ST-CNN: Spatial-Temporal Convolutional Neural Network for crowd counting in videos.

Yunqi Miao, Jungong Han, Yongsheng Gao, Baochang Zhang

Abstract: Highlights • We propose a crowd counting network (ST-CNN) to accurately calculate the number of people in the scene. • We utilized both spatial and temporal features to solve the problem of crowd counting. • Experiments on two challenging datasets, Mall and WorldExpo010, prove the effectiveness of our method. Abstract The task of crowd counting and density maps estimating from videos is challenging due to severe occlusions, scene perspective distortions and diverse crowd distributions. Conventional crowd counting methods via deep learning technique process each video frame independently with no consideration of the intrinsic temporal correlation among neighboring frames, thus making the performance lower than the required level of real-world applications. To overcome this shortcoming, a new end-to-end deep architecture named Spatial-Temporal Convolutional Neural Network (ST-CNN) is proposed, which unifies 2D convolutional neural network (C2D) and 3D convolutional neural network (C3D) to learn spatial-temporal features in the same framework. On top of that, a merging scheme is performed on the resulting density maps, taking advantages of the spatial-temporal information simultaneously for the crowd counting task. Experimental results on two benchmark data sets â Mall dataset and WorldExpo′10 dataset show that our ST-CNN outperforms the state-of-the-art models in terms of mean absolutely error (MAE) and mean squared error (MSE). Previous article in issue Next article in issue