Combining per-pixel and object-based classifications for mapping land cover over large areas

A plethora of national and regional applications need land-cover information covering large areas. Manual classification based on visual interpretation and digital per-pixel classification are the two most commonly applied methods for land-cover mapping over large areas using remote-sensing images, but both present several drawbacks. This paper tests a method with moderate spatial resolution images for deriving a product with a predefined minimum mapping unit (MMU) unconstrained by spatial resolution. The approach consists of a traditional supervised per-pixel classification followed by a post-classification processing that includes image segmentation and semantic map generalization. The approach was tested with AWiFS data collected over a region in Portugal to map 15 land-cover classes with 10 ha MMU. The map presents a thematic accuracy of 72.6 ± 3.7% at the 95% confidence level, which is approximately 10% higher than the per-pixel classification accuracy. The results show that segmentation of moderate-spatial resolution images and semantic map generalization can be used in an operational context to automatically produce land-cover maps with a predefined MMU over large areas.     

Coastal wetland classification with multiseasonal high-spatial resolution satellite imagery

ABSTRACT

Accurate mapping of wetland distribution is required for wetland conservation, management, and restoration, but remains a challenge due to the complexity of wetland landscapes. This research employed four seasons of multispectral images from Gaofen-1 satellite to map wetland land-cover distribution in Hangzhou bay coastal wetland (245 km²) in China. Maximum likelihood classifier (MLC), random forest (RF), and the expert-based approach were examined based on spectral, spatial, and phenological features. The results showed that land-cover classification accuracies of 83.9% using RF and 90.3% using the expert-based approach were obtained, and they had higher accuracy than MLC, which had an overall accuracy of only 63.3%. The high classification accuracy for nine land-cover classes using the expert-based approach indicated the important role of expert knowledge from the phenological features in improving wetland classification accuracy. As high spatial resolution satellite images become more easily obtainable, effective use of temporal information of different sensor data will be valuable for detailed land-cover classification with higher accuracy. The approach to establish expert rules from multitemporal images provides a new way to improve land-cover classification in different terrestrial ecosystems.     

Accuracy analysis of remote sensing change detection by rule-based rationality evaluation with post-classification comparison

Accuracy assessment for remote sensing classification is commonly based on using an error matrix, or confusion table, which needs reference, or ‘ground truthing’, data to support. When undertaking change detection using numerous multi-temporal images, it is often difficult to make the accuracy assessment by the ‘traditional’ method, which typically requires simultaneous collection of reference data. In this study, we propose a new approach by arguing change rationality with post-classification comparison. Multi-temporal Landsat TM images were classified for land use in an urban fringe area of Beijing, China and the post-classification comparison of these classified images shows change trajectories through the time series. These change trajectories were then analysed by assessing their rationality against a set of logical rules to separate cases of ‘real land use change’ and possible classification errors. The analysis results show that the overall accuracy for land use change in the urban fringe area was 86%, with a fuzziness of 7%. Although it is argued that the uncertainty still exists on classification accuracy assessed by this method, it nevertheless provides an alternative approach for more reasonable assessment when ideal simultaneous ‘ground truthing’ is not available.     

Land-cover classification using multi-temporal GF-1 wide field view data

ABSTRACT

Vegetation is an important land-cover type and its growth characteristics have potential for improving land-cover classification accuracy using remote-sensing data. However, due to lack of suitable remote-sensing data, temporal features are difficult to acquire for high spatial resolution land-cover classification. Several studies have extracted temporal features by fusing time-series Moderate Resolution Imaging Spectroradiometer data and Landsat data. Nevertheless, this method needs assumption of no land-cover change occurring during the period of blended data and the fusion results also present certain errors influencing temporal features extraction. Therefore, time-series high spatial resolution data from a single sensor are ideal for land-cover classification using temporal features. The Chinese GF-1 satellite wide field view (WFV) sensor has realized the ability of acquiring multispectral data with decametric spatial resolution, high temporal resolution and wide coverage, which contain abundant temporal information for improving land-cover classification accuracy. Therefore, it is of important significance to investigate the performance of GF-1 WFV data on land-cover classification. Time-series GF-1 WFV data covering the vegetation growth period were collected and temporal features reflecting the dynamic change characteristics of ground-objects were extracted. Then, Support Vector Machine classifier was used to land-cover classification based on the spectral features and their combination with temporal features. The validation results indicated that temporal features could effectively reflect the growth characteristics of different vegetation and finally improved classification accuracy of approximately 7%, reaching 92.89% with vegetation type identification accuracy greatly improved. The study confirmed that GF-1 WFV data had good performances on land-cover classification, which could provide reliable high spatial resolution land-cover data for related applications.     

Classification of the wildland–urban interface: A comparison of pixel- and object-based classifications using high-resolution aerial photography

The expansion of urban development into wildland areas can have significant consequences, including an increase in the risk of structural damage from wildfire. Land-use and land-cover maps can assist decision-makers in targeting and prioritizing risk mitigation activities, and remote sensing techniques provide effective and efficient methods to create such maps. However, some image processing approaches may be more appropriate than others in distinguishing land-use and land-cover categories, particularly when classifying high spatial resolution imagery for urbanizing environments. Here we explore the accuracy of pixel-based and object-based classification methods used for mapping in the wildland–urban interface (WUI) with free, readily available, high spatial resolution urban imagery, which is available in many places to municipal and local fire management agencies. Results indicate that an object-based classification approach provides a higher accuracy than a pixel-based classification approach when distinguishing between the selected land-use and land-cover categories. For example, an object-based approach resulted in a 41.73% greater accuracy for the built area category, which is of particular importance to WUI wildfire mitigation.     

Pre-classification and post-classification change-detection techniques to monitor land-cover and land-use change using multi-temporal Landsat imagery: a case study on Pisa Province in Italy

This article explores the simultaneous use of pre-classification and post-classification change-detection techniques to map and monitor land-cover and land-use change using multi-temporal Landsat Multi-spectral Scanner and Enhanced Thematic Mapper plus data over one of the most important tourism centres of Italy (e.g. Pisa Province) for 1972, 2000 and 2006.

Pre-classification approaches of principal-component analysis and band combination are potentially tailored to reduce data redundancy of the satellite imagery in order to highlight different objects of significance for change-detection analysis across time-series data. In this work, the application of pre-classification techniques could contribute to produce land-cover and land-use maps with higher quality of classification. At this point, the average value of overall classification accuracies for the three classification outputs was an estimated 90%.

Then, ‘from–to’ change information, as well as the area and the type of landscape transformations, are provided through the post-classification technique. The findings of this study show that the province of Pisa has significantly experienced a high rate of deforestation and urban development over past decades. It is revealed that artificial structures (e.g. urban and industrial zones) in Pisa Province increased at a change rate of around 265% and forested land decreased from approximately 45% to 32% of the total area of the province between 1972 and 2006. Likewise, the perceptible growth of built-up structures from about 4% to 10.6% in Pisa City during this 34-year period has imposed a heavy pressure on the landscape of Pisa.     

