We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
An Embeddable Algorithm for Automatic Garbage Detection Based on Complex Marine Environment
Summary
Researchers developed an improved object detection algorithm based on Mask R-CNN with dilated convolution in the feature pyramid network to enable more accurate automated identification and segmentation of marine garbage by underwater detectors. The embeddable algorithm is designed to function effectively in complex, low-resolution underwater environments.
With the continuous development of artificial intelligence, embedding object detection algorithms into autonomous underwater detectors for marine garbage cleanup has become an emerging application area. Considering the complexity of the marine environment and the low resolution of the images taken by underwater detectors, this paper proposes an improved algorithm based on Mask R-CNN, with the aim of achieving high accuracy marine garbage detection and instance segmentation. First, the idea of dilated convolution is introduced in the Feature Pyramid Network to enhance feature extraction ability for small objects. Secondly, the spatial-channel attention mechanism is used to make features learn adaptively. It can effectively focus attention on detection objects. Third, the re-scoring branch is added to improve the accuracy of instance segmentation by scoring the predicted masks based on the method of Generalized Intersection over Union. Finally, we train the proposed algorithm in this paper on the Transcan dataset, evaluating its effectiveness by various metrics and comparing it with existing algorithms. The experimental results show that compared to the baseline provided by the Transcan dataset, the algorithm in this paper improves the mAP indexes on the two tasks of garbage detection and instance segmentation by 9.6 and 5.0, respectively, which significantly improves the algorithm performance. Thus, it can be better applied in the marine environment and achieve high precision object detection and instance segmentation.
Sign in to start a discussion.
More Papers Like This
Detection of Trash in Sea Using Deep Learning
Researchers developed a deep learning convolutional neural network (CNN) model to detect and classify trash in marine and aquatic environments from underwater images, aiming to overcome the limitations of manual debris detection for objects that may be submerged or partially obscured.
Full stage networks with auxiliary focal loss and multi-attention module for submarine garbage object detection
Researchers developed a new AI-based detection system using modified YOLO neural networks to identify and locate garbage objects on the seafloor in complex underwater images. The system uses multi-scale feature extraction and a specialized loss function to accurately detect small and deformed debris items, supporting robotic clean-up efforts in marine environments.
Enhancing marine debris identification with convolutional neural networks
A deep learning model was developed to identify and classify marine debris components captured by underwater remotely operated vehicle imagery, addressing the challenge of widely distributed ocean waste including microplastics. The convolutional neural network demonstrated improved accuracy for debris detection and classification compared to conventional image analysis methods.
A Comprehensive Review of Deep Learning Algorithms for Underwater Trash Detection: Advancements, Challenges, and Future Directions
This review examines deep learning approaches for automated underwater trash detection, covering CNN-based architectures including YOLO and Faster R-CNN, and finds they outperform traditional sonar and manual inspection methods while identifying key challenges such as low visibility and limited labeled datasets.
A Comprehensive Review of Deep Learning Algorithms for Underwater Trash Detection: Advancements, Challenges, and Future Directions
This review examines deep learning approaches for automated underwater trash detection, covering CNN-based architectures including YOLO and Faster R-CNN, and finds they outperform traditional sonar and manual inspection methods while identifying key challenges such as low visibility and limited labeled datasets.