Target Detection of Forward-Looking Sonar Image Based on Improved YOLOv5

Zhang, Haoting; Mao, Tian; Shao, Guofan; Cheng, Juan; Liu, Jingjing

doi:10.1109/access.2022.3150339

Cited by 60 publications

(35 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…able to adaptively change the depth and width of the network by changing parameters to its own data volume scale [53] (self-adaptation to small underwater objects), iii. can guarantee good training result [54] of highest detection accuracy as proved in this study (Table 5).…”

Section: Underwater Imaging Using the Deep-learning Methodsmentioning

confidence: 99%

Optimizing the Hyperparameter Tuning of YOLOv5 for Underwater Detection

et al. 2022

View full text Add to dashboard Cite

This study optimized the latest YOLOv5 framework, including its subset models, with training on different datasets that differed in image contrast and cloudiness to assess model performances based on quantitative metrics and image processing speed. The hyperparameter in the feature-extraction phase was configured based on the learning rate and momentum and further improved based on the adaptive moment estimation (ADAM) optimizer and the function reducing-learning-rate-on-plateau to optimize the model's training scheme. The optimized YOLOv5s achieved a better performance, with a mean average precision of 98.6% and a high inference speed of 106 frames per second. The ADAM optimizer with a detailed learning rate (0.0001) and momentum (0.99) fine-tuning yielded a sufficient convergence rate (0.69% at 55th epoch) to assist YOLOv5s in attaining a more precise detection for underwater objects.INDEX TERMS Image processing speed, object recognition, optimization model, tuning hyper-parameter, underwater imaging

show abstract

Section: Underwater Imaging Using the Deep-learning Methodsmentioning

confidence: 99%

Optimizing the Hyperparameter Tuning of YOLOv5 for Underwater Detection

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The difference be tween the original YOLOv5 model and the YOLOv5_Our model is as follows. The weigh trained by the original YOLOv5 model is put on the image data set as the pre-training weight of the configured data set [41]. That is, the original YOLOv5 model uses its own weight obtained by pre-learning on COCO (Common Object in Context) dataset.…”

Section: Experimental Setup and Flowchartmentioning

confidence: 99%

Improved YOLOv5: Efficient Object Detection Using Drone Images under Various Conditions

2022

View full text Add to dashboard Cite

With the recent development of drone technology, object detection technology is emerging, and these technologies can also be applied to illegal immigrants, industrial and natural disasters, and missing people and objects. In this paper, we would like to explore ways to increase object detection performance in these situations. Photography was conducted in an environment where it was confusing to detect an object. The experimental data were based on photographs that created various environmental conditions, such as changes in the altitude of the drone, when there was no light, and taking pictures in various conditions. All the data used in the experiment were taken with F11 4K PRO drone and VisDrone dataset. In this study, we propose an improved performance of the original YOLOv5 model. We applied the obtained data to each model: the original YOLOv5 model and the improved YOLOv5_Ours model, to calculate the key indicators. The main indicators are precision, recall, F-1 score, and mAP (0.5), and the YOLOv5_Ours values of mAP (0.5) and function loss were improved by comparing it with the original YOLOv5 model. Finally, the conclusion was drawn based on the data comparing the original YOLOv5 model and the improved YOLOv5_Ours model. As a result of the analysis, we were able to arrive at a conclusion on the best model of object detection under various conditions.

show abstract

“…Hosting Zhang [7] has implemented a target detection system based on YOLOv5 on forward-looking sonar images with detect accuracy mAP@0.5:0.95 and a detection speed of 9ms. They have used multiple objection algorithms such as YOLOv5, Faster R-CNN, and E -cientDet and mention YOLOv5 has better performance object detection algorithms.…”

Section: Payal Bose [6] Et Al Have Implemented Medicinal Plants Leaf ...mentioning

confidence: 99%

Comprehensive Analysis of CNN and YOLOv5 Object Detection Model to Classify Phytomedicine Tree’s Leaf Disease

Islam

Haque

Rahaman

et al. 2022

Preprint

View full text Add to dashboard Cite

Phytomedicine is not only known to the poor people of East Bengal and West Bengal as a medicine but also as a beacon of hope for survival in a diseased life. In this approach, Terminalia Arjuna, Lawsonia inermis, Azadirachta indica, and Ocimum tenuiflorum Phytomedicine tree datasets. Terminalia Arjuna mainly protects gastric mucosa from oxidative damage and it makes it strong so that the stomach gets protection against ulcers. It also exhibits strong antibacterial and antimicrobial properties which help to fight against stomach infections like gastric, diarrhea, and dysentery. There are various uses of Lawsonia inermis. It is known as a powerful detoxifier and it helps to prefer healthy gum, and healthy hair and reduces arthritis pain. The flower of Lawsonia inermis can be used for headaches due to the heat of the sun. Neem is known as Phytomedicine for all diseases and the most common diseases are treated with acne, nourishing the skin, treating wounds, use to reduce dandruff and joint pain, etc. Mainly it increases immunity and provides a healthy life. Another famous Phytomedicine known as Ocimum tenuiflorum is used to treat kidney stones, alleviate fever and headaches, provide a healthy heart, healthy eye, healthy oral, and fight against acne, etc. It is also known as a big source of vitamin K. The most famous and fast object detection algorithms as YOLOv5 and Keras pre-trained models as Xception, ResNet152V2, VGG19, and InceptionResNetV2 have been developed to predict disease-affected or disease-free leaves. The implemented approach has gained a height accuracy of 97.00% from Xception and 95% accuracy from YOLOv5.

show abstract

Target Detection of Forward-Looking Sonar Image Based on Improved YOLOv5

Cited by 60 publications

References 28 publications

Optimizing the Hyperparameter Tuning of YOLOv5 for Underwater Detection

Optimizing the Hyperparameter Tuning of YOLOv5 for Underwater Detection

Improved YOLOv5: Efficient Object Detection Using Drone Images under Various Conditions

Comprehensive Analysis of CNN and YOLOv5 Object Detection Model to Classify Phytomedicine Tree’s Leaf Disease

Contact Info

Product

Resources

About