Improved YOLOv4 for Water Wastes Detection
Gu Shaokui, Niu Jinxing, Li Longyan
Journal of Scientific Research and Reports · pp. 85–95 · Published 31 Aug 2022
10.9734/jsrr/2022/v28i1030561Abstract
Quantifying plastic refuse in water area helps to understand how plastic refuse accumulates in water area and is essential for targeted cleanup efforts. Currently, the most common methods for quantifying plastic in water area are human visual counting and sampling using nets, but such methods are costly and labor-intensive. This study proposes a watershed refuse identification algorithm based on an improved YOLOv4. Lightweight improvements to YOLOv4. EfficientNetB1 is used to replace the backbone network of YOLOv4, and the Depthwise Convolution is used to replace the original convolution to reduce the number of model parameters and computation. The anchors are re-clustered using k-means algorithm to improve the accuracy. The experimental results show that the improved algorithm improves the detection speed by 11.2% and reduces the number of parameters by 76.54% compared with YOLOv4 at the expense of 0.69% recognition accuracy.
Cited by 0
No indexed citations yet.
Related research
- Automatic Segmentation of Organ at Risk in Head and Neck Cancer CT Images Using Medical Open Network for Artificial Intelligence (MONAI) with Deep Learning Techniques — shares topic coverage
- Diagnostic Accuracy of Artificial Intelligence for Breast Cancer Detection: A Systematic Review — shares topic coverage
- Leveraging Deep Learning Algorithms for Predicting Power Outages and Detecting Faults: A Review — shares topic coverage
- Bridging Prenatal Diagnostics and AI: A Systematic Review and Meta-Analysis of the Efficacy of Advanced Algorithms in Identifying Congenital Fetal Abnormalities — shares topic coverage
- Applications of Deep Learning in Predicting the Risk of Metabolic Syndrome from Lifestyle and Behavioral Factors: A Scoping Review — shares topic coverage
Article metrics
Real usage data collected on this platform.
0
Page views
0
PDF downloads
0
Outbound clicks
0
Citations
Views by country
Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".
No views recorded yet.
Traffic sources
Referring site, by host.
No traffic recorded yet.
Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.