Method for identifying depth of foundation pit based on multiple cameras

Abstract

The invention discloses a method for identifying the depth of a foundation pit based on multiple cameras in the building field, and the method comprises the following steps: S201, collecting and obtaining paired dual-camera data, including position parameters of the cameras, videos of the cameras and calibration correction of the dual cameras; S202, preprocessing the acquired video data, wherein the preprocessing comprises key frame extraction and frame image preprocessing; S203, performing segmentation by using the trained deep semantic Faster RCNN segmentation network to obtain a foundation pit part. S204, obtaining the upper and lower edges of the foundation pit by using an edge detection algorithm image processing technology, and correcting the position of the part needing to be measured; S205, predicting the depth of a part needing to be measured by using a binocular camera imaging principle, and estimating the depth of the foundation pit. and S206, integrating the depth information of the foundation pit and the measured position information in the S204 and the S205, and visually feeding back the measured part and the estimated height.

Description

technical field [0001] The invention relates to the field of construction engineering, in particular to a method for identifying the depth of a foundation pit based on multiple cameras. Background technique [0002] At this stage, the identification of the depth of the foundation pit on the construction project site is mainly completed by visual inspection and matching measuring instruments, such as box rulers and tape measures. After the measurement is completed, the data is recorded again, and finally the identification of the depth of the foundation pit is achieved. In the identification process, the identification of the depth of the foundation pit is done manually, which increases the cost of the project. Of course, it is difficult to ensure the accuracy and real-time performance of the identification data. Contents of the invention [0003] The purpose of the present invention is to provide a method for automatically identifying the depth of the foundation pit and r...

AI Technical Summary

Problems solved by technology

In the identification process, the identification of the depth of the foundation pit is done manually, which increases the cost of the project. Of course, it is difficult to ensure the accuracy and real-time performance of the identification data.

Images