Action real-time monitoring method based on YOLO

Abstract

The invention provides an action real-time monitoring method based on YOLO. The method comprises the following steps of: S1, building a scene model which is configured to carry out the video collection of a position where a camera is located, S2, detecting a target in the scene model to obtain a detection box, S3, constructing and training a deep learning extraction network, and inputting the detection boxes of all people into the network to obtain feature vectors of all the detection boxes, S4, predicting an action vector of the video tracking target, and performing dangerous action matchingor prediction on the tracking target by utilizing the feature vector of the detection frame and the predicted action vector to obtain an optimal matching and prediction detection frame, S5, performingred marking processing on the target detection frame of the dangerous action, S6, performing alarm prompt. By adopting the detection frame, red marking processing can be carried out, so that the camera pays attention, an object in the detection frame can be detected in real time, and the action of a person is ensured to be accurately recognized.

Description

technical field [0001] The invention relates to the technical field of motion monitoring, in particular to a YOLO-based real-time motion monitoring method. Background technique [0002] In community monitoring, the main thing is to rely on security guards to be on duty on the monitoring screen, which not only consumes a lot of manpower, but also has great defects in the manual on-duty monitoring screen, which cannot give real-time warnings to dangerous people and dangerous actions in the monitoring. [0003] For example, CN110569711A prior art discloses a Kinect-based graphic recognition. In static image recognition, when the operator is far away, the captured image is blurred, and image information cannot be accurately extracted. At the same time, there is a problem of slow processing speed in dynamic recognition. shortcoming. Another typical prior art such as CN102521579A discloses an action recognition method and system based on two-dimensional planar camera push, which ...

AI Technical Summary

Problems solved by technology

The robustness of the segmentation effect of the traditional method is poor, and it cannot distinguish the skin areas of different people in the image, and the effect in complex scenes is even less ideal.

[0004] In order to solve the common problems in the field such as single detection means, inaccurate detection and inability to monitor the action behavior of the target, the present invention is made

Images