Color identification and contour extraction-based object dynamic locating method

Abstract

The invention belongs to the field of object locating methods and discloses a color identification and contour extraction-based object dynamic locating method. The method comprises the following steps of 1) performing object marking: applying a tag to the surface of each object needed to be identified; 2) performing data obtaining: collecting images of all tags in real time and transmitting the images to a computer; 3) performing color identification: converting the obtained images to an HSV space from an RGB space, and extracting a pixel pattern of each single-color interval; 4) performing contour extraction: performing the contour extraction, and reserving contours with areas in a screening range; and 5) performing object locating: performing fitting on the contours obtained by screening to obtain a minimum fitting periphery, obtaining central point coordinates of the objects, and then obtaining the positions of the objects. According to the method, the to-be-identified objects are subjected to specific color and shape marking, so that the identification difficulty is lowered; and the RGB space is converted to the HSV space, and the specific color intervals are set, so that accurate color distinguishing and accurate object locating can be realized.

Description

technical field [0001] The invention belongs to the field of object positioning methods, and more particularly relates to a dynamic object positioning method. Background technique [0002] OpenCV is a cross-platform computer vision library released based on BSD license (open source). It can run on Linux, Windows, Android and Mac OS operating systems. It consists of a series of C functions and a small number of C++ classes. It also provides Python, Ruby , MATLAB and other languages, and realize many general algorithms in image processing and computer vision. [0003] OpenCV is committed to real-world real-time applications, and its execution speed has been greatly improved through the writing of optimized C code, and faster processing speed can be obtained by purchasing Intel's IPP high-performance multimedia function library (Integrated Performance Primitives). Applications include: human-computer interaction, object recognition, image segmentation, face recognition, motion...

AI Technical Summary

Problems solved by technology

[0005] Generally speaking, positioning through GPS or other wireless technologies can only locate large objects in a large area. The positioning accuracy is on the order of meters (m), and it is difficult to accurately locate small objects in a small area. Centimeter (cm) order of magnitude, in addition, the positioning of objects by traditional camera positioning is mostly affected by environmental factors, there is a large error, and even the object cannot be recognized

Images