遥感监测东北地区典型湖泊湿地变化的方法研究

湖泊湿地生态脆弱,易受环境因子的影响。近十年来,东北地区湖泊湿地的时空格局发生了显著变化。如何简单、有效地提取湿地变化范围进而确定其变化类型是湿地变化检测中最需要解决的问题。基于2006~2016年30 m空间分辨率的Landsat-TM/OLI影像数据,水体、植被和土壤等生态因子的动态变化率被用于提取东北地区湖泊湿地变化范围;多维特征数据集的湿地分类方案确定湿地的变化类型。另外,湿地变化检测类型分为转出类型（湿地减少）,转入类型（湿地增加）和湿地间转换类型（湿地相对稳定）。最终基于动态变化率计算方法,松嫩平原湿地、兴凯湖湿地和呼伦湖湖泊湿地变化结果的正检率均高于90%。同时,利用年内多时相数据和综合多维生态指数共同表征地表的状态变化,实验区的湖泊湿地分类结果的整体分类精度和 Kappa 系数分别达到 84.31%和0.788。湖泊湿地变化检测方法具有很好的检测精度,可以代表研究区湖泊湿地类型的实际变化,是湿地资源调查与遥感监测技术研究的有益补充,为进一步深化与拓宽地表生态质量评价及其动态变化检测的方法研究提供理论基础。     

Classification of Landsat images based on spectral and topographic variables for land-cover change detection in Zagros forests

Detection of land-cover changes through time can be complicated because of sensor-specific differences in spatial and spectral resolutions; classified land-cover changes can be due to either real changes on the ground or a switch in sensors used to collect data. This study focused on two objectives: (1) selecting the best predictor variables for the classification of semi-arid Zagros forests given the characteristics of the study area and available data sets and (2) evaluating the application of the random forest (RF) algorithm as a unified technique for the classification of data sets acquired from different sensors. Three images of the same study area were acquired from the Landsat-5 Thematic Mapper (TM) sensor in 2009, the Landsat-7 Enhanced Thematic Mapper (ETM+) sensor with Scan Line Corrector (SLC) in 1999 and the Landsat-2 Multispectral Scanner (MSS) sensor in 1975. Following image preprocessing, the RF algorithm was applied for variable selection and classification. A test of equivalence was used to compare the overall accuracy of the classified maps from the three sensors. Slope, normalized difference vegetation index (NDVI) and elevation were determined to be the most important predictor variables for all three images. High overall classification accuracies were achieved for all three images (97.90% for MSS, 95.43% for TM and 95.29% for ETM). The ETM- and TM-derived maps had equivalent overall accuracy and even significantly higher overall accuracy was obtained for the MSS-derived map. The post-classification comparison showed an increase in agriculture and a decrease in forest cover. The selected predictor variables were consistent with ecological reality and showed more details on the changes of the land-cover classes across biophysical variables of the study area through time.     

An integrated spatio-temporal classification method for urban fringe change detection analysis

The urban fringe is the transition zone between urban land use and rural land use. It represents the most active part of the urban expansion process. Change detection using multi-temporal imagery is proven to be an efficient way to monitor land-use/land-cover change caused by urban expansion. In this study, we propose a new multi-temporal classification method for change detection in the urban fringe area. The proposed method extracts and integrates spatio-temporal contextual information into multi-temporal image classification. The spatial information is extracted by object-oriented image segmentation. The temporal information is modelled with temporal trajectory analysis with a two-step calibration. A probabilistic schema that employs a global membership function is then used to integrate the spectral, spatial and temporal information. A trajectory accuracy measurement is proposed to assist the comparison on the performances of the integrated spatio-temporal method and classical pixel- and ‘snapshot’-based classification methods. The experiment shows that the proposed method can significantly improve the accuracies of both single scene classification and temporal trajectory analysis.     

Spatiotemporal analysis of land-use and land-cover change in the Brazilian Amazon

This paper provides a comparative analysis of land-use and land-cover (LULC) changes among three study areas with different biophysical environments in the Brazilian Amazon at multiple scales, from per-pixel, polygon, census sector, to study area. Landsat images acquired during the years of 1990/1991, 1999/2000, and 2008/2010 were used to examine LULC change trajectories with the post-classification comparison approach. A classification system composed of six classes – forest, savanna, other vegetation (secondary succession and plantations), agro-pasture, impervious surface, and water – was designed for this study. A hierarchical-based classification method was used to classify Landsat images into thematic maps. This research shows different spatiotemporal change patterns, composition, and rates among the three study areas and indicates the importance of analysing LULC change at multiple scales. The LULC change analysis over time for entire study areas provides an overall picture of change trends, but detailed change trajectories and their spatial distributions can be better examined at a per-pixel scale. The LULC change at the polygon scale provides the information of the changes in patch sizes over time, while the LULC change at census sector scale gives new insights on how human-induced activities (e.g. urban expansion, roads, and land-use history) affect LULC change patterns and rates. This research indicates the necessity to implement change detection at multiple scales for better understanding the mechanisms of LULC change patterns and rates.     

