针对当前梯田提取算法在复杂地形区域效果差异大的问题,提出一种改进AdaBoost的梯田提取方法.对高分辨率梯田影像、DEM数据及相关地形因子进行融合与分割,构建不同地形特征的样本数据集;进行特征选择和样本均衡化;采用改进AdaBoost算法对三块地形差异较大的复杂区域进行提取.结果表明,该方法在复杂梯田区域上提取的平均总精度和Kappa系数分别为 93.13%和 0.83,均高于其他算法的提取效果.该算法能够对无人机遥感影像的地物提取提供支持.

新冠肺炎疫情防控期间,多数学生无法正常返校学习,为了保证"停课不停学",高校师生共同经历了在线课堂、在线学习、在线作业等线上学习历程.随着信息技术的发展,线上教学越来越普遍,为了确保课程教学质量,有效评价学生学习效果,在线考核将成为新的趋势.线上考核可以弥补线下考核的不足,成为在线教学的有效辅助手段.为深入推进课程考核方式改革,确保在线考核科学有效,文章从在线考核的设计思路与方式、设计原则、在线考核的保障措施、理论课程和实验实习课程在线考核的设计与实施、在线考核取得的成效以及改进建议等方面介绍了课程在线考核的实施.实践结果表明,在线考核使考核结果更加合理化,学生学习的主动性和积极性得到了极大的提升,教师利用现代化网络技术进行教学的水平和能力进一步增强,创造性得到了充分发挥,教学效果明显提升.

Rill erosion is one of the main forms of soil erosion on hillslopes in hilly and gully regions of the Loess Plateau. For simplicity, many studies assume hillslopes with a uniform sloping profile. However, the most loess hillslopes are convex shape with variable degrees in this area. Estimating soil losses and planning soil conservation practices on such slopes have required much local judgment. The objective of this study was to clarify soil erosion evolution qualitatively and quantitatively on a convex slope based on a three-dimensional (3D) reconstruction technique and geographic information system (GIS) in simulated rainfall experiments. The results showed that: (1) The erosion processes of the convex slope could be reasonably described with the following stages: splash and sheet erosion - drop pits - head-cut erosion - intermittent rill - continuous rill - rill network development transition from rill to ephemeral gully. (2) Soil loss rate from the convex slope varied from 0.127 Kg m(-2) min(-1) in the sheet erosion stage to 0.342 Kg m(-2) min(-1) in rill network development stage, which was much greater compared with the results of uniform slope erosion reported by others in this area. Once rill erosion evolved into the dominant erosion pattern (after 30 mm of rainfall), rill length, width, and depth enlarged noticeably with headward and lateral erosion. (3) The contribution of sediment from rill and inter-rill erosion to total erosion was accurately depicted, and rill erosion contributed up to 60% of the total sediment amount. (4) Soil erosion rate was significantly correlated with rill morphological parameters-fractal dimension, rill density, and degree of rill dissection (correlation coefficients of 0.978, 0.989, and 0.980, respectively). These results are helpful for the qualitative and quantitative understanding of the erosion processes of hillslopes in Chinese Loess Plateau, and have an important reference for the rational arrangement of erosion control measures.

针对大区域高分辨率数字高程模型(DEM)数据较难获取、超分辨率重构(降尺度)较低分辨率的DEM精度不高、难以满足实际需要的问题,提出一种对起伏特征较明显的山区DEM超分辨率重构的方法.利用较深层的神经网络充分学习高低分辨率DEM之间的非线性映射关系;为了降低训练难度,结合残差学习的方法进行数据训练.将双立方插值法、稀疏混合估计法重构的DEM及提取的坡度结果分别同深层残差网络法的结果进行对比,结果表明,3种方法DEM结果的差值平均值分别为0.41、0.34、0.34 m,RMSE分别为0.594 5、0.5715、0.4869 m;坡度结果的差值平均值分别为3.02°、2.04°、1.99°,RMSE分别为3.649 8°、3.136 0°、2.738 7°;处理时间分别为0.052、663.39、2.16 so研究表明,对于10、20、40m的DEM,本文方法在空间分布和误差方面优于其他方法,在耗时效率上也优于稀疏混合估计法,适合应用于梯田等地形复杂的区域进行超分辨率重构.

