Real-time monitoring method based on multi-sensor fusion and used for action of fire-fighting robot

Abstract

The invention discloses a real-time monitoring method based on multi-sensor fusion and used for the action of a fire-fighting robot. The real-time monitoring method comprises he following steps: obtaining the video of a fire scene in real time through a camera, acquiring the movement information of the fire-fighting robot in real time through an angular speed sensor and a gravity sensor, and carrying out fusion processing, resolving the attitude change data of the fire-fighting robot in real time, and carrying out image pre-processing on video frames; identifying a straight travelling mode ofthe fire-fighting robot according to the dynamic change features of a triaxial acceleration module value obtained by the angular speed sensor and in combination with the resolved course angle of the fire-fighting robot; after acquiring and processing images, building an image identification model through a model of a convolutional neural network; and identifying and obtaining a target ignition point position according to the image identification model, designing different steering control with regard to the different target ignition point positions according to the target ignition point position identified by the image identification model, and carrying out robot fire-extinguishing operation. The real-time monitoring method further comprises the steps of clustering and classifying for therobot fire-extinguishing action.

Description

technical field [0001] The invention belongs to the field of machine identification, in particular to a method for real-time monitoring of fire-fighting robot actions based on multi-sensor fusion. Background technique [0002] With the continuous popularization of robot technology, robots that can enter and extinguish fires in fire scenes have been manufactured in hardware. In many dangerous scenes, using robots to extinguish fires is not only efficient, but also can greatly reduce uncertain risks. The secondary injury caused by the source can save the lives of firefighters. However, at present, the control algorithms of fire-fighting robots on the market still have the problems that the target ignition point is not easy to identify, and the robot's action control is not clear, which sometimes leads to blind fire-fighting robots and cannot effectively complete the task. Therefore, it is extremely important and urgent to provide a highly recognizable algorithm suitable for f...

AI Technical Summary

Problems solved by technology

However, at present, the control algorithms of fire-fighting robots on the market still have the problem that the target ignition point is not easy to identify, and the robot's action control is not clear, which sometimes leads to blind fire-fighting robots and cannot effectively complete the task.

Images