https://github.com/vaishnavi502/ric-cctv

https://github.com/vaishnavi502/ric-cctv

Last synced: 24 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/vaishnavi502/ric-cctv
• Owner: Vaishnavi502
• Created: 2023-08-29T00:55:23.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-01-19T04:57:55.000Z (12 months ago)
• Last Synced: 2024-01-19T05:53:51.168Z (12 months ago)
• Language: Python
• Size: 14.8 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# ric-cctv

## Real-time Image Captioning for CCTV grabs

Current version:

Uses yolov3-tiny for "person" identification


Custom training done on yolov3 to identify 4 classes including "delivery person" and "package"


Data annotation done in Roboflow by [@Subhiksha](https://github.com/Subhiksha-Sakthivel) and [@Debika](https://github.com/deeepp)

yolov3-tiny download links:

[darknet](https://github.com/pjreddie/darknet)


https://github.com/smarthomefans/darknet-test/blob/master/yolov3-tiny.weights


https://github.com/pjreddie/darknet/blob/master/data/coco.names


Instructions for custom training: https://github.com/spmallick/learnopencv/tree/master/YOLOv3-Training-Snowman-Detector


[Ref1](https://stackoverflow.com/questions/28717054/calculating-sharpness-of-an-image)


[Ref2](https://pyimagesearch.com/2015/09/07/blur-detection-with-opencv/)