Fire-fighting area passability analysis system based on stereoscopic vision

Abstract

The invention discloses a fire-fighting area passability analysis system based on stereoscopic vision. The firefighting area passability analysis system comprises an input module, a depth estimation module and a passability analysis module, the depth estimation module comprises a twin network layer with shared weight, a pyramid stereo matching network, a projection transformation layer and a three-dimensional inverse projection layer; the twin network layer and the pyramid stereo matching network receive the binocular image transmitted by the input module, and pixel-level features for stereo matching and advanced features for target detection are extracted; the projection transformation layer is used for constructing a plane scanning body; the three-dimensional inverse projection layer isused for converting the plane scanning body into a 3D geometry through a derivable image torsion operation, and constructing three-dimensional geometrical characteristics of a world coordinate system;and a passability analysis module which is constructed based on a 3D convolutional network and is used for performing passability analysis on the three-dimensional geometry. According to the invention, the scene depth can be jointly generated, the passability analysis is carried out on the 4 * 4 * 10 m< 3 > space of the fire-fighting area, and the smoothness of a fire-fighting life passage is ensured along with the patrol of the intelligent miniature fire-fighting vehicle-mounted binocular vision system.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an end-to-end deep network, which can realize a fire-fighting area passability analysis system based on stereo vision. Background technique [0002] At present, the fire truck passages in the units or residential areas are managed with signs and markings along the way, and the sign setting of the fire truck passages and the management responsibilities of the fire truck passages are clarified. For the detection of fire truck passages, in the prior art, lidar sensors are mostly installed on inspection vehicles for detection. This method is expensive and not suitable for large-scale applications. In order to reduce the cost, some researchers proposed to use video images to analyze the fire area. However, there are still many problems in the current video image analysis methods. For example, the 2D network cannot extract stable 3D information, or the current block-bas...

AI Technical Summary

Problems solved by technology

For the detection of fire truck passages, in the prior art, lidar sensors are mostly installed on inspection vehicles for detection. This method is expensive and not suitable for large-scale applications.

In order to reduce the cost, some researchers proposed to use video images to analyze the fire area. However, there are still many problems in the current video image analysis methods. For example, the 2D network cannot extract stable 3D information, or the current block-based matching The structure of the Siamese network makes it difficult to use environmental information to find the consistency of unsuitable areas (occluded areas, weakly textured areas, etc.), which makes it difficult for video image analysis methods to be truly applied to the actual inspection process.

Images