基于卷积神经网络提取多尺度分层特征识别玉米杂草  

Recognition of maize and weed based on multi-scale hierarchical features extracted by convolutional neural network

作　　者：王璨[1] 武新慧[1] 李志伟[1] 

机构地区：[1]山西农业大学工学院,太谷030801

出　　处：《农业工程学报》2018年第5期144-151,共8页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家重点研发计划(2017YFD0701501)

摘　　要：为提高作物与杂草识别的准确率、稳定性和实时性,该文以幼苗期玉米及杂草为研究对象,提出了基于卷积神经网络提取多尺度分层特征的玉米杂草识别方法。首先建立卷积神经网络模型,以从图像的高斯金字塔中提取多尺度分层特征作为识别依据,再与多层感知器相连接实现图像中各像素的识别;为了避免目标交叠所带来的问题,对图像进行超像素分割,通过计算每个超像素内部的平均像素类别分布确定该超像素块的类别,再将相同类别的相邻超像素合并,最终实现图像中各目标的识别。试验结果表明:该方法的平均目标识别准确率达98.92%,标准差为0.55%,识别单幅图像的平均耗时为1.68 s,采用GPU硬件加速后识别单幅图像的平均耗时缩短为0.72 s。该方法实现了精确、稳定和高效的玉米与杂草识别,研究可为精确除草的发展提供参考。Effective recognition method of crop and weed is the basis for promoting the development of intelligent mechanization weeding pattern. Summarizing the previous research, we found that the accuracy and stability of the recognition model could be improved by natural and diversified feature presentation, but there are still 2 main problems. On the one hand, feature presentation of the natural property of target was difficult to be obtained by the hand-engineered feature extractor. The spatial consistency of the obtained features was bad, and the real-time performance of recognition system was reduced for the complex feature extraction algorithm. On the other hand, the effect of image preprocessing has important influence on recognition results, especially the overlapping segmentation of crop and weed. For overlapped objects, it is usually difficult to segment them without affecting their respective feature presentations, resulting in low recognition accuracy and stability. In order to solve the main problems in the current research, we explored the way to improve the recognition accuracy, stability and real-time performance, and a recognition method of crop and weed based on multiscale hierarchical feature learning combined with superpixels segmentation was proposed. The main research contents of this paper were as follows: 1) Excellent internal features of image are hierarchical. In this research, the multiscale hierarchical feature is a scene level feature with invariance and consistency in scale space. Multiscale convolutional neural network was built to extract multiscale hierarchical feature. Multiscale convolutional neural network contains multiple copies of a single CNN(convolutional neural network) that are applied to multi-scale Gaussian pyramid of the input image. The CNN model as feature extractor in this paper includes 3 stages. In the first 2 stages, it contains a bank of filters(convolution kernels) to produce dense feature maps, a point to point nonlinear mapping activation function, and a spatial poo

关 键 词：作物 图像识别 图像分割 杂草识别 深度学习 卷积神经网络 超像素 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]