Change detection with heterogeneous data using ecoregional stratification, statistical summaries and a land allocation algorithm

A ca. 1980 national-scale land-cover classification based on aerial photo interpretation was combined with 2000 AVHRR satellite imagery to derive land cover and land-cover change information for forest, urban, and agriculture categories over a seven-state region in the U.S. To derive useful land-cover change data using a heterogeneous dataset and to validate our results, we a) stratified the classification using predefined ecoregions, b) developed statistical relationships by ecoregion between land-cover proportions derived from the 1980 national-level classification and aggregate statistical data that were available in time series for all regions in the U.S., c) classified multi-temporal AVHRR data using a process that constrained the results to the estimated proportions of land covers in ecoregions within a multi-objective land allocation (MOLA) procedure, d) interpreted land cover from a sample of aerial photographs from 2000, following the protocols used to produce the 1980 classification for use in accuracy assessment of land cover and land-cover change data, and e) compared land cover and land-cover change results for the MOLA method with an unsupervised classification alone. Overall accuracies for the 2000 MOLA and unsupervised land-cover classifications were 85% and 82%, respectively. On average, the 1980-2000 land-cover change RMSEs were one order of magnitude lower using the MOLA method compared with those based on the unsupervised data.     

Mapping and monitoring riparian vegetation distribution,structure and composition with regression tree models and post-classification change metrics

Riparian systems have become increasingly susceptible to both natural and human disturbances as cumulative pressures from changing land use and climate alter the hydrological regimes. This article introduces a landscape dynamics monitoring protocol that incorporates riparian structural classes into the land-cover classification scheme and examines riparian change within the context of surrounding land-cover change. We tested whether Landsat Thematic Mapper (TM) imagery could be used to document a riparian tree die-off through the classification of multi-date Landsat images using classification and regression tree (CART) models trained with physiognomic vegetation data. We developed a post-classification change map and used patch metrics to examine the magnitude and trajectories of riparian class change relative to mapped disturbance parameters. Results show that catchments where riparian change occurred can be identified from land-cover change maps; however, the main change resulting from the die-off disturbance was compositional rather than structural, making accurate post-classification change detection difficult.     

Land Cover Classification for Different Spatial Resolution Images from CNN

Based on convolutional neural networks and five different spatial resolution remote sensing images, the land use/land cover classification study was carried out on a small area in the eastern part of Xining City, aiming at exploring the differences of image classification by CNN with different spatial resolutions and CNN’s ability to extract different features. In order to improve the selection efficiency of the samples, a window sliding method was introduced to assist the samples selection. The research shows that the overall classification accuracy of the five different spatial resolution images is above 89%, the Kappa coefficient is above 0.86. The result further shows that within the resolution scale the higher the resolution, the performance of the CNN classification results for the details is better, and can maintain high classification accuracy, indicating that CNN is more suitable for high spatial resolution images; at the same time, the image spatial resolution is too high, the ground objects exhibit high intra-class variability and low inter-class variability, the classification accuracy tends to decrease. In comparison, CNN has the best classification effect on SPOT 6 images in this study, and window sliding is an effective sample-assisted selection method. This research has certain reference significance for similar research in the future.     

