Deep learning-based call answering and making behavior analysis method and equipment

Abstract

The invention belongs to the field of image recognition, and particularly relates to a deep learning call answering and making behavior analysis method and device, and the method comprises the following steps: a system automatically learns visual features from the image data of a large number of people answering and making calls through a deep convolutional neural network, represents the behaviors, and builds a database; an image acquisition device, namely a camera, is used for monitoring the interior of the gas station in real time, capturing and monitoring figure forms and actions and transmitting data to the system; due to the effect of deep learning, the system can analyze the captured image and compare the image with a database; by arranging a wind wheel, the wind wheel can drive a cam to rotate, by arranging the cam and a first spring, the cam can enable a lifting plate to do reciprocating motion in the vertical direction so as to drive a sponge block to do reciprocating motion on the surface of a lens, by arranging a second spring, the sponge block can keep pressure on the lens all the time, and cleaning of the lens is achieved; and the operation is relatively convenient.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a deep learning method and device for analyzing the behavior of making and receiving calls. Background technique [0002] In some special occasions, it is not allowed to make calls, which will cause potential safety hazards. For example, in gas stations and other places, the behavior of making calls is strictly monitored in the gas station. Once the behavior of making and receiving calls is found, the staff should immediately go to stop it. . [0003] Currently, cameras are used to monitor the gas station, and gas station staff are required to watch the surveillance video in real time and check whether people in the gas station are answering or making phone calls. [0004] However, the current camera does not have the function of automatically cleaning the lens. In special weather, water mist or water droplets will appear on the lens of the camera, which affects the monitoring o...

AI Technical Summary

Problems solved by technology

[0004] However, the current camera does not have the function of automatically cleaning the lens. In special weather, water mist or water droplets will appear on the lens of the camera, which will affect the monitoring of the camera. After a long time of use, dust will adhere to the lens of the camera, which will affect the use of the camera. , it needs to be wiped in time; therefore, a method and equipment for analyzing the behavior of making and receiving calls based on deep learning are proposed to solve the above problems

Images