Open AccessCrowd Density Estimation Based on Multi-Column Hybrid Convolutional Network
Author(s) -
Linlin Guo,
Weimin Zhou
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1828/1/012025
Subject(s) - bilinear interpolation , convolutional neural network , computer science , convolution (computer science) , dilation (metric space) , feature (linguistics) , interpolation (computer graphics) , pattern recognition (psychology) , mean squared error , block (permutation group theory) , algorithm , artificial intelligence , estimator , feature extraction , bicubic interpolation , image (mathematics) , artificial neural network , linear interpolation , mathematics , statistics , computer vision , linguistics , philosophy , geometry , combinatorics
This paper studies an accurate counting model for dealing with highly crowded people, multi-column hybrid convolutional neural network model. The model is mainly composed of three parts. The first part uses the first ten layers of VGG-16 convolutional network for image feature extraction. The middle layer is a dilated convolution with three rows of “jaggy” dilation rates, and each row uses the Resnet-block connection method, which is used primarily to perceive human head features of different sizes. Compared with a variety of image up-sampling ways, in the third part of the model, this paper tries to use a combination of bilinear interpolation and convolution to up-sample image features, and research shows that this method effectively reduces the model error. In this experiment, the average absolute error (MAE), mean square error (MSE) and average relative error (MRE) are used as evaluation indicators, and experiments on the ShanghaiTech dataset proves that the network works well.