Underwater human detection using faster R-CNN with data augmentation

Dulhare, Uma N.; Ali, Mohd Hasham

doi:10.1016/j.matpr.2021.05.653

Cited by 10 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this method is costly and can restrict the movements of swimmers because of the requirement to wear sensor devices, potentially leading to drowning incidents, which does not align with the original research intention. Considering these issues, methods based on image or video recognition have been proposed, including background subtraction 7 , hue saturation value (HSV) 8 , k-means clustering algorithm 9 , and deep learning 10 – 12 . While recognizing postures through videos or images resolves the issues associated with wearable sensors, the use of airborne optical cameras poses challenges in simultaneously imaging both the water surface and underwater because of the influence of visible light wavelengths.…”

Section: Introductionmentioning

confidence: 99%

Surface and underwater human pose recognition based on temporal 3D point cloud deep learning

Wang,

Wu,

Zhao

2024

Sci Rep

View full text Add to dashboard Cite

Airborne surface and underwater human pose recognition are crucial for various safety and surveillance applications, including the detection of individuals in distress or drowning situations. However, airborne optical cameras struggle to achieve simultaneous imaging of the surface and underwater because of limitations imposed by visible-light wavelengths. To address this problem, this study proposes the use of light detection and ranging (LiDAR) to simultaneously detect humans on the surface and underwater, whereby human poses are recognized using a neural network designed for irregular data. First, a temporal point-cloud dataset was constructed for surface and underwater human pose recognition to enhance the recognition of comparable movements. Subsequently, radius outlier removal (ROR) and statistical outlier removal (SOR) were employed to alleviate the impact of noise and outliers in the constructed dataset. Finally, different combinations of secondary sampling methods and sample sizes were tested to improve recognition accuracy using PointNet++. The experimental results show that the highest recognition accuracy reached 97.5012%, demonstrating the effectiveness of the proposed human pose detection and recognition method.

show abstract

Section: Introductionmentioning

confidence: 99%

Surface and underwater human pose recognition based on temporal 3D point cloud deep learning

Wang,

Wu,

Zhao

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Kaiyue Liu et al [35] enhanced the model performance by incorporating a residual module and integrating a global attentional mechanism into the object detection network. Dulhare UN et al [36] employed Faster R-CNN and data augmentation algorithms to tackle the issue of low accuracy in detecting humans in underwater environments. In 2024, Rakesh Joshi et al [37] addressed the issue of underwater scattering caused by suspended particles in water, severely degrading signal detection performance.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Underwater Object Detection Algorithm for Embedded Deployment Using Higher-Order Information and Image Enhancement

Liu,

Wen,

Huang

et al. 2024

JMSE

View full text Add to dashboard Cite

Underwater object detection is crucial in marine exploration, presenting a challenging problem in computer vision due to factors like light attenuation, scattering, and background interference. Existing underwater object detection models face challenges such as low robustness, extensive computation of model parameters, and a high false detection rate. To address these challenges, this paper proposes a lightweight underwater object detection method integrating deep learning and image enhancement. Firstly, FUnIE-GAN is employed to perform data enhancement to restore the authentic colors of underwater images, and subsequently, the restored images are fed into an enhanced object detection network named YOLOv7-GN proposed in this paper. Secondly, a lightweight higher-order attention layer aggregation network (ACC3-ELAN) is designed to improve the fusion perception of higher-order features in the backbone network. Moreover, the head network is enhanced by leveraging the interaction of multi-scale higher-order information, additionally fusing higher-order semantic information from features at different scales. To further streamline the entire network, we also introduce the AC-ELAN-t module, which is derived from pruning based on ACC3-ELAN. Finally, the algorithm undergoes practical testing on a biomimetic sea flatworm underwater robot. The experimental results on the DUO dataset show that our proposed method improves the performance of object detection in underwater environments. It provides a valuable reference for realizing object detection in underwater embedded devices with great practical potential.

show abstract

“…In particular, convolutional neural network technology and deep learning technology are applied to the research of related technologies in the image field, which makes the related technologies of image processing develop rapidly [1,2,3,4]. As a branch of image research technology, object detection has always been a hot research field, and the research of this technology has a broad application field, such as satellite detection [5,6], military detection [7], human detection [8,9], road traffic [10,11], medical treatment [12,13] and other aspects. The application of deep convolutional neural network makes up for the shortcomings of the traditional image object detection algorithms, and has a great improvement in speed and accuracy.…”

Section: Introductionmentioning

confidence: 99%

Small object detection in satellite remote sensing images based on super-resolution enhanced DETR

Wei,

Zhang

2024

International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2024)

View full text Add to dashboard Cite

Underwater human detection using faster R-CNN with data augmentation

Cited by 10 publications

References 8 publications

Surface and underwater human pose recognition based on temporal 3D point cloud deep learning

Surface and underwater human pose recognition based on temporal 3D point cloud deep learning

Lightweight Underwater Object Detection Algorithm for Embedded Deployment Using Higher-Order Information and Image Enhancement

Small object detection in satellite remote sensing images based on super-resolution enhanced DETR

Contact Info

Product

Resources

About