https://github.com/niteshctrl/intruder-mobile-notification-system
On Progress | | Notifications will be sent on Telegram with intruder images | | Stay tuned for more
https://github.com/niteshctrl/intruder-mobile-notification-system
object-detection telegram-notification yolov3
Last synced: 20 days ago
JSON representation
On Progress | | Notifications will be sent on Telegram with intruder images | | Stay tuned for more
- Host: GitHub
- URL: https://github.com/niteshctrl/intruder-mobile-notification-system
- Owner: niteshctrl
- License: mit
- Created: 2021-06-26T07:48:44.000Z (almost 5 years ago)
- Default Branch: main
- Last Pushed: 2021-07-04T19:17:47.000Z (almost 5 years ago)
- Last Synced: 2023-12-09T21:26:16.302Z (over 2 years ago)
- Topics: object-detection, telegram-notification, yolov3
- Language: Jupyter Notebook
- Homepage:
- Size: 20.5 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Real-Time Intruder Notifier(BETA)
## Under Construction.
#### Patience is the key!! Meanwhile grab a pair of dumbbells and have a look at [Biceps Curl Counter](https://github.com/niteshctrl/BicepCurlCounter)
---
## Improvements TBD:
- [ ] Reduce Inference latency
- [ ] Use multiprocessing to save video(OpenCV) and process video(YOLO) simultaneously.
Currently, the function calls have the following time delays:
|After Fn call | Frames processed/~10sec|
| :---: | :---: |
|model.predict | 72 |
|Decode_netout: | 17 |
|rescale_yolo_boxes: | 15 |
|do_nms: | 03 |
|filter boxes: | 02 |
| - | - |
|final: | 02 |