欢迎您访问《智慧农业(中英文)》官方网站! English

Smart Agriculture ›› 2024, Vol. 6 ›› Issue (5): 88-97.doi: 10.12133/j.smartag.SA202404011

• 技术方法 • 上一篇    下一篇

基于无人机图像和改进LSC-CNN模型的密集苗木检测和计数方法

彭小丹1,3, 陈锋军1,2,3,4(), 朱学岩1,4, 才嘉伟1,3, 顾梦梦5   

  1. 1. 北京林业大学 工学院,北京 100083,中国
    2. 林木资源高效生产全国重点实验室,北京 100083,中国
    3. 城乡生态环境北京实验室,北京 100083,中国
    4. 林业装备与自动化国家林业和草原局重点实验室,北京 100083,中国
    5. 科罗拉多州立大学 园艺与景观建筑系,柯林斯堡 80523,美国
  • 收稿日期:2024-04-18 出版日期:2024-09-30
  • 基金项目:
    国家重点研发计划项目(2019YFD1002401); 北京林业大学科技创新计划项目(2021ZY74); 北京市共建项目专项
  • 作者简介:
    彭小丹,研究方向为林业信息检测。Email:
  • 通信作者:
    陈锋军,博士,教授,研究方向为林业信息检测与智能处理。Email:

Dense Nursery Stock Detecting and Counting Based on UAV Aerial Images and Improved LSC-CNN

PENG Xiaodan1,3, CHEN Fengjun1,2,3,4(), ZHU Xueyan1,4, CAI Jiawei1,3, GU Mengmeng5   

  1. 1. School of Technology, Beijing Forestry University, Beijing 100083, China
    2. National Key Laboratory of Efficient Production of Forest Resources, Beijing 100083, China
    3. Beijing Laboratory of Urban and Rural Ecological Environment, Beijing Municipal Education Commission, Beijing 100083, China
    4. Key Laboratory of State Forestry Administration for Forestry Equipment and Automation, Beijing 100083, China
    5. Architecture of Horticultural and Landscape, Colorado State University, Fort Collins CO 80523, USA
  • Received:2024-04-18 Online:2024-09-30
  • Foundation items:National Key Research and Development Program(2019YFD1002401); Beijing Forestry University Science and Technology Innovation Program Project(2021ZY74); Beijing Common Construction Project
  • About author:
    PENG Xiaodan, E-mail:
  • Corresponding author:
    CHEN Fengjun, E-mail:

摘要:

【目的/意义】 快速、准确地统计密集种植的苗木数量对苗木经营管理具有重要意义。为解决无人机航拍的密集种植苗木图像中苗木粘连、尺度差异大的问题,提出以点标签数据为监督信号的改进密集检测计数模型(Locate, Size and Count, LSC-CNN),同时实现苗木的检测和计数。 【方法】 改进的LSC-CNN模型通过将LSC-CNN模型特征提取网络的最后一层卷积替换为扩张卷积(Dilated Convolutions, DConv),实现在保留苗木细节特征的同时扩大感受野,帮助模型更好地理解上下文信息以区分粘连苗木。此外,在多个尺度分支前引入注意力机制(Convolutional Block Attention Module, CBAM)使模型聚焦于有助于苗木检测和计数的关键特征,以更好地适应不同尺度的苗木。为解决类别不平衡问题,提高模型的泛化能力,将损失函数替换为标签平滑交叉熵损失函数。 【结果和讨论】 经测试,改进LSC-CNN模型在456幅苗木图像的测试集上的平均绝对误差(Mean Absolute Error, MAE)、均方根误差(Root Mean Square Error, RMSE)和平均计数准确率(Mean Counting Accurate, MCA)分别为14.24株、22.22株和91.23%,三项指标均优于IntegrateNet、PSGCNet、CANet、CSRNet、CLTR和LSC-CNN模型。 【结论】 改进LSC-CNN模型能够准确实现密集种植苗木的检测和计数,适用于多种树木的检测和计数工作。

关键词: 无人机, 密集种植, 计数, 多尺度, LSC-CNN

Abstract:

[Objective] The number, location, and crown spread of nursery stock are important foundations data for their scientific management. Traditional approach of conducting nursery stock inventories through on-site individual plant surveys is labor-intensive and time-consuming. Low-cost and convenient unmanned aerial vehicles (UAVs) for on-site collection of nursery stock data are beginning to be utilized, and the statistical analysis of nursery stock information through technical means such as image processing achieved. During the data collection process, as the flight altitude of the UAV increases, the number of trees in a single image also increases. Although the anchor box can cover more information about the trees, the cost of annotation is enormous in the case of a large number of densely populated tree images. To tackle the challenges of tree adhesion and scale variance in images captured by UAVs over nursery stock, and to reduce the annotation costs, using point-labeled data as supervisory signals, an improved dense detection and counting model was proposed to accurately obtain the location, size, and quantity of the targets. [Method] To enhance the diversity of nursery stock samples, the spruce dataset, the Yosemite, and the KCL-London publicly available tree datasets were selected to construct a dense nursery stock dataset. A total of 1 520 nursery stock images were acquired and divided into training and testing sets at a ratio of 7:3. To enhance the model's adaptability to tree data of different scales and variations in lighting, data augmentation methods such as adjusting the contrast and resizing the images were applied to the images in the training set. After enhancement, the training set consists of 3 192 images, and the testing set contains 456 images. Considering the large number of trees contained in each image, to reduce the cost of annotation, the method of selecting the center point of the trees was used for labeling. The LSC-CNN model was selected as the base model. This model can detect the quantity, location, and size of trees through point-supervised training, thereby obtaining more information about the trees. The LSC-CNN model was made improved to address issues of missed detections and false positives that occurred during the testing process. Firstly, to address the issue of missed detections caused by severe adhesion of densely packed trees, the last convolutional layer of the feature extraction network was replaced with dilated convolution. This change enlarges the receptive field of the convolutional kernel on the input while preserving the detailed features of the trees. So the model is better able to capture a broader range of contextual information, thereby enhancing the model's understanding of the overall scene. Secondly, the convolutional block attention module (CBAM) attention mechanism was introduced at the beginning of each scale branch. This allowed the model to focus on the key features of trees at different scales and spatial locations, thereby improving the model's sensitivity to multi-scale information. Finally, the model was trained using label smooth cross-entropy loss function and grid winner-takes-all strategy, emphasizing regions with highest losses to boost tree feature recognition. [Results and Discussions] The mean counting accuracy (MCA), mean absolute error (MAE), and root mean square error (RMSE) were adopted as evaluation metrics. Ablation studies and comparative experiments were designed to demonstrate the performance of the improved LSC-CNN model. The ablation experiment proved that the improved LSC-CNN model could effectively resolve the issues of missed detections and false positives in the LSC-CNN model, which were caused by the density and large-scale variations present in the nursery stock dataset. IntegrateNet, PSGCNet, CANet, CSRNet, CLTR and LSC-CNN models were chosen as comparative models. The improved LSC-CNN model achieved MCA, MAE, and RMSE of 91.23%, 14.24, and 22.22, respectively, got an increase in MCA by 6.67%, 2.33%, 6.81%, 5.31%, 2.09% and 2.34%, respectively; a reduction in MAE by 21.19, 11.54, 18.92, 13.28, 11.30 and 10.26, respectively; and a decrease in RMSE by 28.22, 28.63, 26.63, 14.18, 24.38 and 12.15, respectively, compared to the IntegrateNet, PSGCNet, CANet, CSRNet, CLTR and LSC-CNN models. These results indicate that the improved LSC-CNN model achieves high counting accuracy and exhibits strong generalization ability. [Conclusions] The improved LSC-CNN model integrated the advantages of point supervision learning from density estimation methods and the generation of target bounding boxes from detection methods.These improvements demonstrate the enhanced performance of the improved LSC-CNN model in terms of accuracy, precision, and reliability in detecting and counting trees. This study could hold practical reference value for the statistical work of other types of nursery stock.

Key words: UAV, intensive planting, counting, multi-scale, LSC-CNN

中图分类号: