Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images
With the development of unmanned aerial vehicle (UAV), obtaining high-resolution aerial images has become easier. Identifying and locating specific crops from aerial images is a valuable task. The location and quantity of crops are important for agricultural insurance businesses. In this paper, the...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Agriculture |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0472/12/1/26 |
_version_ | 1797496872445673472 |
---|---|
author | Di Zhang Feng Pan Qi Diao Xiaoxue Feng Weixing Li Jiacheng Wang |
author_facet | Di Zhang Feng Pan Qi Diao Xiaoxue Feng Weixing Li Jiacheng Wang |
author_sort | Di Zhang |
collection | DOAJ |
description | With the development of unmanned aerial vehicle (UAV), obtaining high-resolution aerial images has become easier. Identifying and locating specific crops from aerial images is a valuable task. The location and quantity of crops are important for agricultural insurance businesses. In this paper, the problem of locating chili seedling crops in large-field UAV images is processed. Two problems are encountered in the location process: a small number of samples and objects in UAV images are similar on a small scale, which increases the location difficulty. A detection framework based on a prototypical network to detect crops in UAV aerial images is proposed. In particular, a method of subcategory slicing is applied to solve the problem, in which objects in aerial images have similarities at a smaller scale. The detection framework is divided into two parts: training and detection. In the training process, crop images are sliced into subcategories, and then these subcategory patch images and background category images are used to train the prototype network. In the detection process, a simple linear iterative clustering superpixel segmentation method is used to generate candidate regions in the UAV image. The location method uses a prototypical network to recognize nine patch images extracted simultaneously. To train and evaluate the proposed method, we construct an evaluation dataset by collecting the images of chilies in a seedling stage by an UAV. We achieve a location accuracy of 96.46%. This study proposes a seedling crop detection framework based on few-shot learning that does not require the use of labeled boxes. It reduces the workload of manual annotation and meets the location needs of seedling crops. |
first_indexed | 2024-03-10T03:09:42Z |
format | Article |
id | doaj.art-a0400f3325c942b894b4b1d3a3411e4e |
institution | Directory Open Access Journal |
issn | 2077-0472 |
language | English |
last_indexed | 2024-03-10T03:09:42Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Agriculture |
spelling | doaj.art-a0400f3325c942b894b4b1d3a3411e4e2023-11-23T12:35:00ZengMDPI AGAgriculture2077-04722021-12-011212610.3390/agriculture12010026Seeding Crop Detection Framework Using Prototypical Network Method in UAV ImagesDi Zhang0Feng Pan1Qi Diao2Xiaoxue Feng3Weixing Li4Jiacheng Wang5School of Automation, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Automation, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Automation, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Automation, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Automation, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Automation, Beijing Institute of Technology, Beijing 100081, ChinaWith the development of unmanned aerial vehicle (UAV), obtaining high-resolution aerial images has become easier. Identifying and locating specific crops from aerial images is a valuable task. The location and quantity of crops are important for agricultural insurance businesses. In this paper, the problem of locating chili seedling crops in large-field UAV images is processed. Two problems are encountered in the location process: a small number of samples and objects in UAV images are similar on a small scale, which increases the location difficulty. A detection framework based on a prototypical network to detect crops in UAV aerial images is proposed. In particular, a method of subcategory slicing is applied to solve the problem, in which objects in aerial images have similarities at a smaller scale. The detection framework is divided into two parts: training and detection. In the training process, crop images are sliced into subcategories, and then these subcategory patch images and background category images are used to train the prototype network. In the detection process, a simple linear iterative clustering superpixel segmentation method is used to generate candidate regions in the UAV image. The location method uses a prototypical network to recognize nine patch images extracted simultaneously. To train and evaluate the proposed method, we construct an evaluation dataset by collecting the images of chilies in a seedling stage by an UAV. We achieve a location accuracy of 96.46%. This study proposes a seedling crop detection framework based on few-shot learning that does not require the use of labeled boxes. It reduces the workload of manual annotation and meets the location needs of seedling crops.https://www.mdpi.com/2077-0472/12/1/26chili detectionprototypical networksmall-scale similarity problemunmanned aerial vehicle images |
spellingShingle | Di Zhang Feng Pan Qi Diao Xiaoxue Feng Weixing Li Jiacheng Wang Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images Agriculture chili detection prototypical network small-scale similarity problem unmanned aerial vehicle images |
title | Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images |
title_full | Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images |
title_fullStr | Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images |
title_full_unstemmed | Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images |
title_short | Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images |
title_sort | seeding crop detection framework using prototypical network method in uav images |
topic | chili detection prototypical network small-scale similarity problem unmanned aerial vehicle images |
url | https://www.mdpi.com/2077-0472/12/1/26 |
work_keys_str_mv | AT dizhang seedingcropdetectionframeworkusingprototypicalnetworkmethodinuavimages AT fengpan seedingcropdetectionframeworkusingprototypicalnetworkmethodinuavimages AT qidiao seedingcropdetectionframeworkusingprototypicalnetworkmethodinuavimages AT xiaoxuefeng seedingcropdetectionframeworkusingprototypicalnetworkmethodinuavimages AT weixingli seedingcropdetectionframeworkusingprototypicalnetworkmethodinuavimages AT jiachengwang seedingcropdetectionframeworkusingprototypicalnetworkmethodinuavimages |