Fire hazard detection robot and method based on deep learning

Abstract

The invention discloses a fire hazard detection robot and method based on deep learning. The detection robot comprises a mobile robot body, a control system, a thermal infrared imager, an RGB-D camera, a laser radar and a gas sensor, wherein the control system, the thermal infrared imager, the RGB-D camera, the laser radar and the gas sensor are fixedly arranged on the mobile robot body; and the control system is respectively in communication connection with the mobile robot body, the thermal infrared imager, the RGB-D camera, the laser radar and the gas sensor. The method comprises the following steps of enabling the control system to control the mobile robot body to carry out automatic inspection, and acquiring an RGB image of a target area and depth information of the target area in real time by the RGB-D camera; completing positioning and map construction through the RGB-D camera and the laser radar; carrying out fire hazard detection and smoldering fire detection in real time; andfinally carrying out graded early warning on the fire hazard. A visual interface is formed, so that the personnel can monitor in real time.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and relates to a fire hazard detection robot and a detection method, in particular to a fire hazard detection robot system and method based on deep learning. Background technique [0002] With the growth of e-commerce, the requirements for the security of e-commerce warehousing and logistics are getting higher and higher. The freight transfer warehouse of the logistics company has the characteristics of a wide variety of goods, a large inventory, and accumulation of various flammable packaging cartons. Once a fire breaks out in a logistics center, the losses are often huge and the lessons learned are profound. At present, the fire detection in the market generally uses the traditional image processing method to detect the flames that have already appeared, which cannot detect the smoldering situation in the environment and other fire hazards in time. At the same time, in response to t...

AI Technical Summary

Problems solved by technology

At present, the inspection of the above-mentioned fire hazards is manual inspection, which has problems such as high cost, low efficiency, and failure to find fire hazards in time.

Images