Navigation system and method for indoor fire escape

Abstract

The invention discloses a navigation system and method for indoor fire escape. The system is simpler to operate for an individual user, does not need to wear additional equipment, and is easier to accept by the user. Meanwhile, existing indoor equipment is utilized to the maximum extent, extra installation, arrangement and regular maintenance are not needed to ensure the precision, the cost can besaved, and overall arrangement of the system is simple and flexible; even if a part of the camera does not work, the operation of the whole system is not easily influenced, and relatively high positioning precision can be achieved even if a part of area is invisible; meanwhile, a user posture detection function is achieved, a current state of the user is judged, the smoke state is deduced, and atrapped user is kept still. The information can help subsequent firefighters to carry out rescue decision judgment.

Description

technical field [0001] The invention relates to the technical field of fire escape, in particular to a navigation system and a method for escape from an indoor fire. Background technique [0002] The positioning systems used in current fire escapes are mostly used by firefighters, and require additional equipment and relevant professional operating knowledge, which makes these systems less suitable for indoor personnel escape. [0003] For indoor escape personnel, their location and current state are also important for firefighters to adopt more effective lifesaving strategies when they arrive at the scene. Relying on effective indoor positioning and navigation, most of the indoor personnel can leave the fire scene when the firefighters arrive at the scene. The position and state of the remaining trapped personnel will be reported to the firefighters based on the information monitored by the positioning system to help them formulate related rescue plans. [0004] In the sy...

AI Technical Summary

Problems solved by technology

However, the current design of this system is 2D positioning, without height information, and the obtained position information is relative position, which cannot be seamlessly connected with outdoor positioning systems, and the visual tracking layout adopts a fixed framing method, which is only suitable for single camera shooting However, it cannot be flexibly applied to multi-camera conversion, and the tracking algorithm also uses the traditional feature extraction method. This algorithm is relatively inflexible and needs to be adjusted according to the actual situation, and it cannot achieve real-time monitoring, let alone distinguish the body of pedestrians at the fire scene in real time. posture state

At the same time, when the system data is fused, the method of matching visual step points and inertial step points is often used, and the algorithm is relatively cumbersome.

Images