Leaf segmentation method based on multi-scale double-attention mechanism and full convolutional neural network

Abstract

The invention discloses a segmentation system based on a multi-scale double attention mechanism and a full convolutional neural network, which comprises a feature extraction backbone network, a feature pyramid network, a semantic segmentation network, a target detector, a coefficient predictor and a fusion module, and is characterized in that the semantic segmentation network comprises a first convolutional layer, an attention module and a second convolutional layer; the feature extraction backbone network is a VoVNet57 network and is used for extracting features of a training set image and a test set image and sending the features to the feature pyramid network; the feature pyramid network is used for performing same-level feature map fusion to obtain a P3-P7 feature map; a P3-P7 feature map obtained through the feature pyramid fusion network is input into an FCOS target detector, thus generating a suggestion box category and a position thereof pixel by pixel by the target detector, and performing a Soft NMS operation on the suggestion box to obtain a final detection box; a coefficient predictor performs weight prediction of instance information on the detection frame to generate an instance proportion corresponding to the detection frame; the semantic segmentation network is used for processing the P3-P6 feature map obtained through the feature pyramid fusion network to generate four segmentation maps; and the fusion module is used for superposing the four segmented images and the detection frame and outputting a final segmented image according to the corresponding instance proportion.

Description

technical field [0001] The invention relates to an image processing method, in particular to a leaf segmentation method based on a multi-scale double-attention mechanism and a fully convolutional neural network. Background technique [0002] Plant phenotype plays an important role in genetics, botany and agronomy. Among the organs of most plants, leaves account for the largest proportion and play a vital role in vegetation growth and development. The morphological structure and physiological parameters of leaves Estimation is of great significance for vegetation growth monitoring, and the observation of leaves can help reveal its growth status, and ultimately help us identify genetic contribution capabilities, improve plant genetic characteristics, and increase crop yields. In high-throughput phenotyping, automatic segmentation of plant leaves is a prerequisite for measuring more complex phenotypic traits. Although leaves have distinct appearance and shape features, occlusi...

AI Technical Summary

Problems solved by technology

Although leaves have distinct appearance and shape characteristics, occlusion and variation in leaf shape and pose, as well as imaging conditions, make this problem challenging.

[0003] Since the 1980s, many effective methods have been proposed to deal with the leaf segmentation problem, but the existing leaf segmentation methods cannot adapt to complex backgrounds, and the post-processing methods are cumbersome, but there is still a lot of room for improvement in terms of accuracy , and there is still a certain gap from the real practical application

Images