梯田是坡耕地上最主要的水土保持工程,准确地提取梯田信息对水土保持监测和评价十分重要.为了解决无人机遥感梯田识别研究中梯田特征自动学习的问题,制作了一套像素级标注的梯田正射影像样本集并设计FCN-8s模型与DenseCRF模型结合的梯田识别方法.实验结果表明,该方法在山脊区梯田、密集水平梯田和不规则梯田识别的总体精度、F1分数和Kappa系数均值分别为86.85％、87.28％、80.41％,与其他方法相比,效果较好.该方法适用于无人机遥感梯田识别领域,是一种精确有效的识别方法.

随着MOOC、SPOC等线上线下混合教学的发展,我国高校的在线教学水平得到提高.但是,由于线上教学平台的功能、教师信息化能力、学生适应性等均存在差异,所以目前的在线教学还面临着教学缺乏临场感、师生缺乏互动、线上教学考核机制不完善以及学生的注意力容易分散、无法通过集体学习相互交流促进、学习缺乏监督等急待解决的问题.为了解决在线教学面临的困难,提高在线教学效果,以"土木工程测量"课程为例,开展了线上教学的改革探索.一是认真进行学情分析,积极重构线上课程教学体系,结构串讲注重精讲适当留白,调动学生学习的内在动机;充分利用线上教学平台,指导学生完成练习任务;组织在线合作学习和讨论,引导学生深入学习;开展直播答疑和总结,提升学生线上学习质量.二是根据线上教学特点,通过设计线上课程教学6个环节的脚本和3个阶段的教学方案、以五星教学法组织线上课程教学的方案、线上课程教学中教师所承担的3种角色、线上课程教学平台5种信息化教学工具的使用等,优化和完善课程教学设计方案.三是以直播教学资源建设为重点,通过签到、提问、投票、小测验等在线教学平台提供的小工具强化对学生学习过程的调控和管理,使教学内容不仅具有完整性、丰富性和系统性等特点,而且适合线上教学平台传播、符合学生线上自主学习认知规律特点.四是遵循"以评促学"主导思想,设计全方位覆盖"课前、课中、课后"的"过程性考核评价体系",为线上课程教学质量提供保障.

新型冠状病毒疫情防控关键时期,按照教育部要求,学校基于自身在线学习资源、平台,将其作为检验课程资源建设、教师在线教学能力的机会.为了保证在线教学质量,需要教务部门做好课程筛选,加强监督评估;需要教学发展中心对在线教学工具平台提供技术支持;需要师生转变教与学理念;需要教师构建在线教学评价机制;需要相关部门及时调研在线教学实施过程中存在问题,并提出合理化建议.同时,提醒教师平时注重储备优质视频资源,做好预案,以防突发事件.

翻转课堂混合教学模式是一种通过改变、逆转教学结构的方式以提高教学效率与教学质量的创新教学模式,这种教学模式可以促进学生能力的全面发展.在测量学课程教学实践与教学改革过程中逐步建立了操作性强的混合教学对策;并通过挖掘对策的理论依据形成翻转课堂符合实际的混合教学设计模式的10个关键步骤;运用四步结构法组织测量课程的教学;建立与混合教学模式相匹配的评价体系.以期形成的教学对策、教学设计模式、四步结构教学法和教学评价体系对改变教学模式和提升教学质量提供现实意义.通过对测量学在混合教学模式实践中取得的成就及尚待解决的问题进行总结反思,以期对其它课程应用混合教学模式有现实指导意义,进而有助于混合教学模式的推广应用.

Although predecessors have made great contributions to the semantic segmentation of 3D indoor scenes, there still exist some challenges in the debris recognition of terrain data. Compared with hundreds of thousands of indoor point clouds, the amount of terrain point cloud is up to millions. Apart from that, terrain point cloud data obtained from remote sensing is measured in meters, but the indoor scene is measured in centimeters. In this case, the terrain debris obtained from remote sensing mapping only have dozens of points, which means that sufficient training information cannot be obtained only through the convolution of points. In this paper, we build multi-attribute descriptors containing geometric information and color information to better describe the information in low-precision terrain debris. Therefore, our process is aimed at the multi-attribute descriptors of each point rather than the point. On this basis, an unsupervised classification algorithm is proposed to divide the point cloud into several terrain areas, and regard each area as a graph vertex named super point to form the graph structure, thus effectively reducing the number of the terrain point cloud from millions to hundreds. Then we proposed a graph convolution network by employing PointNet for graph embedding and recurrent gated graph convolutional network for classification. Our experiments show that the terrain point cloud can reduce the amount of data from millions to hundreds through the super point graph based on multi-attribute descriptor and our accuracy reached 91.74% and the IoU reached 94.08%, both of which were significantly better than the current methods such as SEGCloud (Acc: 88.63%, IoU: 89.29%) and PointCNN (Acc: 86.35, IoU: 87.26).

为快速准确获取灌区渠系分布信息,科学调配区域农业水资源、提高水资源利用率,通过基于全卷积神经网络(Fully convolutional networks,FCN)的语义分割模型进行渠系轮廓提取.利用无人机采集正射影像并进行标注,以VGG-19网络为基础,通过多尺度特征融合的方式实现FCN-8s结构,使用Tensorflow深度学习框架构建FCN渠系提取模型;对数据集进行数据增强,分割后放入FCN模型中训练、测试.实验结果显示,针对不同复杂程度的测试区域,FCN模型的提取准确度、完整度、精度均高于支持向量机方法和改进霍夫变换方法,均值分别为95.78％、92.29％、89.45％.结果 表明,该方法能够实现灌区渠系轮廓的高精度提取,具有较好的泛化性和鲁棒性.

慕课、微课和翻转课堂的出现,引发了对传统教学理念和教学模式新的变革.文章针对当前遥感课程教学中存在的问题,以慕课、微课和翻转课堂各自的特点为基础,构建遥感课程内容教学体系,设计基于慕课和微课背景下的遥感课程翻转课堂教学模式.这种模式不仅可以激发学生自主学习的积极性,还可以培养学生独立分析问题和解决问题的能力.

通过卫星遥感和低空遥感影像自动、半自动化解译梯田信息有一定的研究进展,但是受数据获取成本、精度、解译方法单一等限制,只限于大面积提取梯田区域,低成本地进行梯田的田面精准提取以及面积统计仍需进一步研究.基于面向对象方法分别对0.5m分辨率的无人机正射影像和地形指数及两种数据的结合进行梯田区域分割、提取及面积统计,结果表明将正射影像数据与地形指数结合的梯田田面提取结果优于基于单一数据源.

在移动网络时代背景下,利用移动智能设备增进测量实验教学中教师与学生之间的交流互动、 资源推送和反馈评价,激发学生的学习兴趣,以提高测量实验教学课程的教学效果.针对传统测量实验教学存在的问题,以西北农林科技大学测量实验课为例,通过蓝墨云班课进行测量实验教学改革和探索,以期对后续测量实验教学改革有一定参考价值.

