Abstract
With the rapid development of computer vision and artificial intelligence, crowd counting has attracted significant attention from researchers and many well-known methods were proposed. However, due to interocclusions, perspective distortion, and uneven crowd distribution, crowd counting is still a highly challenging task in crowd analysis. Motivated by granular computing, a novel end-to-end crowd counting network (GrCNet) is proposed to enable the problem of crowd counting to be conceptualized at different levels of granularity, and to map problem into computationally tractable subproblems. It shows that by adaptively dividing the image into granules and then feeding the granules into different counting subnetworks separately, the scale variation range of image is narrowed and the the adaptability of counting algorithm to different scenarios is improved. Experiments on four well-known crowd counting benchmark datasets indicate that GrCNet achieves state-of-the-art counting performance and high robustness in dense crowd counting.