Deep learning-based image high-density population counting method
A deep learning and crowd counting technology, applied in the field of image processing, can solve problems such as perspective distortion, poor effect of crowd counting algorithms, and poor adaptability, and achieve strong generalization ability, easy learning, and good robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0046] Example
[0047] Based on the theory of convolutional neural network in deep learning, the present invention proposes a convolutional neural network model with complementary depth and shallow depth to complete the crowd density estimation of a single high-density crowd image. The method flow is as follows figure 1 Shown:
[0048] First use the deep learning framework caffe to build a deep and shallow complementary convolutional neural network;
[0049] Then, the existing public data sets UCF_CC_50, UCSD, WorldExpo and ShanghaiTech images in the data are enhanced, and finally the image data is enlarged to 192 times;
[0050] After the enhanced image data is processed by Gaussian kernel fuzzy normalization, the real crowd density map is obtained. The network output estimated density map and the real density map are continuously iteratively trained to optimize the entire network structure according to the loss function;
[0051] Input the crowd pictures and label pictures to the net...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap