Wood counting method based on deep learning

Abstract

The invention discloses a wood counting method based on deep learning, and the method comprises the specific steps of photographing a set number of wood pictures, marking the wood contour in the images, and forming a data set; inputting the data set into a Mask RCNN model for training; performing preprocessing operation on the to-be-detected picture, and enabling the picture to be clearer by using an image enhancement algorithm; inputting the preprocessed to-be-detected picture into the trained Mask RCNN model to obtain a mask area of the wood section and wood area frame coordinates; performing overlapping judgment on the wood area by utilizing the coordinates of the wood area frame, and deleting the area coordinate points which are judged to be overlapped; carrying out false detection judgment on the area around the wood by utilizing the coordinates of the wood area frame, and deleting the area coordinate points of the wood which is judged to be false detected; and counting the coordinates of the remaining areas to obtain the number of the woods. The invention is not interfered by the environment, the robustness of the deep network is high, and the invention is more suitable for the actual production environment.

Description

technical field [0001] The invention belongs to the field of artificial intelligence detection, and specifically relates to a wood counting method based on deep learning. Background technique [0002] For wood production and processing enterprises, automatic counting of wood has always been a difficult problem, and many enterprises still mainly rely on manual counting. Manual inspection is time-consuming, labor-intensive, low-efficiency, subjectivity is high, precision is low and inaccurate, and disputes are likely to arise. Therefore, for a large number of repetitive tasks, consider using computers to replace humans, and develop a set of algorithms to automatically calculate the number of wood. [0003] The development of existing technologies and the continuous reduction of the price of image equipment make digital image recognition technology develop rapidly and be widely used in many fields. Digital image recognition can be applied to automatic counting of wood. First,...

AI Technical Summary

Problems solved by technology

However, the image processing technology has high requirements on the quality of the wood image. At night, in rainy or foggy days, the captured image is not clear enough, and the image recognition technology cannot separate the background through the pixel color value.

Therefore, digital image recognition technology has limitations and is not very versatile

Images