Poster: Generating Scarce Realities for Traffic Light Violation Detection
Taiga Kume, Hiroo Bekku, T. Okoshi, Jin Nakazawa · 2024
The preparation of a large and diverse dataset is essential for training a robust deep learning model. However, there are instances where certain data are theoretically possible but challenging to observe in reality (e.g., traffic light violations). We refer to these unique instances as 'Scarce Realities', highlighting their rarity and the difficulties they present in data collection and model training. One effective and emerging approach involves using generative models to generate and augment such data. In this study, we demonstrate the promising potential of combining object detection models with simple image generation models as a way to generate fake videos. We achieve this by partially editing existing videos to artificially create 'Scarce Realities', using the generation of fake dashboard camera footage of traffic light violations as an example.