A crowd counting method based on deep learning target detection

Abstract

The invention discloses a crowd counting method based on deep learning target detection. The crowd counting method comprises the following steps of constructing a deep learning network model: adoptinga YOLO3 network taking a DarkNet network as a basic network; processing the training data, obtaining crowd image data under multiple scenes, and expanding the scale of the training set in an image mirroring processing and scale random interception manner; and training the network: optimizing the network through the loss function and the gradient descent training parameters. The invention aims toovercome the defects of the existing crowd counting. In a specific environment, a target detection method based on a deep neural network is adopted to count and count crowds, so that the problem of low accuracy in a traditional feature extraction method is solved, and also the problem that errors are large under the condition of crowd sparsity in a deep learning feature regression method is solved, the detection speed is greatly increased, the detection speed is four times the speed based on a 101-layer residual network RetineaNet (retinal network), and the precision is equivalent to that of the 101-layer residual network RetineaNet (retinal network).

Description

technical field [0001] The invention relates to a crowd counting method in the field of computer vision, in particular to a crowd counting method based on deep learning target detection. Background technique [0002] With the growth of the population and the acceleration of the urbanization process, there are more and more behaviors of crowds gathering in large numbers, and the scale is getting bigger and bigger, and the resulting stampede incidents are also increasing day by day. In order to facilitate the management of the city, the administrator has installed a large number of cameras in the city. At present, crowd density estimation and accurate crowd counting through surveillance video is one of the research hotspots in the field of computer vision. This technique is commonly used in: [0003] 1. Highly complex occasions where crowds are concentrated. Such as: large public places such as gymnasiums, canteens, squares, etc. The crowd counting system can estimate the ...

AI Technical Summary

Problems solved by technology

[0017] (3) It is not suitable for crowded places

Moreover, this method is only suitable for use in scenes with a relatively small number of people, such as at the bus gate. If there are a lot of occlusions in the scene, the results obtained by using this method are not ideal.

[0020] 3. The direct method in the feature-based regression method requires foreground segmentation, and the quality of the segmentation performance directly affects the final calculation result. However, the foreground segmentation is a relatively difficult task, and the performance of the algorithm is largely affected by it. , so the performance and accuracy of this method will be greatly reduced in places where the crowd is relatively concentrated, so this is an important factor limiting the performance of this method

[0022] At present, the mainstream of the target detection network based on deep learning is based on the deep residual network, which realizes the purpose of target detection by training the coordinates and object categories of the bounding box. The disadvantage of using the deep residual network as the basic network is slow speed. The last few layers of the network have redundancy, which is not optimal for feature extraction efficiency

Images