Statistical method of pedestrian flow based on RGB and D information fusion

Abstract

The invention discloses a human flow statistics method based on RGB and D information fusion, which comprises the following steps: step 1, collecting an image sample containing human head information;2, marking that head area of the RGB sample, cutting the positive and negative sample, regularizing the size of the cut sample image and attaching corresponding sample labels to different samples; 3,extracting HOG features of all RGB sample image, and inputting that extracted HOG features and the corresponding sample tag into an SVM classifier for training; 4, detecting the head area of the RGBimage in the newly inputted video frame by using the trained SVM classifier; 5, detecting the depth information of Depth image of the newly inputted video frame; 6, fusing that detection results to obtain a final detection target frame; 7, tracking the target object to obtain the moving trajectory of the target object, and counting the human flow information.

Description

technical field [0001] The invention relates to a people flow statistics method based on the fusion of RGB and D information. Background technique [0002] In recent years, the construction of smart cities has become a major trend in the development of social life. The number of people entering and leaving in real time is important information for the control and management of public places, such as public transportation facilities and shopping malls. Obtaining people flow information can not only avoid safety problems caused by excessive people flow, but also can be used to rationally plan time and space resources to obtain better economic benefits. [0003] Traditional people counting technology is realized through revolving doors, laser, infrared, pressure and other sensors. However, in order to obtain the number of people (entry / exit), it is necessary for people to pass the designated sensors in sequence. Therefore, when people walk side by side or there is a large fl...

AI Technical Summary

Problems solved by technology

[0007] Purpose of the invention: to overcome the inaccuracy of head area detection using traditional machine learning methods based on RGB images alone, the unrobustness of directly using the depth information of Depth images that have not been effectively processed, and the high efficiency of deep learning methods. Equipment requirements and large data volume requirements; consider the data failure problem of RGB and Depth images under different care conditions, and introduce a people flow statistics method based on information fusion of RGB and Depth

Images