An Improved Ship Classification Method Based on YOLOv7 Model with Attention Mechanism

Cen, Jian; Feng, Hao; Liu, Xi; Hu, Yongjian; Li, Haoliang; Li, Haisheng; Huang, Weijian

doi:10.1155/2023/7196323

Cited by 6 publications

(3 citation statements)

References 40 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu et al [20] introduced the multiscale feature fusion module into the YOLOv7 model and established suitable anchor boxes to replace the fixed anchor boxes, effectively improving the ship feature's capture ability. Chen et al [21] combined the convolutional attention mechanism and residual connectivity into the YOLOv7 model, enabling the model to accurately locate ships in dark environments and achieve effective ship classification detection. Lang et al [22] proposed LSDNet, a mobile ship detection model that introduces partial convolution in YOLOv7-Tiny to reduce redundant computations and memory accesses, thereby extracting spatial features more efficiently.…”

Section: Related Workmentioning

confidence: 99%

YOLOv7-Ship: A Lightweight Algorithm for Ship Object Detection in Complex Marine Environments

Jiang,

Su,

Sun

2024

JMSE

View full text Add to dashboard Cite

Accurate ship object detection ensures navigation safety and effective maritime traffic management. Existing ship target detection models often have the problem of missed detection in complex marine environments, and it is hard to achieve high accuracy and real-time performance simultaneously. To address these issues, this paper proposes a lightweight ship object detection model called YOLOv7-Ship to perform end-to-end ship detection in complex marine environments. At first, we insert the improved “coordinate attention mechanism” (CA-M) in the backbone of the YOLOv7-Tiny model at the appropriate location. Then, the feature extraction capability of the convolution module is enhanced by embedding omnidimensional dynamic convolution (ODconv) into the efficient layer aggregation network (ELAN). Furthermore, content-aware feature reorganization (CARAFE) and SIoU are introduced into the model to improve its convergence speed and detection precision for small targets. Finally, to handle the scarcity of ship data in complex marine environments, we build the ship dataset, which contains 5100 real ship images. Experimental results show that, compared with the baseline YOLOv7-Tiny model, YOLOv7-Ship improves the mean average precision (mAP) by 2.2% on the self-built dataset. The model also has a lightweight feature with a detection speed of 75 frames per second, which can meet the need for real-time detection in complex marine environments to a certain extent, highlighting its advantages for the safety of maritime navigation.

show abstract

Section: Related Workmentioning

confidence: 99%

YOLOv7-Ship: A Lightweight Algorithm for Ship Object Detection in Complex Marine Environments

Jiang,

Su,

Sun

2024

JMSE

View full text Add to dashboard Cite

show abstract

“…Penelitian mendeteksi kotoran anjing dengan memodifikasi algoritma sehingga mendapatkan akurasi yang lebih baik mencapai 98,66% [6]. Penelitian [7] yang sama juga dilakukan menggunakan teknologi YOLO untuk mendeteksi dan mengklasifikasi jenis kapal yang melintas di dermaga dengan kinerja 97,59% dan dapat secara akurat menemukan kapal dilingkungan kegelapan mencapai 96,13% sehingga mencapai deteksi dan klasifikasi kapal lebih efektif.…”

Section: Pendahuluanunclassified

Catfish Fry Detection and Counting Using YOLO Algorithm

Takyudin,

Fitri,

Yuhandri

2023

JAIC

View full text Add to dashboard Cite

The development of computer vision technology is growing very fast and penetrating all sectors, including fisheries. This research focuses on detecting and counting catfish fry. This research aims to apply deep learning in detecting catfish fry objects and counting accurately so as to help farmers and buyers reduce the risk of loss. The detection system in this research uses digital image processing techniques as a way to obtain information from the detection object. The research method uses YOLO Object Detection which has a very fast ability to identify objects. The object detected is a catfish puppy object that is given a bounding box and the detection label displays the class name and precision value. The dataset amounted to 321 images of catfish puppies from internet and photography sources that were trained to produce a new digital image model. The number of split training, validation and testing datasets is worth 831 annotation images, 83 validation images and 83 images for the testing process. The value of the training model mAP 50.39 %, Precision 61.17 % and Recall 58 % Detection test results based on the YOLO method obtained an accuracy rate of 65.7%. The avg loss value in the final model built with YOLO is 4.6%. Based on the results of tests carried out with the number of objects 50 to 500 tail size 2-8 cm using video, objects in the image are successfully recognized with an accuracy of 63% to 70%. Calculations using the YOLO algorithm show quite good results.

show abstract

“…Due to stability and accuracy, anchor-based methods have become more popular in recent years. Typical methods include YOLOv1-v5 [16,[36][37][38][39][40], single shot multibox detector [41], and Region CNN etc. For instance, Girshick et al [42] proposed a novel method of R-CNN for target detection.…”

Section: Applications Of Machine Vision In Target Detectionsmentioning

confidence: 99%

A Deep Learning Method for Ship Detection and Traffic Monitoring in an Offshore Wind Farm Area

Liu

et al. 2023

JMSE

View full text Add to dashboard Cite

Newly built offshore wind farms (OWFs) create a collision risk between ships and installations. The paper proposes a real-time traffic monitoring method based on machine vision and deep learning technology to improve the efficiency and accuracy of the traffic monitoring system in the vicinity of offshore wind farms. Specifically, the method employs real automatic identification system (AIS) data to train a machine vision model, which is then used to identify passing ships in OWF waters. Furthermore, the system utilizes stereo vision techniques to track and locate the positions of passing ships. The method was tested in offshore waters in China to validate its reliability. The results prove that the system sensitively detects the dynamic information of the passing ships, such as the distance between ships and OWFs, and ship speed and course. Overall, this study provides a novel approach to enhancing the safety of OWFs, which is increasingly important as the number of such installations continues to grow. By employing advanced machine vision and deep learning techniques, the proposed monitoring system offers an effective means of improving the accuracy and efficiency of ship monitoring in challenging offshore environments.

show abstract

An Improved Ship Classification Method Based on YOLOv7 Model with Attention Mechanism

Cited by 6 publications

References 40 publications

YOLOv7-Ship: A Lightweight Algorithm for Ship Object Detection in Complex Marine Environments

YOLOv7-Ship: A Lightweight Algorithm for Ship Object Detection in Complex Marine Environments

Catfish Fry Detection and Counting Using YOLO Algorithm

A Deep Learning Method for Ship Detection and Traffic Monitoring in an Offshore Wind Farm Area

Contact Info

Product

Resources

About