migYOLO - An end-to-end YOLOv8-based object detection pipeline for CMOS camera images recorded by the MIGDAL experiment ...
migYOLO v1.0.0 migYOLO is the software accompanying the MIGDAL collaboration paper titled Transforming a rare event search into a not-so-rare event search in real-time with deep learning-based object detection. This package includes model weights for two YOLOv8m models custom trained on image data r...
| Main Author: | |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | English |
| Published: |
Zenodo
2024
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.5281/zenodo.12628437 https://zenodo.org/doi/10.5281/zenodo.12628437 |
| Summary: | migYOLO v1.0.0 migYOLO is the software accompanying the MIGDAL collaboration paper titled Transforming a rare event search into a not-so-rare event search in real-time with deep learning-based object detection. This package includes model weights for two YOLOv8m models custom trained on image data recorded by the ORCA Quest qCMOS camera readout of the MIGDAL TPC, as well as a sample of 800 raw camera images to demonstrate usage of the pipeline, and 400 additional camera frames for benchmarking the processing speed of the camera. Please consult the migYOLO git repository and official documentation for more detailed descriptions of the software package and its contents, as well as up to date information about installation and usage. ... |
|---|