Deep Learning for Computer Vision - building end-to-end systems from perception to deployment.
B.Eng. - Automation & Control Engineering Technology (HCMUTE).
- Edge AI (Jetson) + real-time CV
- Robotics systems (vision + motion + control)
- Practical deployment: streaming, APIs, telemetry, alerts
- Two-stage cascaded detection (smoke -> fire confirmation) to reduce false positives
- Jetson Nano deployment with TensorRT FP16; RTSP/MJPEG streaming
- Data fusion: detections + Pixhawk telemetry for geo-tagged alerts
- Auto LOITER on smoke detection + Telegram alerts
Repo: https://github.com/khangle2101/Real-Time-Fire-Smoke-Detection-Drone
- HSV segmentation + calibration (pixel -> mm) for pick coordinates
- MATLAB forward/inverse kinematics, Arduino stepper control
- Includes Unknown rejection case (markings/ink) to avoid misclassification