has several disadvantages. There are few features that can be used for recognition, many different types of fishing vessels operations, and the classification standards are also different (Zhang et al, 2022;Kim et al, 2022). Due to these disadvantages, the fishing vessels trajectory map is not accurate.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on target detection of Engraulis japonicus purse seine based on improved model of YOLOv5

et al. 2022

View full text Add to dashboard Cite

The refined monitoring and identification of fishing operations by fishing vessels is of great significance and value to fishing vessels. In order to solve the problem of inaccurate statistics of current Engraulis japonicus fishing quota and classification, this paper proposes an improved identification algorithm based on YOLOv5. This method introduces the SENet attention mechanism into the YOLOv5 backbone network structure, integrates the target information in different periods of fishing operations, reduces the interference of complex backgrounds, improves the precision of model detection, and ensures real-time detection efficiency. The artificially shot Engraulis japonicus videos are used as the dataset of the study, and the video is converted into a picture format to realize pre-labeling and processing. The 5550 images are divided into the training set, validation set, and test set according to 8:1:1. In order to verify the validity of the data, a set of in the control experiment, the YOLOv5 backbone network was replaced by MobileNetV2 and the SENet attention mechanism was introduced, and four models were implemented for comparison. The experimental results show that the research algorithm can obtain a mean average precision (mAP) of 99.3%, a precision of 98.9%, and a recall of 98.7%, which are improved by 1.4%, 1.7% and 2.5% respectively compared with the original model. The experimental results match the expectations. According to the statistics of some categories, the Kalman filter and the Hungarian matching method are used to count the main categories of fishing baskets, and an accuracy of 96.5% can be obtained. The threshold method for fishing nets and processing vessels can obtain 85.8% and 75% accuracy. These results shows that this target detection research can provide new ideas for job identification of Engraulis japonicus and provide auxiliary means for job statistics.

show abstract

Section: Target Detection Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Research on target detection of Engraulis japonicus purse seine based on improved model of YOLOv5

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The structure of YOLOv5 can be split into input, backbone, neck, and prediction. Some research has been done on creating new backbones, improving existing backbones [12], or swapping YOLOv5's backbone for another existing backbone. Ting et al [13] swapped the exiting backbone for Hauawei's GhostNet [14] and stacked two of these GhostNets into what they call a Ghostbottlenet.…”

Section: Literature Reviewmentioning

confidence: 99%

Object Detection and Ship Classification Using YOLOv5

Sean¹,

Caitlin

Galliera

et al. 2021

BIJCS

View full text Add to dashboard Cite

Using a public dataset of images of maritime vessels provided by Analytics Vidhya, manual annotations were made on a subsample of images with Roboflow using the ground truth classifications provided by the dataset. YOLOv5, a prominent open source family of object detection models that comes with an out-of-the-box pre-training on the Common Objects in Context (COCO) dataset, was used to train on annotations of subclassifications of maritime vessels. YOLOv5 provides significant results in detecting a boat. The training, validation, and test set of images trained YOLOv5 in the cloud using Google Colab. Three of our five subclasses, namely, cruise ships, ROROs (Roll On Roll Off, typically car carriers), and military ships, have very distinct shapes and features and yielded positive results. Two of our subclasses, namely, the tanker and cargo ship, have similar characteristics when the cargo ship is unloaded and not carrying any cargo containers. This yielded interesting misclassifications that could be improved in future work. Our trained model resulted in the validation metric of mean Average Precision (mAP@.5) of 0.932 across all subclassification of ships.

show abstract

“…The YOLO model detection head was optimized through multiple relationship head modules. Zhang et al 21 proposed an improved deep learning model YOLOv5-DN, introducing the CSPDensenet model structure to replace the CSP-Darknet model structure, improving the model's feature extraction ability. To solve the problem that the CNN network model only focuses on local feature information, Huang et al 22 introduced the combination of Swin transformer and CNN to effectively extract the features of the ship's superstructure, and proposed a CNN and Swin transformer model for ship detection.…”

Section: Introductionmentioning

confidence: 99%

Lightweight ship detection method based on Swin-YOLOFormer

Cen,

Chen,

Liu

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Deep learning models have achieved great success in the field of ship detection, but these models often require a large amount of computing and storage resources, and are not suitable for some resource-constrained situations. To solve the above problems, we propose a lightweight Swin-YOLOFormer ship detection method. First, in terms of the backbone network, the Swin transformer lightweight model is introduced to reduce the redundancy parameters of the backbone network. Second, in the feature fusion network, an improved ghost-efficient long-range attention network-hierarchy module is proposed to extract features and reduce the burden of model parameters. Finally, in order to prevent feature loss, an improved SPPCPSC module is proposed to enhance the feature of receptive field. Through experimental verification, compared with the YOLOv7 benchmark model, the number of proposed model parameters was reduced by 66.05% to 13.501 M, which not only accelerated the model training speed but also reached 97.81% accuracy. The results show that the proposed method achieves model lightweight and maintain high precision.

show abstract

Marine ship detection and classification based on YOLOv5 model

Cited by 18 publications

References 0 publications

Research on target detection of Engraulis japonicus purse seine based on improved model of YOLOv5

Research on target detection of Engraulis japonicus purse seine based on improved model of YOLOv5

Object Detection and Ship Classification Using YOLOv5

Lightweight ship detection method based on Swin-YOLOFormer

Contact Info

Product

Resources

About