Explore the vast range of titles available.

Geographic object-based image analysis (GEOBIA) is a remote sensing image analysis paradigm that defines and examines image-objects: groups of neighboring pixels that represent real-world geographic objects. Recent reviews have examined methodological considerations and highlighted how GEOBIA improves upon the 30+ year pixel-based approach, particularly for H-resolution imagery. However, the literature also exposes an opportunity to improve guidance on the application of GEOBIA for novice practitioners. In this paper, we describe the theoretical foundations of GEOBIA and provide a comprehensive overview of the methodological workflow, including: (i) software-specific approaches (open-source and commercial); (ii) best practices informed by research; and (iii) the current status of methodological research. Building on this foundation, we then review recent research on the convergence of GEOBIA with deep convolutional neural networks, which we suggest is a new form of GEOBIA. Specifically, we discuss general integrative approaches and offer recommendations for future research. Overall, this paper describes the past, present, and anticipated future of GEOBIA in a novice-accessible format, while providing innovation and depth to experienced practitioners.

Wildlife management is based on various measurements representative of the health of populations and their habitats. Some agencies are focusing on animal surveys to manage species such as white-tailed deer (Odocoileus virginianus). Current survey methods are faced with the challenge of reduced operating costs as well as estimating and correcting detection biases. Our pilot study (data collected on 6 Nov 2012 at Saint-David-de-Falardeau, QC, Canada) assessed the potential of a new approach detect and count deer based on visible and thermal infrared image processing at very-high spatial resolutions using an unmanned aerial system (UAS). Supervised and unsupervised pixel-based image classification approaches as well as object-based image analysis (OBIA) were assessed for different spatial resolutions and with different combinations of spectral bands. None of the pixel-based approaches were effective for detecting deer. The OBIA approach detected deer with a rate of up to 100% under the best conditions by using a combination of visible and thermal infrared imagery at a spatial resolution of 0.8 cm/pixel. Overall, this approach had an average detection rate of 0.5, which is comparable to conventional aerial surveys. Visual obstructions by coniferous canopy and the spectral confusion associated with certain elements (e.g., bare soil, rocks) are problems that remain unresolved. Using UASs with image processing for surveys of deer and other species of large mammals is promising, but currently limited by the flight range of unmanned aerial vehicles and the associated regulations.

Object-based image analysis (OBIA) has been widely used for land use and land cover (LULC) mapping using optical and synthetic aperture radar (SAR) images because it can utilize spatial information, reduce the effect of salt and pepper, and delineate LULC boundaries. With recent advances in machine learning, convolutional neural networks (CNNs) have become state-of-the-art algorithms. However, CNNs cannot be easily integrated with OBIA because the processing unit of CNNs is a rectangular image, whereas that of OBIA is an irregular image object. To obtain object-based thematic maps, this study developed a new method that integrates object-based post-classification refinement (OBPR) and CNNs for LULC mapping using Sentinel optical and SAR data. After producing the classification map by CNN, each image object was labeled with the most frequent land cover category of its pixels. The proposed method was tested on the optical-SAR Sentinel Guangzhou dataset with 10 m spatial resolution, the optical-SAR Zhuhai-Macau local climate zones (LCZ) dataset with 100 m spatial resolution, and a hyperspectral benchmark the University of Pavia with 1.3 m spatial resolution. It outperformed OBIA support vector machine (SVM) and random forest (RF). SVM and RF could benefit more from the combined use of optical and SAR data compared with CNN, whereas spatial information learned by CNN was very effective for classification. With the ability to extract spatial features and maintain object boundaries, the proposed method considerably improved the classification accuracy of urban ground targets. It achieved overall accuracy (OA) of 95.33% for the Sentinel Guangzhou dataset, OA of 77.64% for the Zhuhai-Macau LCZ dataset, and OA of 95.70% for the University of Pavia dataset with only 10 labeled samples per class.

