2022
DOI: 10.1109/lgrs.2022.3183350
|View full text |Cite
|
Sign up to set email alerts
|

Oil Tank Detection With Improved EfficientDet Model

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 10 publications
(6 citation statements)
references
References 34 publications
0
6
0
Order By: Relevance
“…To verify the effect of our algorithm in bubble detection, the comparative experiments between improved YOLOv8n and the other mainstream algorithms are conducted under the same experimental environment, the results of which are presented in Table 3 below. In the Table 3, we can see that our algorithm has higher accuracy compared to SSD, Faster R-CNN, YOLOv5s, YOLOv7-tiny, EfficientDet-D1 [39][40] and SpineNet-49 [41], with an increase of 7.2%, 4.1%, 5%, 3.3%,1.6% and 0.9% in mAP, respectively. Compared to the improved YOLOv8n algorithm we proposed, the SpineNet model has a much lower detection efficiency, and the model size is nearly ten times larger than ours.…”
Section: Comparative Experimentsmentioning
confidence: 99%
“…To verify the effect of our algorithm in bubble detection, the comparative experiments between improved YOLOv8n and the other mainstream algorithms are conducted under the same experimental environment, the results of which are presented in Table 3 below. In the Table 3, we can see that our algorithm has higher accuracy compared to SSD, Faster R-CNN, YOLOv5s, YOLOv7-tiny, EfficientDet-D1 [39][40] and SpineNet-49 [41], with an increase of 7.2%, 4.1%, 5%, 3.3%,1.6% and 0.9% in mAP, respectively. Compared to the improved YOLOv8n algorithm we proposed, the SpineNet model has a much lower detection efficiency, and the model size is nearly ten times larger than ours.…”
Section: Comparative Experimentsmentioning
confidence: 99%
“…Figure 1 An overview of proposed EfficientDet Object Detection Working Pipeline using EfficientNet backbone, BiSkFPN bottleneck and MFL head. [16] While performing AMODMV, biggest challenge is the noisy images (limited visibility) because of the impurities of water, wrong placement angles of image sensing kits, and interpreting the results from the object detection model. In addition, The marine environment is often cluttered with a variety of objects, such as rocks, plants, and debris, which can make it difficult to distinguish between objects of interest and background clutter [2,3].…”
Section: Low Level Featuresmentioning
confidence: 99%
“…A new method that uses AM to dampen the effect of noise (caused by pollution, clouds, and climate) in remote sensing images. This work [16] also modifies pooling in every layer such that it can capture tiny class specific pixels and hence uses exhaustive feature space. This approach increases computational complexity but helps to achieve higher accuracy.…”
Section: 1-mynet: Improved Efficientdet Using Attention Mechanism (Am...mentioning
confidence: 99%
“…Oil tanks are essential energy storage devices and critical infrastructures which are widely used in petroleum, natural gas, petrochemical industries and transportation (Xu et al, 2022;Yu et al, 2021). Rapid and accurate detection of oil tanks is substantial in terms of disaster management, risk evaluation and monitoring (Ok and Başeski, 2015;Xu et al, 2022).…”
Section: Introductionmentioning
confidence: 99%
“…They obtained better accuracy values compared to state-of-the-art segmentation models such as U-Net, SegNet and PSPNet. Xu et al (2022) present an improved version of EfficientDet architecture using 3-D deformable convolution, attention mechanism and focal loss function. They have achieved better accuracy results compared to various models which are generally region proposal-based architectures.…”
Section: Introductionmentioning
confidence: 99%