Developer—Multimodal Video Intelligence Platform
VideoObject Detection
I developed and deployed a multimodal video intelligence system that included automated labeling and detection functions for various video attributes. My work involved training YOLOv8 on over 600 classes and implementing person and object detection across multiple video feeds. I also managed the underlying data collection, annotation, and model validation process for these tasks.
• Collected and annotated large volumes of video data for object and person recognition.
• Trained YOLOv8 for real-time object detection and used RetinaFace and FaceNet for identity tracking.
• Processed and summarized labeled video data for improved system performance.
• Maintained quality control and continuous evaluation of labeled datasets.
I developed and deployed a multimodal video intelligence system that included automated labeling and detection functions for various video attributes. My work involved training YOLOv8 on over 600 classes and implementing person and object detection across multiple video feeds. I also managed the underlying data collection, annotation, and model validation process for these tasks. • Collected and annotated large volumes of video data for object and person recognition. • Trained YOLOv8 for real-time object detection and used RetinaFace and FaceNet for identity tracking. • Processed and summarized labeled video data for improved system performance. • Maintained quality control and continuous evaluation of labeled datasets.
2024 - 2025