A method on airborne remote sensing tillage direction mapping based on improved probabilistic Hough transform

IF 6.1 1区农林科学 Q1 SOIL SCIENCE

Soil & Tillage Research Pub Date : 2025-04-30 DOI:10.1016/j.still.2025.106621

Xinle Zhang , Baicheng Du , Xiangtian Meng , Yihan Ma , Xinyi Han , Huanjun Liu

{"title":"A method on airborne remote sensing tillage direction mapping based on improved probabilistic Hough transform","authors":"Xinle Zhang , Baicheng Du , Xiangtian Meng , Yihan Ma , Xinyi Han , Huanjun Liu","doi":"10.1016/j.still.2025.106621","DOIUrl":null,"url":null,"abstract":"<div><div>The tillage direction is a key aspect of crop planting layout in agricultural croplands. Identifying tillage direction aids agricultural production management by increasing crop yields, simplifying machine operation, and preventing soil erosion. Most current studies utilize unmanned aerial vehicle (UAV) imagery to extract positional information of planting rows in individual croplands. However, these studies have limited extraction areas and cannot obtain specific tillage direction information for each cropland on a large regional scale. Our study utilized 0.2 m resolution remote sensing images and vector data from the Hongxinglong reclamation area, acquired during the 2023 aerial experiment. We improved the probabilistic Hough transform to enable dynamic parameter adjustment for detecting straight lines and calculating their quantities. Used it as an algorithm to develop a tillage direction mapping model and complete the mapping of 1108 croplands in the reclamation area. The study results indicate that: (1) The model accurately generates maps of cropland tillage directions at a large regional scale. Under optimal parameters, the model achieves a mapping accuracy of 0.845 and a Kappa coefficient of 0.806. (2) Compared to the mapping results prior to algorithm improvement, the improved probabilistic Hough transform algorithm increases mapping accuracy by 0.136 and the Kappa coefficient by 0.156, confirming the effectiveness of the improvements. (3) The generalization capability experiment demonstrates that the model exhibits strong generalization under various remote sensing data, tillage types, climate zone crop types, cropland sizes and different seasons. Overall, this study addresses gaps in current research methodologies for tillage direction maps at large regional scales and offers valuable insights for related fields. The results of the tillage direction map benefit agricultural production management and research.</div></div>","PeriodicalId":49503,"journal":{"name":"Soil & Tillage Research","volume":"252 ","pages":"Article 106621"},"PeriodicalIF":6.1000,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Soil & Tillage Research","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167198725001758","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SOIL SCIENCE","Score":null,"Total":0}

引用次数: 0

Abstract

The tillage direction is a key aspect of crop planting layout in agricultural croplands. Identifying tillage direction aids agricultural production management by increasing crop yields, simplifying machine operation, and preventing soil erosion. Most current studies utilize unmanned aerial vehicle (UAV) imagery to extract positional information of planting rows in individual croplands. However, these studies have limited extraction areas and cannot obtain specific tillage direction information for each cropland on a large regional scale. Our study utilized 0.2 m resolution remote sensing images and vector data from the Hongxinglong reclamation area, acquired during the 2023 aerial experiment. We improved the probabilistic Hough transform to enable dynamic parameter adjustment for detecting straight lines and calculating their quantities. Used it as an algorithm to develop a tillage direction mapping model and complete the mapping of 1108 croplands in the reclamation area. The study results indicate that: (1) The model accurately generates maps of cropland tillage directions at a large regional scale. Under optimal parameters, the model achieves a mapping accuracy of 0.845 and a Kappa coefficient of 0.806. (2) Compared to the mapping results prior to algorithm improvement, the improved probabilistic Hough transform algorithm increases mapping accuracy by 0.136 and the Kappa coefficient by 0.156, confirming the effectiveness of the improvements. (3) The generalization capability experiment demonstrates that the model exhibits strong generalization under various remote sensing data, tillage types, climate zone crop types, cropland sizes and different seasons. Overall, this study addresses gaps in current research methodologies for tillage direction maps at large regional scales and offers valuable insights for related fields. The results of the tillage direction map benefit agricultural production management and research.

查看原文本刊更多论文

基于改进概率霍夫变换的航空遥感耕作方向制图方法

耕作方向是农田作物种植布局的一个关键方面。确定耕作方向有助于农业生产管理，提高作物产量，简化机器操作，防止土壤侵蚀。目前的研究大多是利用无人机（UAV）图像来提取单个农田的种植行位置信息。然而，这些研究的提取面积有限，无法在大区域尺度上获得每个农田的具体耕作方向信息。本研究利用2023年航空试验获得的红星龙垦区0.2 m分辨率遥感影像和矢量数据。改进了概率霍夫变换，实现了直线检测和直线数量计算的动态参数调整。将其作为算法开发耕作方向制图模型，完成了垦区1108块农田的制图。研究结果表明：(1)该模型能准确生成大区域尺度的耕地耕作方向图。在最优参数下，模型的映射精度为0.845，Kappa系数为0.806。(2)与算法改进前的映射结果相比，改进后的概率霍夫变换算法映射精度提高了0.136，Kappa系数提高了0.156，证实了改进的有效性。(3)综合能力试验表明，该模型对不同遥感数据、不同耕作方式、不同气候带作物类型、不同耕地面积、不同季节均具有较强的综合能力。总的来说，本研究弥补了目前大区域尺度耕作方向图研究方法的不足，为相关领域提供了有价值的见解。耕作方向图的成果有利于农业生产管理和研究。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Soil & Tillage Research 农林科学-土壤科学

CiteScore

13.00

自引率

6.20%

发文量

266

审稿时长

5 months

期刊介绍： Soil & Tillage Research examines the physical, chemical and biological changes in the soil caused by tillage and field traffic. Manuscripts will be considered on aspects of soil science, physics, technology, mechanization and applied engineering for a sustainable balance among productivity, environmental quality and profitability. The following are examples of suitable topics within the scope of the journal of Soil and Tillage Research: The agricultural and biosystems engineering associated with tillage (including no-tillage, reduced-tillage and direct drilling), irrigation and drainage, crops and crop rotations, fertilization, rehabilitation of mine spoils and processes used to modify soils. Soil change effects on establishment and yield of crops, growth of plants and roots, structure and erosion of soil, cycling of carbon and nutrients, greenhouse gas emissions, leaching, runoff and other processes that affect environmental quality. Characterization or modeling of tillage and field traffic responses, soil, climate, or topographic effects, soil deformation processes, tillage tools, traction devices, energy requirements, economics, surface and subsurface water quality effects, tillage effects on weed, pest and disease control, and their interactions.