Method for identifying well lid part in streetscape image of mobile mapping system

Abstract

The invention discloses a method for identifying a well lid part in a streetscape image of a mobile mapping system. The method comprises the steps of reading image data and obtaining image parameters; preprocessing an image and enhancing edge features in the image; performing edge detection on the preprocessed image by utilizing a weighted vector edge detection method, and obtaining an edge feature image; obtaining edge point sets based on the vector edge feature image, and extracting a vector contour link table corresponding to each edge point set; calculating all vector contour link tables one by one according to a determining criterion, resolving a suspected well lid elliptic equation coefficient by adopting a least square method, and controlling detection precision by utilizing a coefficient similarity threshold and a coefficient counter; and performing false ellipse removal according to geometric characteristics and / or position characteristics of the well lid in the streetscape image of the mobile mapping system. The invention aims to provide the method for identifying the well lid part in the streetscape image of the mobile mapping system, and the method is accurate in positioning and high in identification rate.

Description

technical field [0001] The invention relates to an image recognition method, in particular to a method for recognizing manhole cover parts in a street view image of a mobile mapping system. Background technique [0002] Mobile Mapping Systems (MMS for short) is one of the most cutting-edge scientific and technological achievements in the surveying and mapping industry today, representing the latest development direction in the field of geospatial data collection along roads and data census along roads. MMS is a new type of surveying and mapping and data acquisition device developed by integrating cutting-edge technologies such as Global Navigation Satellite System (GNSS), Inertial Navigation System (INS), CCD image, laser scanner and automatic control. [0003] There are many mobile carrying platforms for multi-sensor MMS, currently the main one is vehicle-mounted. The vehicle-mounted multi-sensor MMS uses vehicle-mounted close-range photogrammetry to realize the rapid coll...

AI Technical Summary

Problems solved by technology

The Hough transform has the advantage of being insensitive to noise, but it has the disadvantage of a large amount of calculation. For the massive images that need to be processed in real time for mobile road mapping, it will not be able to achieve better application results in actual engineering.

(c) The least squares method is an optimal estimation technique derived from the maximum likelihood method when the random error is normally distributed. It has the characteristic of minimizing the sum of the squares of the measurement errors. Due to the complex background environment of the municipal manhole cover and the relatively small area of ​​the effective detection area in the whole image, the existing identification method of the municipal manhole cover in the street view image of the mobile mapping system based on the least squares method is not accurate enough. Problems such as low recognition rate

Images