Crowd Counting by Using Top-k Relations: A Mixed Ground-Truth CNN Framework

Crowd counting has important applications in the environments of smart cities, such as intelligent surveillance. In this paper, we propose a novel convolutional neural network (CNN) framework for crowd counting with mixed ground-truth, called top-
$k$
relation-based network (TKRNet). Specifically, the estimated density maps generated in a coarse-to-fine manner are treated as coarse locations for crowds so as to assist our TKRNet to regress the scattered point-annotated ground truth. Moreover, an adaptive top-
$k$
relation module (ATRM) is proposed to enhance feature representations by leveraging the top-
$k$
dependencies between the pixels with an adaptive filtering mechanism. Specifically, we first compute the similarity between two pixels so as to select the top-
$k$
relations for each position. Then, a weight normalization operation with an adaptive filtering mechanism is proposed to make the ATRM adaptively eliminate the influence from the low correlation positions in the top-
$k$
relations. Finally, a weight attention mechanism is introduced to make the ATRM pay more attention to the positions with high weights in the top-
$k$
relations. Extensive experimental results demonstrate the effectiveness of our proposed TKRNet on several public datasets in comparison to state-of-the-art methods.