Journal
IEEE SIGNAL PROCESSING LETTERS
Volume 29, Issue -, Pages 1794-1798Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2022.3198371
Keywords
Convolution; Head; Training; Visualization; Oceans; Measurement; Kernel; Crowd counting; normed-deformable convolution; constrained offsets; uniform sampling
Categories
Funding
- Natural Science Foundation of Shandong Province [ZR2021MF011]
Ask authors/readers for more resources
In this paper, an improved Normed-Deformable Convolution (NDConv) method is proposed to address the issue of crowd counting. By learning the coordinate offsets of the sampling points, the heads are covered more uniformly, leading to more complete head features and improved counting performance.
In recent years, crowd counting has become an important issue in computer vision. In most methods, the density maps are generated by convolving with a Gaussian kernel from the ground-truth dot maps which are marked around the center of human heads. Due to the fixed geometric structures in CNNs and indistinct head-scale information, the head features are obtained incompletely. Deformable Convolution is proposed to exploit the scale-adaptive capabilities for CNN features in the heads. By learning the coordinate offsets of the sampling points, it is tractable to improve the ability to adjust the receptive field. However, the heads are not uniformly covered by the sampling points in the deformable convolution, resulting in loss of head information. To handle the non-uniformed sampling, an improved Normed-Deformable Convolution (i.e.,NDConv) implemented by Normed-Deformable loss (i.e.,NDloss) is proposed in this paper. The offsets of the sampling points which are constrained by NDloss tend to be more even. Then, the features in the heads are obtained more completely, leading to better performance. Especially, the proposed NDConv is a light-weight module which shares similar computation burden with Deformable Convolution. In the extensive experiments, our method outperforms state-of-the-art methods on ShanghaiTech A, ShanghaiTech B, UCF-QNRF, and UCF_CC_50 dataset, achieving 61.4, 7.8, 91.2, and 167.2 MAE, respectively.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available