Software Engineering
Current
University Of London -Goldsmith University
Independently developed a system that processes video frames in real-time using YOLO, improving model accuracy through dynamic retraining.• Built a client-server architecture to stream video frames via socket communication, enabling real-time object detection and annotation.• Implemented automatic retraining of the YOLO model based on newly annotated data, enhancing detection accuracy with each iteration.• Developed a pipeline to compare pre- and post-training performance by generating combined videos, illustrating model improvements.• Integrated ONNX model export to facilitate cross-platform deployment.
2022 - Present
~4 yrs 6 mos
