Combining convolutional neural network with transformer to improve YOLOv7 for gas plume detection and segmentation in multibeam water column images
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study enhances underwater gas plume detection by combining Convolutional Neural Networks (CNNs) with transformers in the YOLOv7 model. The improved method offers greater accuracy and efficiency for identifying gas plumes in water column images.
Area Of Science
- Marine geology
- Underwater acoustics
- Artificial intelligence
Background
- Multibeam bathymetry generates high-resolution water column images (WCIs) for target detection.
- Gas plumes in WCIs present challenges due to sparse texture and motion, hindering traditional detection methods.
- Convolutional Neural Networks (CNNs) improve detection but struggle with the elongated morphology of gas plumes.
Purpose Of The Study
- To enhance the accuracy and efficiency of underwater gas plume detection and segmentation.
- To address the limitations of CNNs in capturing the global context of elongated targets.
- To improve upon the YOLOv7 model for WCI analysis.
Main Methods
- A hybrid CNN-Transformer approach was developed, integrating transformers with YOLOv7.
- The Efficient Layer Aggregation Networks (ELAN) structure was optimized within the backbone network.
- A novel Cross-BiFormer (C-BiFormer) module was proposed for collaborative local and global feature extraction.
- Networks of varying depths were constructed using C-BiFormer modules to enhance receptive fields.
Main Results
- The improved YOLOv7 model demonstrated enhanced detection and segmentation accuracy for gas plumes.
- The C-BiFormer module effectively balanced local feature extraction with global semantic modeling.
- The modified model achieved a smaller size and higher accuracy compared to the baseline YOLOv7.
- Optimizing feature extraction in deeper network layers proved more effective for gas plume recognition.
Conclusions
- The integration of CNNs and transformers offers a superior approach for underwater gas plume detection.
- The proposed C-BiFormer module enhances multi-scale feature extraction and model efficiency.
- The developed model provides a more accurate and computationally efficient solution for analyzing WCIs.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
Related Concept Videos
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Fluid dynamics is the study of fluids in motion. Velocity vectors are often used to illustrate fluid motion in applications like meteorology. For example, wind—the fluid motion of air in the atmosphere—can be represented by vectors indicating the speed and direction of the wind at any given point on a map. Another method for representing fluid motion is a streamline. A streamline represents the path of a small volume of fluid as it flows. When the flow pattern changes with time, the...
Turbulent flow is characterized by unpredictable fluctuations in velocity and pressure, which result in a chaotic fluid movement distinct from the orderly patterns of laminar flow. While laminar flow is governed by smooth, parallel layers with minimal mixing, turbulent flow exhibits highly irregular, three-dimensional patterns. This behavior arises due to instabilities in the fluid's velocity profile, and amplifies as the flow velocity increases. Minor disturbances, known as turbulent...
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...