A human-assisted domestic garbage target recognition system

Abstract

An artificially assisted household garbage target recognition system, the artificially assisted processing module continuously displays each frame of received images, manually draws a straight line on the displayed image on the target object to be sorted, and the artificially assisted processing module recognizes The local plane coordinate information and angle information of the target; at the same time, the recognized information and image information are sent to the computer integrated processing unit; the computer integrated processing unit displays the received image and displays the manually drawn straight line, and the straight line follows the known The moving speed of the target object is translated; according to the received data information, it is judged whether the information identified by the manual auxiliary processing module is accurate, and the finally confirmed accurate information is converted from the local coordinate system to the image coordinate system to obtain the information of the target object identified this time. Eliminate the information of the target identified this time and the one identified last time to obtain the information of the final target, and draw a straight line on the finally recognized target in the display image.

Description

technical field [0001] The invention relates to a human-assisted domestic garbage target recognition system. Background technique [0002] In machine vision technology, the existing image recognition methods usually extract certain features, compare the obtained features with ideal values, and compare the high similarity as the recognition result. [0003] In the field of multi-target sorting, there are many target categories and feature types that need to be identified, such as bottles and cans of various shapes and colors. Due to the large amount of calculation of feature extraction, the method of extracting multiple features cannot be achieved in real time. Meet the requirements; and the accuracy of the feature extraction method has not been high, and it is difficult to meet the use requirements in the industrial automation production line. [0004] The present invention is aimed at the field of sorting and identification of domestic waste. The environment of the domesti...

AI Technical Summary

Problems solved by technology

[0004] The present invention is aimed at the field of sorting and identification of domestic waste. The environment of the domestic waste site is harsh, the composition is complex and diverse, the target object is easily blocked by other non-target objects, and the target object is easily contaminated and mixed with other components, resulting in the shape information and color information of the target object. None of them are outstanding, and cannot be identified by conventional image processing methods or material identification methods

Images