Back to Search
Start Over
Crowd Counting by Using Top-k Relations: A Mixed Ground-Truth CNN Framework.
- Source :
-
IEEE Transactions on Consumer Electronics . Aug2022, Vol. 68 Issue 3, p307-316. 10p. - Publication Year :
- 2022
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
- Subjects :
- *CONVOLUTIONAL neural networks
*ADAPTIVE filters
*SMART cities
*CROWDS
*COUNTING
Subjects
Details
- Language :
- English
- ISSN :
- 00983063
- Volume :
- 68
- Issue :
- 3
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Consumer Electronics
- Publication Type :
- Academic Journal
- Accession number :
- 158242142
- Full Text :
- https://doi.org/10.1109/TCE.2022.3190384