In regular convolutional neural networks (CNN), fully-connected layers act as classifiers to estimate the probabilities for each instance in classification tasks. The accuracy of CNNs can be improved by replacing fully connected layers with gradient boosting algorithms. In this regard, this study investigates three robust classifiers, namely XGBoost, LightGBM, and Catboost, in combination with a CNN for a land cover study in Hanoi, Vietnam. The experiments were implemented using SPOT7 imagery through (1) image segmentation and extraction of features, including spectral information and spatial metrics, (2) normalization of attribute values and generation of graphs, and (3) using graphs as the input dataset to the investigated models for classifying six land cover classes, namely House, Bare land, Vegetation, Water, Impervious Surface, and Shadow. The results show that CNN-based XGBoost (Overall accuracy = 0.8905), LightGBM (0.8956), and CatBoost (0.8956) outperform the other methods used for comparison. It can be seen that the combination of object-based image analysis and CNN-based gradient boosting algorithms significantly improves classification accuracies and can be considered as alternative methods for land cover analysis.

The allocation of attention to objects raises several intriguing questions: What are objects, how does attention access them, what anatomical regions are involved? Here, we review recent progress in the field to determine the mechanisms underlying object-based attention. First, findings from unconscious priming and cueing suggest that the preattentive targets of object-based attention can be fully developed object representations that have reached the level of identity. Next, the control of object-based attention appears to come from ventral visual areas specialized in object analysis that project downward to early visual areas. How feedback from object areas can accurately target the object’s specific locations and features is unknown but recent work in autoencoding has made this plausible. Finally, we suggest that the three classic modes of attention may not be as independent as is commonly considered, and instead could all rely on object-based attention. Specifically, studies show that attention can be allocated to the separated members of a group—without affecting the space between them—matching the defining property of feature-based attention. At the same time, object-based attention directed to a single small item has the properties of space-based attention. We outline the architecture of object-based attention, the novel predictions it brings, and discuss how it works in parallel with other attention pathways.

To improve the accuracy of change detection in urban areas using bi-temporal high-resolution remote sensing images, a novel object-based change detection scheme combining multiple features and ensemble learning is proposed in this paper. Image segmentation is conducted to determine the objects in bi-temporal images separately. Subsequently, three kinds of object features, i.e., spectral, shape and texture, are extracted. Using the image differencing process, a difference image is generated and used as the input for nonlinear supervised classifiers, including k-nearest neighbor, support vector machine, extreme learning machine and random forest. Finally, the results of multiple classifiers are integrated using an ensemble rule called weighted voting to generate the final change detection result. Experimental results of two pairs of real high-resolution remote sensing datasets demonstrate that the proposed approach outperforms the traditional methods in terms of overall accuracy and generates change detection maps with a higher number of homogeneous regions in urban areas. Moreover, the influences of segmentation scale and the feature selection strategy on the change detection performance are also analyzed and discussed.

Tanjung Kelayang is vulnerable to ecosystem change driven by human activities and environmental factors. This study aimed to map and analyze changes in benthic habitats using Sentinel-2A imagery from 2019 and 2024 by applying an Object-Based Image Analysis (OBIA) approach combined with a Support Vector Machine (SVM) classifier. The analysis included water column correction using the depth-invariant index (DII), multiresolution segmentation, habitat classification, accuracy assessment, and post-classification change detection. Six benthic habitat classes were identified, namely coral, seagrass, macroalgae, sand, rocks, and coral rubble. The results show a decrease in coral cover of 87.99 ha (19.96%) and a substantial increase in coral rubble of 80.33 ha (87.77%), indicating reef degradation. The classification achieved an Overall Accuracy of 70.97% with a kappa coefficient of 0.61, reflecting a good classification performance. These findings demonstrate that Sentinel-2A imagery combined with the OBIA method is effective for monitoring changes in shallow marine habitats, and supports spatial-based coastal zone management.

