基于无人机图像和贝叶斯CSRNet模型的粘连云杉计数  

Adhesion spruce counting based on UAV images and Bayesian CSRNet model

作　　者：朱学岩 张新伟 才嘉伟 郑一力[1,2,3,4] 顾梦梦 陈锋军 Zhu Xueyan;Zhang Xinwei;Cai Jiawei;Zheng Yili;Gu Mengmeng;Chen Fengjun(School of Technology,Beijing Forestry University,Beijing 100083,China;Beijing Laboratory of Urban and Rural Ecological Environment,Beijing 100083,China;Key Laboratory of State Forestry Administration for Forestry Equipment and Automation,Beijing,100083,China;Research Center for Intelligent Forestry,Beijing 100083,China;Department of Horticultural Science,Texas A&M University,College Station TX 77843,USA)

机构地区：[1]北京林业大学工学院,北京100083 [2]城乡生态环境北京实验室,北京100083 [3]国家林业局林业装备与自动化国家重点实验室,北京100083 [4]智慧林业研究中心,北京100083 [5]德州农工大学园艺系,卡城77843

出　　处：《农业工程学报》2022年第14期43-50,F0003,共9页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家重点研发计划项目(2019YFD1002401);中央高校基本科研业务费专项资金(2021ZY74);北京市共建项目联合资助。

摘　　要：自动、准确且快速地统计苗木数量是实现苗圃高效管理的重要基础。针对现有苗木计数方法准确率较低且无法准确统计粘连苗木等问题,该研究提出了一种基于贝叶斯CSRNet模型的云杉计数模型。该模型以对粘连苗木具有良好稳定性的CSRNet模型为基础,引入贝叶斯损失函数,以人工标注的点标签数据作为监督信号。以1176幅云杉图像训练贝叶斯CSRNet模型,并通过166幅测试集云杉图像进行测试。结果表明,贝叶斯CSRNet模型可以准确、快速地统计无人机航拍图像内的云杉,对测试集图像内云杉的平均计数准确率(Mean Counting Accuracy,MCA)、平均绝对误差(Mean Absolute Error,MAE)和均方误差(Mean Square Error,MSE)分别为99.19%、1.42和2.80。单幅云杉图像耗时仅为248 ms,模型大小为62 Mb。对比YOLOv3模型、改进YOLOv3模型、CSRNet模型和贝叶斯CSRNet模型对166幅测试集云杉图像的计数结果,贝叶斯CSRNet模型的MCA分别比YOLOv3模型、改进YOLOv3模型、CSRNet模型高3.43%、1.44%和1.13%;MAE分别低6.8、2.9和1.67;MSE分别低101.74、23.48和8.57。在MCT(Mean Counting Time)和MS(Model Sizel)两项指标上,贝叶斯CSRNet模型与CSRNet模型相同且优于YOLOv3模型和改进YOLOv3模型。贝叶斯CSRNet模型可实现无人机航拍图像内苗木数量的自动、准确、快速统计,为苗木库存智能盘点提供参考。An accurate and rapid counting of the seedlings is of great significance to evaluate the yield and quality in the nursery for the decision making on reasonable production plans. The traditional way is the manual operation to count the seedlings one by one by workers. It is time-consuming and labor-intensive, particularly with the slow data update. It is a high demand for the new counting of the seedlings to meet the actual needs. Taking spruce as the research object, this study aims to develop automatic, accurate, and fast counting, where the images were captured by the unmanned aerial vehicle(UAV) as the experimental data. At first, some attempts were made to count the seedlings using density map regression with deep learning,especially for the higher accuracy of the adhesion forest seedlings. Specifically, the density map regression(CSRNet) was selected as the base model, due to the excellent robustness of the seedling adhesion. In the CSRNet model, the coarse ground-truth density map was normally generated by the point annotations using a Gaussian kernel as the supervised signal training, leading to low counting accuracy. A Bayesian CSRNet model was designed to directly use the manually annotated point label data as the supervised signal, where the Bayesian loss function was also introduced to improve the counting accuracy of the CSRNet model. Then, the 558 acquired spruce images were divided into the training set(392 images) and test set(166 images). The brightness was also adjusted to add the random noise, in order to process 392 spruce images from the training set. Among them, the brightness adjustment mainly simulated the spruce images under different light intensities,whereas, the addition of random noise was the spruce images under different environmental noises. After data processing, the 392 spruce images in the training set were expanded to 1 176 images. After that, the Bayesian CSRNet model was trained on the 1 176 spruce images and tested on the 166 test set. The results showed that the Bayesian CSR

关 键 词：无人机 模型 苗木计数 贝叶斯CSRNet CSRNet 粘连苗木 云杉 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]