Irrigation district canal system with modern water-saving irrigation technology has a significant impact on rational distribution of water and the safety of water supply.However,the resolution of the commonly used remote sensing image of irrigation area is not high,which brings difficulties to the extraction and mapping of the drainage system.The high-precision ortho-image,elevation and slope data collected by UAVs were taken together as data sources.Features with strong canal discriminative ability were obtained from them to construct a training set.The classification system was trained via the support vector machine to segment canals from images.Then,the extraction results were denoised,connected and optimized,and the canal extraction of UAV high resolution multi-source data was realized.The results showed that the canal extraction method can identify the branch canal in the irrigation area.Meanwhile,competitive performance was achieved in the continuity of the canal,the bucket and the part of canal system.The precision was up to 89.35％.The extraction error was mainly caused by the deposition of canopy mud in the lower canal system which made the terrain features not easy to be recognized.In conclusion,the method proposed provided a new solution for the extraction of irrigation and drainage canal and can be applied to the actual agricultural production.

Terraced fields are a kind of soil and water conservation measures explored by humans on sloping fields.The construction of terraces largely develops the agricultural growth potential of sloping arable land,which has the functions of water storage and soil conservation.Due to the difficulty in obtaining information such as the number of terraces and distribution of area,it is difficult to carry out the quantitative research on the terraced fields.With the continuous development of unmanned aerial vehicle (UAV) technology,it becomes possible to access high-precision terrain information.Based on the UAV orthorectified images and slope data calculated by digital elevation model (DEM),the rough contour of terraced fields was extracted by Canny edge detection operator,and the false edges of terraced fields were removed according to the structural characteristics of terraced fields.According to edge strength superposition and edge connection operation,the terraces were divided by region growing algorithm.The method effectively solved the problems of uneven terraced fields in the hilly areas,interference of the surface sediments and complicated spectral characteristics of the images.Compared with the field data of terraced plots marked by hand,the results showed that the total accuracy of the proposed algorithm in terraced fields can reach 84.9％.The research result can provide a solution for the rapid mapping of terraced fields.

Most crops in northern China are irrigated, but the topography affects the water use, soil erosion, runoff and yields. Technologies for collecting high-resolution topographic data are essential for adequately assessing these effects. Ground surveys and techniques of light detection and ranging have good accuracy, but data acquisition can be time-consuming and expensive for large catchments. Recent rapid technological development has provided new, flexible, high-resolution methods for collecting topographic data, such as photogrammetry using unmanned aerial vehicles (UAVs). The accuracy of UAV photogrammetry for generating high-resolution Digital Elevation Model (DEM) and for determining the width of irrigation channels, however, has not been assessed. A fixed-wing UAV was used for collecting high-resolution (0.15 m) topographic data for the Hetao irrigation district, the third largest irrigation district in China. 112 ground checkpoints (GCPs) were surveyed by using a real-time kinematic global positioning system to evaluate the accuracy of the DEMs and channel widths. A comparison of manually measured channel widths with the widths derived from the DEMs indicated that the DEM-derived widths had vertical and horizontal root mean square errors of 13.0 and 7.9 cm, respectively. UAV photogrammetric data can thus be used for land surveying, digital mapping, calculating channel capacity, monitoring crops, and predicting yields, with the advantages of economy, speed and ease. Keywords: UAVs, GIS, DEM, irrigation area, photogrammetry, accuracy evaluation DOI: 10.25165/j.ijabe.20181103.3012 Citation: Zhang H M, Yang J T, Baartman J E M, Li S Q, Jin B, Han W T. Quality of terrestrial data derived from UAV photogrammetry: A case study of Hetao irrigation district in northern China. Int J Agric & Biol Eng, 2018; 11(3): 171–177.

