ABSTRACT
In view of the difficulty in crowd counting due to occlusion and unequal distribution in crowded scenes, this paper presents a people counting method based on scale adaptive network. In this method, the first ten sixteen-vgg layers are used to initially obtain the population characteristics; then the scale adaptive module designed by us is regarded as the main branch, which can extract the multi-scale population characteristics, and at this stage, the expansion convolution is introduced to further optimize the feature map; in order to effectively solve the occlusion problem between crowds, this paper designs a shallow convolution module as another branch, and fuses its output feature map with that of scale adaptive module. Finally, this paper selects representative datasets to test the method. The results show that in terms of mean absolute error (MAE) and mean square error (MSE), the proposed method is significantly lower than the comparison method.
- WEI M, Crowd density analysis with convolutional netural network [D]. Hefei: China University of science and technology, 2018.Google Scholar
- SIVA P, SHAFIEE, M J, JAMIESON, M, & WONG, A. Scene invariant crowd segmentation and counting using scale-normalized histogram of moving gradients (homg) [J]. 2016, arXiv preprint arXiv:1602.00386.Google Scholar
- BOOMINATHAN L, KRUTHIVENTI S S, & BABU R V. Crowdnet: A deep convolutional network for dense crowd counting. [C] // In Proceedings of the 24th ACM international conference on Multimedia, 2016: 640--644.Google Scholar
- ZHANG Y, ZHOU, D, CHEN, S, GAO, S, & MA, Y. Single-image crowd counting via multi-column convolutional neural network. [C] // In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016:589--597.Google Scholar
- SINDAGI V A, & PATEL V M Cnn-based cascaded multi-task learning of high-level prior and density estimation for crowd counting. [C] // In 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2017:1--6.Google Scholar
- LIU J, GAO C, MENG D, & HAUPTMANN A G. Decidenet: Counting varying density crowds through attention guided detection and density estimation. [C] // In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018:5197--5206.Google Scholar
- LIU X, WEIJER J, & BAGDANOV A D.. Leveraging unlabeled data for crowd counting by learning to rank. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7661--7669.Google Scholar
- LI Y, ZHANG X, & CHEN D. Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes. [C] // In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018:1091--1100.Google Scholar
- SHRIVASTAVA A, GUPTA A, & GIRSHICK R. Training region-based object detectors with online hard example mining. [C] // In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016:761--769.Google Scholar
- SAM D B, SURYA S, & BABU R V. Switching convolutional neural network for crowd counting. [C] // In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017:4031--4039.Google Scholar
- SINDAGI V A, & PATEL V M Generating high-quality crowd density maps using contextual pyramid cnns. [C] // In Proceedings of the IEEE International Conference on Computer Vision, 2017:1861--1870.Google Scholar
- BABU S D, SAJJAN N N, VENKATESH B R, & SRINIVASAN M. Divide and grow: Capturing huge diversity in crowd images with incrementally growing cnn. [C] // In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018:3618--3626.Google Scholar
- SHEN Z, XU Y, NI B, WANG M, HU J, & YANG X. Crowd counting via adversarial cross-scale consistency pursuit. [C] // In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018:5245--5254.Google Scholar
- CAO X, WANG Z, ZHAO Y, & SU F. Scale aggregation network for accurate and efficient crowd counting. [C] // In Proceedings of the European Conference on Computer Vision (ECCV), 2018:734--750.Google Scholar
- SHI Z, ZHANG L, LIU Y, CAO X, YE Y, CHENG M M, & ZHENG G. Crowd counting with deep negative correlation learning. [C] // In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018:5382--5390.Google Scholar
- Liu, Y.B., Jia, R.S., Liu, Q.M., Zhang, X.L. and Sun, H.M., 2020. Crowd counting method based on the self-attention residual network. Applied Intelligence, pp. 1--14Google Scholar
Index Terms
- Crowd Counting Method Based on Scale Adaptive Network
Recommendations
Multi-scale dilated convolution of convolutional neural network for crowd counting
AbstractGrowing numbers of crowd density estimation methods have been developed in scene monitoring, crowd safety and on-site management scheduling. We proposed a method for density estimation of a single static image based on convolutional neural network ...
A scale adaptive network for crowd counting
AbstractScale variations occur frequently and present a great challenge for crowd counting in practical applications. In this paper, we propose a scale adaptive network to address the scale variation problem for crowd counting. We design a ...
Multi-scale dilated convolution of feature Fusion Network for Crowd counting
AbstractCrowd counting has long been a challenging task due to the perspective distortion and variability in head size. The previous methods ignore the multi-scale information in images or simply use convolutions with different kernel sizes to extract ...
Comments