Crowd counting method based on scene depth information

Abstract

The invention discloses a crowd counting method based on scene depth information, which comprises the following steps of: (10) image segmentation: extracting depth information of an input image by adopting a monocular image depth estimation algorithm, and segmenting the input image into a close-range region and a distant-range region according to the depth information; (20) close-range area crowdcounting: predicting a head boundary frame of the close-range area by adopting a crowd counting method based on target detection to obtain the number of people in the close-range area; (30) crowd counting in a distant view area: predicting a crowd density map in the distant view area by adopting a crowd counting method based on density estimation, and solving the product of the crowd density map in the distant view area to obtain the number of people in the distant view area; and (40) confirmation of the number of people in the input image: adding the number of people in the distant view areaand the number of people in the close view area to obtain the total number of people in the input image. The crowd counting method based on the scene depth information is good in multi-scale adaptability, low in overfitting degree and accurate in counting.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This patented technology improves upon existing techniques such as multilevel adaptation (MLA) or deep belief networks (DBN). It allows us to train multiple models simultanously instead of one at once, allowing for more flexibility when selecting appropriate regression functions depending on different scenes' sizes. Additionally, it introduces a new approach called Multiplex Coding Network (MCNN), where each region represents only part of the original dataset while other parts are combined together. By doing these modifications, we aim to reduce overfit phenomena during training without compromising accuracy. Overall, our technical effect lies within improved versatility across various applications including crowning count analysis, object recognition, and motion tracking.

Problems solved by technology

Technological Problem addressed in this patents relates to improving crowd counting systems' capabilities without sacrificial effort towards specific objects like humans. Current solutions involve either stator pattern recognition algorithms or fully trained models, but these approaches require extensive prior knowledge about the environment being observed.

Images