Floodplain wetlands play a crucial role in the global carbon cycle, yet the spatiotemporal variation of carbon flux in floodplain wetlands remains poorly understood due to complex hydrological processes. Here, we present an integrated framework to upscale net ecosystem CO2 exchange (NEE) in floodplain wetlands by combining eddy covariance measurements, object‐based image analysis (OBIA), hydrodynamic models, and integrated machine learning (ML) techniques. The proposed framework was instantiated in the Poyang Lake floodplain wetland, China. Results showed that OBIA could effectively capture the heterogeneous surface of wetlands through multi‐scale segmentation, thereby providing suitable space units for NEE upscaling. Hydrological regimes obtained by the hydrodynamic model, that is, maximum flood level (MFL), mean water level (WL) and water level fluctuation (WLF), were the key drivers to the NEE variability. The integrated ML model could effectively upscale NEE with higher R2 and superior robustness than commonly used individual ML model, benefiting from an optimized integration of outputs from multiple ML model through Powell optimization. The spatiotemporal distribution of the upscaled NEE results indicated that permanently inundated areas in floodplain wetlands mostly functioned as carbon sources or weak carbon sinks, while littoral zones functioned as carbon sinks. Hydrological regime changes lead to a shift between carbon sources and sinks in floodplain wetlands. The proposed framework can provide a feasible way to analyze the spatiotemporal changes of NEE and is of great benefit to achieving carbon sequestration in floodplain wetlands.

The National Land Cover Database (NLCD) 2016 provides a suite of data products, including land cover and land cover change of the conterminous United States from 2001 to 2016, at two- to three-year intervals. The development of this product is part of an effort to meet the growing demand for longer temporal duration and more frequent, accurate, and consistent land cover and change information. To accomplish this, we designed a new land cover strategy and developed comprehensive methods, models, and procedures for NLCD 2016 implementation. Major steps in the new procedures consist of data preparation, land cover change detection and classification, theme-based postprocessing, and final integration. Data preparation includes Landsat imagery selection, cloud detection, and cloud filling, as well as compilation and creation of more than 30 national-scale ancillary datasets. Land cover change detection includes single-date water and snow/ice detection algorithms and models, two-date multi-index integrated change detection models, and long-term multi-date change algorithms and models. The land cover classification includes seven-date training data creation and 14-run classifications. Pools of training data for change and no-change areas were created before classification based on integrated information from ancillary data, change-detection results, Landsat spectral and temporal information, and knowledge-based trajectory analysis. In postprocessing, comprehensive models for each land cover theme were developed in a hierarchical order to ensure the spatial and temporal coherence of land cover and land cover changes over 15 years. An initial accuracy assessment on four selected Landsat path/rows classified with this method indicates an overall accuracy of 82.0% at an Anderson Level II classification and 86.6% at the Anderson Level I classification after combining the primary and alternate reference labels. This methodology was used for the operational production of NLCD 2016 for the Conterminous United States, with final produced products available for free download.

Boreal forest areas in the Russian Far East contained very large intact forests. This particular area is considered one of the most productive and diverse forests in the boreal biome of the world, and it is also home to many endangered species. Zeya State Nature Reserve is located at the southern margin of the boreal forest area in the Russian Far East and has rich fauna and flora. However, the forest in the region faced large-scale forest fires and clearcutting for timber recently. The information of disturbances is rarely understood. This study aimed to explore the effects of disturbance and forest dynamics around the reserve. Our study used two-year overlaid Landsat images from Landsat 5 Thematic Mapper (TM) and 8 Operational Land Imager (OLI), to generate forest-cover-change maps of 1988–1999, 1999–2010, and 2010–2016. In this paper, we analyze the direction of forest successional stages, to demonstrate the effectiveness of this protected area in terms of preventing human-based deforestation on the vegetation indices. The vegetation indices included the normalized burn ratio (NBR), the normalized difference vegetation index (NDVI), and the normalized difference water index (NDWI). The study provided information on the pattern of forest-cover change and disturbance area around the reserve. The NDWI was used to differentiate between water and non-water areas. The mean values of NBR and NDVI were calculated and determine the forest successional stages between burn, vegetation recovery, grass, mixed forest, oak forest, and birch and larch forest. The accuracy was assessed by using field measurements, field photos, and high-resolution images as references. Overall, our classification results have high accuracy for all three periods. The most disturbed area occurred during 2010–2016. The reserve was highly protected, with no human-disturbance activity. However, large areas from fire disturbance were found (137 km2) during 1999–2010. The findings also show a large area of disturbance, mostly located outside of the reserve. Mixed disturbance increased to almost 50 km2 during 2010–2016, in the buffer zone and outside of the reserve. We recommend future works to apply our methods to other ecosystems, to compare the forest dynamics and disturbance inside and outside the protected area.