Ship-Detection-on-Remote-Sensing-Synthetic-Aperture-Radar-Data and Trident-synthetic_aperture_radar_maritime_vessel_detection_yolov8
Both tools are competing solutions for maritime vessel detection in Synthetic Aperture Radar (SAR) data, with project A leveraging Faster-RCNN and YOLOv5 architectures and project B utilizing YOLOv8-OBB and Lee speckle filtering.
About Ship-Detection-on-Remote-Sensing-Synthetic-Aperture-Radar-Data
jasonmanesis/Ship-Detection-on-Remote-Sensing-Synthetic-Aperture-Radar-Data
Maritime vessel detection from remote sensing SAR data, based on the architectures of the Faster-RCNN and YOLOv5 networks.
This project helps maritime surveillance and intelligence analysts automatically detect ships in Synthetic Aperture Radar (SAR) satellite imagery. It takes raw SAR images and outputs precise bounding boxes around identified vessels, greatly speeding up the analysis of large datasets. The primary users are professionals involved in monitoring sea lanes or maritime activity using satellite data.
About Trident-synthetic_aperture_radar_maritime_vessel_detection_yolov8
kbhujbal/Trident-synthetic_aperture_radar_maritime_vessel_detection_yolov8
📡 Production-grade maritime surveillance system for detecting ships in Synthetic Aperture Radar (SAR) imagery using YOLOv8-OBB (Oriented Bounding Boxes) and Lee speckle filtering. Handles the unique challenges of radar imagery: multiplicative noise and arbitrarily-oriented vessels.
This system helps maritime surveillance professionals automatically find ships in Synthetic Aperture Radar (SAR) imagery. It takes raw SAR images, processes them to reduce radar-specific noise, and then outputs precise detections of vessels, indicating their exact position and orientation. It's designed for analysts who need to efficiently monitor sea lanes or specific maritime areas.
Scores updated daily from GitHub, PyPI, and npm data. How scores work