Deep Learning Model
Real Time Object Detection
This project was implemented to identify potential threats by detecting people within a one-mile radius using a sensor-based system. An object detection model was trained and tested to recognize both living and non-living objects. The model was also integrated with a security camera setup to monitor and detect unusual activities. YOLO was used as the primary detection framework, along with OpenCV and Supervision.
Role
Independent Project
Collaborators
Srikanth Akkaru
Duration
2022-2023
Tools
Python
YOLO
TensorFlow
OpenCv
Overview & Features
This project showcases real-time object detection using YOLOv9, coupled with Supervision for annotating detected objects on security camera feeds. The system generates real-time logs in nested JSON format, detailing object counts with respective timestamps, and implements a priority system to flag objects based on predefined criteria.
- Real-Time Object Detection: Utilizes YOLOv9 for object detection on live security camera feeds.
- Annotation & Visualization: Uses Supervision to annotate detected objects with bounding boxes and labels.
- Data Logging: Produces nested JSON logs containing per-frame object counts and timestamps.
- Priority System: Flags objects based on presence and duration using a configurable priority mechanism.
- Configurability: Supports customization via JSON configuration files, including camera URLs and parameters.
Requirements
- Python 3.x
- OpenCV (cv2)
- Supervision
- Ultralytics YOLO
Loading...
Redesigned notifications to be more communicative and systematic across domains.
Successfully tested using real time data.
The above footage is to check how good the model detects a person in a driveway from a CCTV camera.