Survey on Deep Learning-Based Marine Object Detection

Zhang, Ruolan; Li, Shaoxi; Ji, Guanfeng; Zhao, Xi; Li, Jing; Pan, Mingyang

doi:10.1155/2021/5808206

Cited by 24 publications

(9 citation statements)

References 133 publications

(147 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…You Only Look Once (YOLO) has been recently proposed in [11] as an efficient one-stage CNN-based model that is able to detect multi objects in real-time. Published peer reviewed comparisons [12][1] [13] illustrate that YOLO outperforms twostage detection methods and other available one-stage methods such as single shot detector (SSD). Since introduced, many versions of YOLO have been introduced such as YOLOv2 [14], YOLOv3 [15], YOLOv4 [16] and and YOLOv5.…”

Section: A Object Detection Methodsmentioning

confidence: 99%

Marine Objects Detection Using Deep Learning on Embedded Edge Devices

Heller

Rizk

Douguet

et al. 2022

2022 IEEE International Workshop on Rapid System Prototyping (RSP)

View full text Add to dashboard Cite

Intelligence techniques based on convolution neural networks (CNNs) are now dominant in the field of object detection and classification. The deployment of CNNs on embedded edge devices targeting real-time inference sets a challenge due to the limited computing resources and power budgets. Several optimization techniques such as pruning, quantization and use of light neural networks enable the realtime inference but at the cost of precision degradation. However, using efficient approaches to apply the optimization techniques at training and inference stages enable high inference speed with limited degradation of detection performance. In this paper, we revisit the problem of detecting and classifying maritime objects. We investigate different versions of the You Only Look Once (YOLO), a state-of-the-art deep neural network, for real-time object detection and compare their performance for the specific application of detecting maritime objects. The trained YOLO networks are efficiently optimized targeting three recent edge devices: Nvidia Jetson Xavier AGX, AMD-Xilinx Kria KV260 Vision AI Kit, and Movidius Myriad X VPU. The proposed deployments demonstrate promising results with an inference speed of 90 FPS and a limited degradation of 2.4% in mean average precision.

show abstract

Section: A Object Detection Methodsmentioning

confidence: 99%

Marine Objects Detection Using Deep Learning on Embedded Edge Devices

Heller

Rizk

Douguet

et al. 2022

2022 IEEE International Workshop on Rapid System Prototyping (RSP)

View full text Add to dashboard Cite

show abstract

“…Detecting small objects would be particularly meaningful and challenging. On the other hand, a large number of maritime object detection models based on deep learning have been proposed, but due to the lack of universal evaluation criteria, it is difficult to compare different improved models [34]. Thus, the development of universal evaluation criteria is also an important part of future work.…”

Section: Comparison With Seaships Datasetmentioning

confidence: 99%

MCMOD: The Multi-Category Large-Scale Dataset for Maritime Object燚etection

Sun¹,

Hu²,

Qi³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The marine environment is becoming increasingly complex due to the various marine vehicles, and the diversity of maritime objects poses a challenge to marine environmental governance. Maritime object detection technology plays an important role in this segment. In the field of computer vision, there is no sufficiently comprehensive public dataset for maritime objects in the contrast to the automotive application domain. The existing maritime datasets either have no bounding boxes (which are made for object classification) or cover limited varieties of maritime objects. To fulfil the vacancy, this paper proposed the Multi-Category Large-Scale Dataset for Maritime Object Detection (MCMOD) which is collected by 3 onshore video cameras that capture data under various environmental conditions such as fog, rain, evening, etc. The whole dataset consists of 16,166 labelled images along with 98,590 maritime objects which are classified into 10 classes. Compared with the existing maritime datasets, MCMOD contains a relatively balanced quantity of objects of different sizes (in the view). To evaluate MCMOD, this paper applied several state-of-the-art object detection approaches from computer vision research on it and compared their performances. Moreover, a comparison between MCMOD and an existing maritime dataset was conducted. Experimental results indicate that the proposed dataset classifies more types of maritime objects and covers more small-scale objects, which can facilitate the trained detectors to recognize more types of maritime objects and detect maritime objects over a relatively long distance. The obtained results also show that the adopted approaches need to be further improved to enhance their capabilities in the maritime domain.

show abstract

“…Nowadays, mainstream deep learning-based target detection models include two-stage detection models and single-stage detection models. The two-stage detection models are the candidate region-based target detection models represented by the R-CNN [2] series; the single-stage detection models [3] are the regression analysis-based target detection models represented by the YOLO [4] and SSD [5] series.…”

Section: Introductionmentioning

confidence: 99%

Object Detection in Security Inspection Scenarios Based on YOLOv5s: Exploring Experiments

Wang,

Zhang,

Xiao

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

At present, there are many problems with the common methods of manual safety checks. Applying object detection technology to X-ray security inspection can effectively improve efficiency and reduce operating costs. The training parameters of deep neural networks directly affect the performance of the network. Based on YOLOv5s network model, this paper uses the method of control variables to explore the impact of training strategies, data enhancement strategies, and loss function selection on network performance. The experimental results show that a suitable batch size and learning rate can achieve significant performance improvements in the model without changing the network structure. With the increase in strength of the data enhancement strategy, the model performance shows a trend of first improving and then decreasing. The selection of the loss function has a great impact on the model’s performance. The research methods and ideas in this article can provide inspiration for subsequent related research.

show abstract

Survey on Deep Learning-Based Marine Object Detection

Cited by 24 publications

References 133 publications

Marine Objects Detection Using Deep Learning on Embedded Edge Devices

Marine Objects Detection Using Deep Learning on Embedded Edge Devices

MCMOD: The Multi-Category Large-Scale Dataset for Maritime Object燚etection

Object Detection in Security Inspection Scenarios Based on YOLOv5s: Exploring Experiments

Contact Info

Product

Resources

About