基于CNN的不同空间分辨率影像土地覆被分类研究

基于卷积神经网络（Convolutional Neural Networks, CNN）和5种不同空间分辨率的遥感影像,对西宁市东部一区域开展土地覆被分类研究,旨在探索CNN在不同空间分辨率下进行影像分类的差异性和对不同地物的提取能力。为提高样本的选择效率,引入了窗口滑动方法进行辅助选样。研究表明5种不同空间分辨率影像的总体分类精度均达89%以上,Kappa系数达0.86以上,分类精度较高。在所涉及的分辨率尺度范围内,空间分辨率越高,CNN分类结果越精细,并能保持较高的分类精度,表明CNN更适合高空间分辨率影像分类;但同时影像空间分辨率越高,地物表现出较高的类内变异性和低类间差异性,分类精度有降低的趋势。相比较而言,SPOT 6影像的分类精度最高,同时窗口滑动是一种有效的样本辅助选择方法。研究对今后同类工作具有一定的借鉴意义。     

Mapping the land-cover distribution in arid and semiarid urban landscapes with Landsat Thematic Mapper imagery

Mapping the land-cover distribution in arid and semiarid urban landscapes using medium spatial resolution imagery is especially difficult due to the mixed-pixel problem in remotely sensed data and the confusion of spectral signatures among bare soils, sparse density shrub lands, and impervious surface areas (ISAs hereafter). This article explores a hybrid method consisting of linear spectral mixture analysis (LSMA), decision tree classifier, and cluster analysis for mapping land-cover distribution in two arid and semiarid urban landscapes: Urumqi, China, and Phoenix, USA. The Landsat Thematic Mapper (TM) imagery was unmixed into four endmember fraction images (i.e. high-albedo object, low-albedo object, green vegetation (GV), and soil) using the LSMA approach. New variables from these fraction images and TM spectral bands were used to map seven land-cover classes (i.e. forest, shrub, grass, crop, bare soil, ISA, and water) using the decision tree classifier. The cluster analysis was further used to modify the classification results. QuickBird imagery in Urumqi and aerial photographs in Phoenix were used to assess classification accuracy. Overall classification accuracies of 86.0% for Urumqi and 88.7% for Phoenix were obtained, much higher accuracies than those utilizing the traditional maximum likelihood classifier (MLC). This research demonstrates the necessity of using new variables from fraction images to distinguish between ISA and bare soils and between shrub and other vegetation types. It also indicates the different effects of spatial patterns of land-cover composition in arid and semiarid landscapes on urban land-cover classification.     

Wetland mapping by fusion of airborne laser scanning and multi-temporal multispectral satellite imagery

Wetlands play a major role in Europe’s biodiversity. Despite their importance, wetlands are suffering from constant degradation and loss, therefore, they require constant monitoring. This article presents an automatic method for the mapping and monitoring of wetlands based on the fused processing of laser scans and multispectral satellite imagery, with validations and evaluations performed over an area of Lake Balaton in Hungary. Markov Random Field models have already been shown to successfully integrate various image properties in several remote sensing applications. In this article, we propose the multi-layer fusion Markov Random Field model for classifying wetland areas, built into an automatic classification process that combines multi-temporal multispectral images with a wetland classification reference map derived from airborne laser scanning (ALS) data acquired in an earlier year. Using an ALS-based wetland classification map that relied on a limited amount of ground truthing proved to improve the discrimination of land-cover classes with similar spectral characteristics. Based on the produced classifications, we also present an unsupervised method to track temporal changes of wetland areas by comparing the class labellings of different time layers. During the evaluations, the classification model is validated against manually interpreted independent aerial orthoimages. The results show that the proposed fusion model performs better than solely image-based processing, producing a non-supervised/semi-supervised wetland classification accuracy of 81–93% observed over different years.     

