In some constrained domains(eg: car driver), the camera is stationary which means the background will not change much. And we can sure when the car is running, there must be a driver. In this kind of cases, are there any fast face detection models that don't contain deep neural networks? I'm asking this because deep neural networks need lots of data to train and wondering if there are some "cheaper" models?
Arguably the best known facial detection algorithm is Viola-Jones, which was proposed in 2001 and does not involve any Neural Networks. Instead the original framework was trained using a variant of AdaBoost, classifying Haar features. This algorithm is very popular because it's lightweight, fast and sufficiently accurate,.