Method and system for detecting and positioning regular object in real time

Abstract

The invention relates to a method for detecting and positioning a regular object in real time. The method comprises the following steps: processing a region of interest containing the object into a binary image; integral processing is performed on the binarized image, and a clustering center point is acquired through a clustering algorithm; and estimating the distance and attitude relationship ofthe object according to the clustering center point. The invention further relates to a system for detecting and positioning the regular object in real time. According to the invention, the detectionaccuracy and robustness can be improved.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a method and system for real-time detection and positioning of regular objects. Background technique [0002] With the trend of modern industrialization, machine vision plays an important role in industrialization. Object detection based on vision is a research hotspot in localization. Indoors have the characteristics of complex environment, light conditions, moving speed of objects, and many obstacles. For these harsh environments, improving the robustness, accuracy and efficiency of detection is the difficulty of visual inspection. The detection and positioning of objects is an important step in the realization of modern automation technology. At present, in unmanned driving, the detection and positioning of obstacles is very challenging, and the efficiency of detection and positioning should be higher; in terms of intelligent logistics , to achieve the extraction of t...

AI Technical Summary

Problems solved by technology

Among them, although the cost of monocular vision detection is low, its accuracy is not high, and it is easily affected by the external environment; although the detection based on multi-line lidar has high accuracy, the price of multi-line lidar is too expensive, and it is easily affected by the external environment. The interference of obstacles leads to false detection; the detection based on special labels, such as Aruco's method, requires too high accuracy for labeling, and it is easy to be destroyed, resulting in the failure to detect two-dimensional codes; positioning based on Bluetooth or RFID technology, It is difficult to meet the ideal requirements in terms of accuracy, and in the case of a large number of goods, the positioning information of the pallet is lost, etc.

[0004] In recent years, the detection research on pallets mainly adopts detection methods based on vision, lidar and the combination of the two. Among them, the detection method based on visual labels is easily affected by label contamination and is not robust to illumination. ; Although the method based on single-line lidar overcomes the influence of illumination, the range of single-line scanning is limited; although the method based on multi-line lidar and visual fusion can improve the accuracy, the price of multi-line lidar is expensive, resulting in cost The improvement, and it is very complicated to complete the joint calibration and registration between the radar and the camera

Images