Building facade window detection system based on multi-feature map fusion

Abstract

The invention discloses a building facade window detection system based on multi-feature map fusion. The system comprises a feature map extraction module used for extracting a key point probability map for describing window vertex features, a key point label map for describing window vertex label information and a center point probability map for describing window center point features according to an input color building facade image; the window generation module is used for clustering the key points belonging to the same window according to the key point probability graph and the key point label graph, and generating a polygon as a preliminary window detection result according to the key points belonging to the same kind; and the central point verification module is used for verifying the preliminary window detection result according to the central point probability graph so as to filter out an incorrect preliminary window detection result. The building facade window detection systemgreatly improves the effect and robustness of window detection.

Description

technical field [0001] The invention belongs to the field of building facade analysis, in particular to a building facade window detection system based on multi-feature map fusion. Background technique [0002] In recent years, the construction of smart cities has become one of the important development directions of our country. Smart cities integrate the constituent systems and services of cities to improve the efficiency of resource utilization, optimize urban management and services, and improve the quality of life of citizens. At present, the construction of smart cities is a hot issue in the fields of information technology and urban planning. In the process of building a smart city, image-based reconstruction of a large-scale 3D virtual city is an indispensable part, and it has broad application prospects in intelligent navigation, traffic management, urban planning, etc. Building facade analysis is the core basic part of 3D virtual city reconstruction. Windows are ...

AI Technical Summary

Problems solved by technology

[0006] (1) Building facade images collected outdoors often contain irrelevant elements and occlusions, such as signal lights, trees, vehicles, etc. These irrelevant elements and occlusions will interfere with the window detection effect

At the same time, changes in light, shadow and reflection will also cause great interference to the algorithm itself.

However, most current work has few modules that explicitly deal with these issues;

[0007] (2) A large part of the building facade images collected outdoors are taken from the side view, and there is even some distortion

Therefore, once the input image does not meet these requirements, the result will be unsatisfactory

Images