This chapter presents an approach for crowd density estimation in public scenes from a surveillance camera. We formulate the problem of estimating density in a structured learning framework applied to random decision forests. Our approach learns the mapping between image patch features and relative locations of all the objects inside each patch, which contribute for generating the patch density map through Gaussian kernel density estimation. We build the forest in a coarse-to-fine manner with two split node layers and further propose a crowdedness prior and an effective forest reduction method to improve the estimation accuracy and speed. Moreover, we introduce a semiautomatic training method to learn the estimator for a specific scene. We achieved state-of-the-art results on the public Mall and UCSD datasets and also proposed two potential applications in traffic counts and scene understanding with promising results.