The improvement of resolution of digital elevation models (DEMs) and the increasing application of the Revised Universal Soil Loss Equation (RUSLE) over large areas have created problems for the efficiency of calculating the LS factor for large data sets. The pretreatment for flat areas, flow accumulation, and slope-length calculation have traditionally been the most time-consuming steps. However, obtaining these features are generally usually considered as separate steps, and calculations still tend to be time-consuming. We developed an integrated method to improve the efficiency of calculating the LS factor. The calculation model contains algorithms for calculating flow direction, flow accumulation, slope length, and the LS factor. We used the Deterministic 8 method to develop flow-direction octrees (FDOTs), flat matrices (FMs) and first-in-first-out queues (FIFOQs) tracing the flow path. These data structures were much more time-efficient for calculating the slope length inside the flats, the flow accumulation, and the slope length linearly by traversing the FDOTs from their leaves to their roots, which can reduce the search scope and data swapping. We evaluated the accuracy and effectiveness of this integrated algorithm by calculating the LS factor for three areas of the Loess Plateau in China and SRTM DEM of China. The results indicated that this tool could substantially improve the efficiency of LS-factor calculations over large areas without reducing accuracy.

坡度对地表水文、土壤侵蚀、土地利用规划有着重要的影响,区域尺度上的坡度通常基于数字高程模型(DEM)提取.区域尺度上,高分辨率坡度数据由于DEM获取途径、方式等原因,较难获得,通常通过超分辨率重构(又称降尺度变换)得到.以黄土高原地区水平梯田地形为研究对象,基于无人机摄影测量技术,生成不同分辨率的DEM数据并提取坡度,设计并给出了基于稀疏混合估计对DEM数据进行超分辨率重构的方法及流程,并与最近邻法、双线性插值法、三次卷积插值法比较,结果表明所提方法在空间分布和误差方面上均优于其他方法.

Terrain is a main environmental factor which affects the surface hydrology and soil erosion.Slope steepness,slope length and LS factor are important parameters in soil erosion.model.As a water conservation measure,terraced field changes the surface morphology and affects slope steepness,slope length and LS factor.Terrain features of the terraced area based on low resolution DEM are fuzzy and difficult to be reasonably estimated due to the lacking of high precision.High resolution DEM,which was accessed by UAV aerial photogrammetry technology,was used to analyze slope steepness,slope length and LS factor under different resolutions.Meanwhile,the changes of these parameters were calculated and analyzed in a none terraced area with the same resolution changes as comparison.The result showed that the DEMs which were accessed by UAV can express the terrace terrain features in details.Distribution of terraced terrain factors coincided with topographic features.These features showed high values distributed in the ridge area and small values distributed in terrace surface.With the decrease of DEM resolutions,the slope steepness of none terraced areas was decreased while the slope length was increased,and LS value was increased firstly and then decreased because of the fast decrease of the slope stcepness,but the variation range was relatively small.For terraced areas,the portion of both small and large part of the slope steepness was decreased,average slope steepness was also decreased.Slope length had a clear increasing trend,so as the LS factor.Under the resolution of 20 m,LS factor was overestimated for about 33％.Terracing is usually considered as a project factor in soil erosion models of soil and water conservation measures.Due to the large influence of resolution on LS factors,the estimation of erosion in terraced field needs to consider the effect of resolution changes.

High-speed landslide is a catastrophic geological disaster in the mountainous area of southwest China. To predict the movement process of landslide reactivation in Chenjiaba town, Beichuan county, Sichuan province, China, we simulated the movement process of two landslide failures in Chenjiaba via rapid mass movement simulation and unmanned aerial vehicle images (UAV), and obtained the movement characteristic parameters of the landslides. According to a back analysis, the most remarkable fitting rheological parameters were friction coefficient (μ = 0. 18) and turbulence (ξ = 400 m · s -2 ). The parameter of landslide pressure was applied as the zoning index of landslide hazard to obtain the influence zone and hazard zoning map of the Chenjiaba landslide. Results show that the Duba River was blocked quickly with a landslide accumulation at the maximum height of 44.14 m when the Chenjiaba deposits lost stability. The hazard zoning map indicated that the landslide hazard degree is positively correlated with the slope. This landslide assessment is a quantitative hazard assessment method based on a landslide movement process and is suitable for high-speed landslide. Such method can provide a scientific basis for urban construction and planning in the landslide hazard area to avoid hazards effectively.