Object-based land cover classification of shaded areas in high spatial resolution imagery of urban areas: A comparison study

A significant proportion of high spatial resolution imagery in urban areas can be affected by shadows. Considerable research has been conducted to investigate shadow detection and removal in remotely sensed imagery. Few studies, however, have evaluated how applications of these shadow detection and restoration methods can help eliminate the shadow problem in land cover classification of high spatial resolution images in urban settings. This paper presents a comparison study of three methods for land cover classification of shaded areas from high spatial resolution imagery in an urban environment. Method 1 combines spectral information in shaded areas with spatial information for shadow classification. Method 2 applies a shadow restoration technique, the linear-correlation correction method to create a “shadow-free” image before the classification. Method 3 uses multisource data fusion to aid in classification of shadows. The results indicated that Method 3 achieved the best accuracy, with overall accuracy of 88%. It provides a significantly better means for shadow classification than the other two methods. The overall accuracy for Method 1 was 81.5%, slightly but not significantly higher than the 80.5% from Method 2. All of the three methods applied an object-based classification procedure, which was critical as it provides an effective way to address the problems of radiometric difference and spatial misregistration associated with multisource data fusion (Method 3), and to incorporate thematic spatial information (Method 1).     

Detection of land use/land cover changes for the northern part of the Nile delta (Burullus region), Egypt

The monitoring of land use/land cover changes along the north part of the Nile delta, Egypt is very important for the planner, management, governmental and non-governmental organizations and the scientific community. This information is essential for planning and implementing policies to optimize the use of natural resources and accommodate development whilst minimizing the impact on the environment. To study these changes along the study area, two sets of Landsat Thematic Mapper (TM) data were used. TM data are useful for this type of study due to its high spatial resolution, spectral resolution and low repetitive acquisition (16 days). A post-classification technique is used in this study based on hybrid classification (unsupervised and supervised). Each method used was assessed, and checked in field. Nine land use/land cover classes are produced. The overall accuracy for a 1984 image is 78% and for a 1997 image is 80%. The objective of this study was to detect land use/land cover changes, and to assess the nature of future change following construction of the international coastal road which crosses the study area.     

Improving forest type classification using the vegetation local difference index

A spatial feature extraction method was applied to increase the accuracy of land-cover classification of forest type information extraction. Traditional spatial feature extraction applications use high-resolution images. However, improving the classification accuracy is difficult when using medium-resolution images, such as a 30 m resolution Enhanced Thematic Mapper Plus (ETM+) image. In this study, we demonstrated a novel method that used the vegetation local difference index (VLDI) derived from the normalized difference vegetation index (NDVI), which were calculated based on the topographically corrected ETM+ image, to delineate spatial features. A simple maximum likelihood classifier and two different ways to use spatial information were introduced in this study as the frameworks to incorporate both spectral and spatial information for analysis. The results of the experiments, where Landsat ETM+ and digital elevation model (DEM) images, together with ground truth data acquired in the study area were used, show that combining the spatial information extracted from medium-resolution images and spectral information improved both classification accuracy and visual qualities. Moreover, the use of spatial information extracted through the proposed method greatly improved the classification performance of particular forest types, such as sparse woodlands.     

基于多尺度分割的遥感影像滨海湿地分类

基于多尺度的高分辨率遥感影像分类方法研究,可以为滨海湿地动态监测、规划保护提供更详尽的湿地分类信息和更快速的数据获取方法,对湿地保护具有重要意义。选取连云港青口河入海口处湿地为研究区,以高分辨率遥感影像WV\|Ⅱ和航空遥感影像为数据源,利用多尺度分割方法将影像分割成不同层次的实体对象;在不同层次,以实体对象为单元,结合光谱、形状、纹理等不同影像特征,进行滨海湿地分类研究,结果表明:利用该方法分类后,研究区各种湿地类型都达到较高精度。基于多尺度分割的影像分类方法能充分利用各种影像特征完成湿地分类,有效地减少了遥感影像中的“椒盐”现象,提高了分类精度;选择适宜的分割尺度和分割参数是基于多尺度分割的遥感影像分类方法提高精度的前提。