In the maritime environment, the instance segmentation of small ships is crucial. Small ships are characterized by their limited appearance, smaller size, and ships in distant locations in marine scenes. However, existing instance segmentation algorithms do not detect and segment them, resulting in inaccurate ship segmentation. To address this, we propose a novel solution called enhanced Atrous Spatial Pyramid Pooling (ASPP) feature fusion for small ship instance segmentation. The enhanced ASPP feature fusion module focuses on small objects by refining them and fusing important features. The framework consistently outperforms state-of-the-art models, including Mask R-CNN, Cascade Mask R-CNN, YOLACT, SOLO, and SOLOv2, in three diverse datasets, achieving an average precision (mask AP) score of 75.8% for ShipSG, 69.5% for ShipInsSeg, and 54.5% for the MariBoats datasets.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3390/jimaging10120299 | DOI Listing |
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11677345 | PMC |
Publication Analysis
Top Keywords
Similar Publications
Enhanced human activity recognition in medical emergencies using a hybrid deep CNN and bi-directional LSTM model with wearable sensors.
Sci Rep
December 2024
Department of Communications and Electronics, Delta University for Science and Technology, Mansoura, Egypt.
Human activity recognition (HAR) is one of the most important segments of technology advancement in applications of smart devices, healthcare systems & fitness. HAR uses details from wearable sensors that capture the way human beings move or engage with their surrounding. Several researchers have thus presented different ways of modeling human motion, and some have been as follows: Many researchers have presented different methods of modeling human movements.
View Article and Find Full Text PDFCrops3D: a diverse 3D crop dataset for realistic perception and segmentation toward agricultural applications.
Sci Data
December 2024
National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Huazhong Agricultural University, Wuhan, 430070, P. R. China.
Point cloud analysis is a crucial task in computer vision. Despite significant advances over the past decade, the developments in agricultural domain have faced challenges due to a scarcity of datasets. To facilitate 3D point cloud research in agriculture community, we introduce Crops3D, the diverse real-world dataset derived from authentic agricultural scenarios.
View Article and Find Full Text PDFFeasibility of Mental Health Triage Call Priority Prediction Using Machine Learning.
Nurs Rep
December 2024
Mental Health and Specialist Services, West Moreton Health, Brisbane, QLD 4076, Australia.
Background: Optimum efficiency and responsiveness to callers of mental health helplines can only be achieved if call priority is accurately identified. Currently, call operators making a triage assessment rely heavily on their clinical judgment and experience. Due to the significant morbidity and mortality associated with mental illness, there is an urgent need to identify callers to helplines who have a high level of distress and need to be seen by a clinician who can offer interventions for treatment.
View Article and Find Full Text PDFPoint-Cloud Instance Segmentation for Spinning Laser Sensors.
J Imaging
December 2024
European Commission, Joint Research Centre (JRC), Via Enrico Fermi 2749, 21027 Ispra, Italy.
In this paper, we face the point-cloud segmentation problem for spinning laser sensors from a deep-learning (DL) perspective. Since the sensors natively provide their measurements in a 2D grid, we directly use state-of-the-art models designed for visual information for the segmentation task and then exploit the range information to ensure 3D accuracy. This allows us to effectively address the main challenges of applying DL techniques to point clouds, i.
View Article and Find Full Text PDFTemporal Gap-Aware Attention Model for Temporal Action Proposal Generation.
J Imaging
November 2024
National Electronic and Computer Technology Center, National Science and Technology Development Agency, Khlong Nueng, Khlong Luang District, Pathum Thani 12120, Thailand.
Temporal action proposal generation is a method for extracting temporal action instances or proposals from untrimmed videos. Existing methods often struggle to segment contiguous action proposals, which are a group of action boundaries with small temporal gaps. To address this limitation, we propose incorporating an attention mechanism to weigh the importance of each proposal within a contiguous group.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!