In recent years, accidents occur frequently because the people number of scenic spots is lack of control. In this paper, a novel real-time people number detection algorithm of scenic spot based on density center clustering (DPBC) is proposed. Taking account of the complexity of the scenic environment, we use the Gauss mixture model (GMM) to suppress the background interference, extract the feature points from the crowd and cluster these feature points by applying a clustering algorithm based on density center. Then we establish a training set and estimate the people number by using the support vector regression model (SVR). We implement the proposed algorithm based on Opencv and use PETS dataset to validate the effectiveness of our proposed algorithm. Experimental results demonstrate that compared with Aibiol algorithm and Conte algorithm, our proposed algorithm improved the accuracy for estimating the people number in a scenic spot.