Multi-scale shared features for cascade object detection

We introduce an efficient computational framework to extract multi-scale feature descriptors. The framework is based on sharing of descriptor elements across the image and scale space to minimize redundant computation. Any type of local patch or grid-based features can be computed through this framework for capturing coarse-to-fine object appearances. We apply it to human detection by boosting a strong soft cascade classifier. Our experiments demonstrate that the proposed descriptors achieve superior performance both in computational efficiency and detection accuracy.