PODD: A Dual-Task Detection for Greenhouse Extraction Based on Deep Learning

被引:9
作者
Feng, Junning [1 ]
Wang, Dongliang [2 ]
Yang, Fan [1 ]
Huang, Jing [1 ]
Wang, Minghao [1 ]
Tao, Mengfan [1 ]
Chen, Wei [1 ]
机构
[1] China Univ Min & Technol Beijing, Coll Geosci & Surveying Engn, Beijing 100083, Peoples R China
[2] Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Land Surface Pattern & Simulat, Beijing 100101, Peoples R China
基金
国家重点研发计划; 美国国家科学基金会;
关键词
greenhouse; area extraction; quantity estimation; target detection; semantic segmentation; OBJECT-BASED CLASSIFICATION; PLASTIC GREENHOUSE; FRAMEWORK; IMAGERY; AREA;
D O I
10.3390/rs14195064
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The rapid boom of the global population is causing more severe food supply problems. To deal with these problems, the agricultural greenhouse is an effective way to increase agricultural production within a limited space. To better guide agricultural activities and respond to future food crises, it is important to obtain both the agricultural greenhouse area and quantity distribution. In this study, a novel dual-task algorithm called Pixel-based and Object-based Dual-task Detection (PODD) that combines object detection and semantic segmentation is proposed to estimate the quantity and extract the area of agricultural greenhouses based on RGB remote sensing images. This algorithm obtains the quantity of agricultural greenhouses based on the improved You Only Look Once X (YOLOX) network structure, which is embedded with Convolutional Block Attention Module (CBAM) and Adaptive Spatial Feature Fusion (ASFF). The introduction of CBAM can make up for the lack of expression ability of its feature extraction layer to retain more important feature information. Adding the ASFF module can make full use of the features in different scales to increase the precision. This algorithm obtains the area of agricultural greenhouses based on the DeeplabV3+ neural network using ResNet-101 as a feature extraction network, which not only effectively reduces hole and plaque issues but also extracts edge details. Experimental results show that the mAP and F1-score of the improved YOLOX network reach 97.65% and 97.50%, 1.50% and 2.59% higher than the original YOLOX solution. At the same time, the accuracy and mIoU of the DeeplabV3+ network reach 99.2% and 95.8%, 0.5% and 2.5% higher than the UNet solution. All of the metrics in the dual-task algorithm reach 95% and even higher. Proving that the PODD algorithm could be useful for agricultural greenhouse automatic extraction (both quantity and area) in large areas to guide agricultural policymaking.
引用
收藏
页数:21
相关论文
共 50 条
[31]   Automatic Detection of Dental Lesions Based on Deep Learning [J].
Liu Feng ;
Han Min ;
Wang Jun ;
Liu Chao .
CHINESE JOURNAL OF LASERS-ZHONGGUO JIGUANG, 2022, 49 (20)
[32]   A review of lane detection methods based on deep learning [J].
Tang, Jigang ;
Li, Songbin ;
Liu, Peng .
PATTERN RECOGNITION, 2021, 111
[33]   Deep Learning and Spatial Analysis Based Port Detection [J].
Li Zeming ;
Cheng Liang ;
Zhu Daming ;
Yan Zhaojin ;
Ji Chen ;
Duan Zhixin ;
Jing Min ;
Li Ning ;
Dongye Shengkun ;
Song Yanruo ;
Liu Jiahui .
LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (20)
[34]   A Comprehensive Overview of Object Detection Based on Deep Learning [J].
Yuan, Gaoling ;
Chen, Linshu ;
Cai, Jiahong ;
Yang, Chaoyi ;
Liu, Jinnian .
PROCEEDINGS OF THE 2024 IEEE 10TH INTERNATIONAL CONFERENCE ON INTELLIGENT DATA AND SECURITY, IDS 2024, 2024, :80-85
[35]   Deep learning-based wall crack detection [J].
Zheng, Zujia ;
Yang, Kui .
International Journal of Wireless and Mobile Computing, 2024, 27 (02) :118-124
[36]   Deep Reinforcement Learning Based Automatic Control in Semi-Closed Greenhouse Systems [J].
Ajagekar, Akshay ;
You, Fengqi .
IFAC PAPERSONLINE, 2022, 55 (07) :406-411
[37]   Adaptive Road Extraction Method in Different Scene Based on Deep Learning [J].
Ding Z.-L. ;
Hu Y.-H. ;
Gong J.-W. ;
Xiong G.-M. ;
Lü C. .
Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 2019, 39 (11) :1133-1137
[38]   Deep learning based object detection from multi-modal sensors: an overview [J].
Liu, Ye ;
Meng, Shiyang ;
Wang, Hongzhang ;
Liu, Jun .
MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (07) :19841-19870
[39]   Abandoned terrace recognition based on deep learning and change detection on the Loess Plateau in China [J].
Guo, Huili ;
Sun, Liquan ;
Yao, Ailing ;
Chen, Ziyu ;
Feng, Hao ;
Wu, Shufang ;
Siddique, Kadambot H. M. .
LAND DEGRADATION & DEVELOPMENT, 2023, 34 (08) :2349-2365
[40]   Deep Learning-Based Object Detection Techniques for Remote Sensing Images: A Survey [J].
Li, Zheng ;
Wang, Yongcheng ;
Zhang, Ning ;
Zhang, Yuxi ;
Zhao, Zhikang ;
Xu, Dongdong ;
Ben, Guangli ;
Gao, Yunxiao .
REMOTE SENSING, 2022, 14 (10)