Multiscale and Multisubgraph-Based Segmentation Method for Ocean Remote Sensing Images

A Real-World Size Organization of Object Responses in Occipitotemporal Cortex

Object-based image analysis (OBIA) method has been proven to improve the accuracy value on benthic habitat mapping. The purpose of this study was to assess the accuracy of several classification algorithms on benthic habitat mapping based on OBIA method with and without input feature of Hue Saturation Intensity (HSI) in the Pajenekang island waters, South Sulawesi, Indonesia. Sentinel-2A satellite imagery with 10 m2 spatial resolution acquired on 3 September 2018 was used in this study. During OBIA analyses, we segmented the object into 5, 10, and 15 classes and treated each of them with input features of mean+ratio vs mean+ratio+hue saturation intensity (HSI). We later classified the benthic habitat by applying several classification algorithms such as the Bayes, K-Nearest Neighbour (KNN), Support Vector Machine (SVM), and Decision Tree (DT). The results showed that the Bayes algorithm produced highest accuracy of 78.35% within 10 segmentation classes and input features of mean+ratio+HSI followed by the KNN of 71.13% with 5 segmentation classes and input features of mean+ration+HSI. The addition of HSI input features into OBIA analyses increased the accuracy of benthic habitat classification mapping of 4.13% with the Bayes classification algorithm.

Shallow sea habitat has a very important role as a place to live and shelter for various types of organisms. Mapping this area needs to be done regularly considering the many benefits it has and the tendency for this area to change, one of them is by using remote sensing technology with the object-based image analysis (OBIA) method. OBIA classification includes the process of image segmentation and classification of all segmentation results. In the segmentation process using scale 100 at level 1 and scale 10 at level 2. Furthermore, at the classification process, 6 (six) habitat classes are obtained, namely sand, coral, macroalgae, sea grass, rubble and dead coral algae. The overall accuracy value in 2018 showed a value of 70%, and in 2022, it showed a value of 70.77%. The kappa coefficient value is 0.617 in the 2018 image acquisition and 0.612 in the 2022 image acquisition. The analysis carried out showed that there was a change in each habitat with the habitat that experienced the greatest changes are sand and dead coral algae class.

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Abstract. Agroforestry is an integrated self-sustainable land use management system that is not only capable of producing food from marginal agricultural land but also capable of maintaining and improving the quality of environment. Accurate assessment of trees on farmlands i.e. agroforestry would help in determining their contribution in meeting timber demand and also in carbon sequestration vis-a-vis climate change mitigation. In the present, high resolution multispectral satellite imagery (LISS-IV) has been used for mapping and estimating agroforestry area in Koraput district of Odisha. Both supervised and Object based Image Analysis (OBIA) classifications methods have been applied. In case of supervised maximum likelihood method, those pixels are fully captured where trees exist, whereas in OBIA captures trees according to their crown shapes. This proved OBIA method to be better in identification of trees on farmlands (scattered trees, boundary, and block plantations) than supervised method. This can lead to accurate estimation of area under trees in scattered form, in linear form and also in patch form. Improved results were obtained in case of OBIA classification with more than 90% accuracy. This research implies that remote sensing provide promising tools for evaluating and mapping of agroforestry at district level. Hence, the proposed approach of using high resolution remote sensing data in conjunction with OBIA method would be promising for mapping agroforestry area.

Substantial progress in Geoinformatics System in recent years leads to the research in monitoring and mapping of glaciers. Monitoring glacier in the mountain region with traditional manual method is very crucial and time-consuming. Glaciers are melting because of global warming. Melting of glaciers can causes calamities like rising in sea level, glacial lake outburst, avalanches etc. Glacier monitoring using multi-temporal data for objects on the surface of the glacier is hard to classify. This paper gives an insight into the importance of Geo-spatial data and object-based image analysis method for satellite image processing. The object-based image analysis benefits more compared to traditional pixel-based image analysis as it is more robust and noise removing more image features etc. Spectral data with multiple bands is the backbone of surveying and monitoring of glacier. In this paper case study of Mount Everest region (27 48° 32N, 86 54° 47E) is represented. The remotely sensed image needs to be taken in a cloud-free environment. Object-based image classification is done in recognition tool. Also, the step by step methodology of object-based classification, segmentation and post-classification possibilities are discussed. Finally, the paper presents several representations of indexes. The integration of indexes is useful for accurately classifying the different part of terrain, lake, vegetation and glacier.

Chinese olive trees (Canarium album L.) are broad-leaved species that are widely planted in China. Accurately obtaining tree crown information provides important data for evaluating Chinese olive tree growth status, water and fertilizer management, and yield estimation. To this end, this study first used unmanned aerial vehicle (UAV) images in the visible band as the source of remote sensing (RS) data. Second, based on spectral features of the image object, the vegetation index, shape, texture, and terrain features were introduced. Finally, the extraction effect of different feature dimensions was analyzed based on the random forest (RF) algorithm, and the performance of different classifiers was compared based on the features after dimensionality reduction. The results showed that the difference in feature dimensionality and importance was the main factor that led to a change in extraction accuracy. RF has the best extraction effect among the current mainstream machine learning (ML) algorithms. In comparison with the pixel-based (PB) classification method, the object-based image analysis (OBIA) method can extract features of each element of RS images, which has certain advantages. Therefore, the combination of OBIA and RF algorithms is a good solution for Chinese olive tree crown (COTC) extraction based on UAV visible band images.

Sentinel-2A remote sensing satellite system was recently launched, providing free global remote sensing data similar to Landsat systems. Although the mission enables the acquisition of 10 m spatial resolution global data, the assessment of Sentinel-2A data performance for mapping in Malaysia is still limited. This study aimed to investigate and assess the capability of Sentinel-2A imagery in mapping urban areas in Malaysia by comparing its performance against the established Landsat-8 data as well as the fusion datasets from combining Landsat-8 and Sentinel-2A datasets and using Wavelet transform (WT), Brovey transform (BT) and principal component analysis. Pixel-based and object-based image analysis (OBIA) classification approaches combined with support vector machine (SVM) and decision tree (DT) algorithms were utilized in this assessment, and the accuracy generated was analysed. The Sentinel-2A data provided superior urban mapping output over the use of Landsat-8 alone, and the fusion datasets do not yield advantages for single-scene urban mapping. The highest overall accuracy (OA) for pixel-based classification of Sentinel-2A images is 84.77 % by SVM, followed by 65.27 % using DT. BT produced the highest OA for the fusion images of 78.40 % with SVM and 52.21 % with DT. For the object-based classification of Sentinel-2A images, the highest OA is 71.33 % by SVM, followed by 76.38 % using DT. Similarly, the highest OA of fusion images is obtained by BT of 50.35 % with SVM, followed by 65.66 % with DT. From the analysis, the use of SVM pixel-based classification for medium spatial resolution Sentinel-2A data is effective for urban mapping in Malaysia and useful for future long-term mapping applications. HIGHLIGHTS An accurate mapping of urban land is still challenging and requires high image quality of spectral and spatial aspects to identify features Single and fusion image analysis conducted in order to investigate and assess the most performing interpretation result by grouping out the features classes Statistical performance and image classification comparison is relevant to prove the most effective result among the images GRAPHICAL ABSTRACT

Determine whether the size-arrival effect (SAE) occurs with immersive, 3D visual experiences and active collision-avoidance responses. When a small near object and a large far object approach the observer at the same speeds, the large object appears to arrive before the small object, known as the size-arrival effect (SAE), which may contribute to crashes between motorcycles and cars. Prior studies of the SAE were limited because they used two dimensional displays and asked participants to make passive judgments. Participants viewed approaching objects using a virtual reality (VR) headset. In an active task, participants ducked before the object hit them. In a passive prediction-motion (PM) judgment, the approaching object disappeared, and participants pressed a button when they thought the object would hit them. In a passive relative TTC judgment, participants reported which of two approaching objects would reach them first. The SAE occurred with the PM and relative TTC tasks but not with the ducking task. The SAE can occur in immersive 3D environments but is limited by the nature of the task and display. Certain traffic situations may be more prone to the SAE and have higher risk for collisions. For example, in left-turn scenarios (e.g., see Levulis, 2018), drivers make passive judgments when oncoming vehicles are far and optical expansion is slow, and binocular disparity putatively is ineffective. Collision-avoidance warning systems may be needed more in such scenarios than when vehicles are near and drivers' judgments of TTC may be more accurate (DeLucia, 2008).

The large-scale variation issue in high-resolution aerial images significantly lowers the accuracy of segmenting small objects. For a deep-learning-based semantic segmentation model, the main reason is that the deeper layers generate high-level semantics over considerably large receptive fields, thus improving the accuracy for large objects but ignoring small objects. Although the low-level features extracted by shallow layers contain small-object information, large-object information has predominant effects. When the model, using low-level features, is trained, the large objects push the small objects aside. This observation motivates us to propose a novel reverse difference mechanism (RDM). The RDM eliminates the predominant effects of large objects and highlights small objects from low-level features. Based on the RDM, a novel semantic segmentation method called the reverse difference network (RDNet) is designed. In the RDNet, a detailed stream is proposed to produce small-object semantics by enhancing the output of RDM. A contextual stream for generating high-level semantics is designed by fully accumulating contextual information to ensure the accuracy of the segmentation of large objects. Both high-level and small-object semantics are concatenated when the RDNet performs predictions. Thus, both small- and large-object information is depicted well. Two semantic segmentation benchmarks containing vital small objects are used to fully evaluate the performance of the RDNet. Compared with existing methods that exhibit good performance in segmenting small objects, the RDNet has lower computational complexity and achieves 3.9–18.9% higher accuracy in segmenting small objects.

The development of forest and land cover classification methods was currently increasing rapidly, one of which is by utilizing remote sensing applications, namely UAV technology. One method with high accuracy that can be used to classify forest and land cover is the object-based image analysis (OBIA) classification method. There is an assumption that the results of orthophoto shooting will look the same at a glance, but each orthophoto result also has a different spatial resolution and affects the detail of each OBIA segmentation. This makes this research important to do how to classify forest and land cover in the Ghimbo Pomuan customary forest, Kenegerian Kampa, Kampar Riau at different flying heights of the UAV. This study aims to map forest and land cover classes based on the UAV flight height and analyze the UAV flight altitude on the resulting land cover classification. The method used is exploration and processing of UAV imagery. Starting with the preparation and determination of observation points, forest and land cover classification using the OBIA method at several UAV flight heights and data analysis. In the Ghimbo Pomuan customary forest area, several land cover classifications were produced using OBIA. The land cover classes include water bodies, forests, oil palm plantations and shrubs. Classification of land cover in the water body class has a tendency of under segmentation at UAV flight height of 120 m. Object details in the oil palm and shrub land cover class were higher at UAV flight heights of 100 m than at 120 m and 130 m, whereas in the forest class there was no difference.

This paper concerns the study of the seafloor through digital seabed elevation models, using object based image analysis methods. The goal of this research was the automated extraction of geomorphological features from the seabed in regions presenting intense volcanic activity. The study area is located around the submarine volcano of the Kolοumbo (in the submarine area northeast of the Santorini island, Greece). For this purpose, a Digital Elevation Model (DEM) of the seabed with a spatial resolution of 50m was used. Derivatives of the DEM, such us Slope, Topographic Position Index (TPI) and Terrain Ruggedness Index (TRI) were created in the open source software "QGIS 2.4". The implementation of the object based image analysis approach was performed in eCognition 8.7 software. Nine segmentation and classification levels were created in order to produce the final level segmentation "level 5", where the final geomorphological features were classified. The results of the method were evaluated using classification stability measures and qualitative and quantitative comparison of the results with existing map.

Forest inventory, monitoring, and assessment requires accurate tree species identification and mapping. Recent experiences with multispectral data from small fixed-wing and rotary blade unmanned aerial vehicles (UAVs) suggest a role for this technology in the emerging paradigm of enhanced forest inventory (EFI). In this paper, pixel-based and object-based image analysis (OBIA) methods were compared in UAV-based tree species classification of nine commercial tree species in mature eastern Ontario mixedwood forests. Unsupervised clustering and supervised classification of tree crown pixels yielded approximately 50%–60% classification accuracy overall; OBIA with image segmentation to delineate tree crowns and machine learning yielded up to 80% classification accuracy overall. Spectral response patterns and tree crown shape and geometric differences were interpreted in context of their ability to separate tree species of interest with these classification methods. Accuracy assessment was based on field-based forest inventory tree species identification. The paper provides a brief summary of future research issues that will influence the growth of this geomatics innovation in forest tree species classification and forest inventory.

With the development of remote sensing technology, remote sensing object detection has been widely applied in various fields, but it still faces some thorny challenges, such as the following: 1) the complexity of object scale changes in remote sensing images makes it difficult to improve the performance of small object detection and 2) remote sensing images have complex backgrounds and densely arranged small and weak objects, which pose a serious problem of feature interference. To alleviate these challenges, we propose an end-to-end adaptive feature separation network called AFSNet, which includes a scale-aware module (SAM) and a class-aware module (CAM). The SAM mainly enables feature maps of different resolutions to detect objects of different scales. Shallow feature maps mainly suppress the features of large objects they contain to focus on small object detection, while deep feature maps increase the detailed features of large objects they contain to focus on large object detection. The CAM is mainly used to distinguish the features in the feature map by category, separating the features of different categories into different channels, thus mitigating the problem of inter class feature interference, and blocking background interference. The effectiveness of this article has been proven on the NWPU VHR-10, IPIU-M, DIOR, and DOTA2.0 datasets. It can be widely applied in civilian, military, and other fields. Through experimental verification, our AFSNet achieved 97.70% mAP on the NWPU VHR-10 dataset, 78.9% mAP on the DIOR dataset, and 58.22% mAP on the DOTA2.0 dataset. Our code is available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Xidian-AIGroup190726/AFSNet</uri>.

The traditionally human-visual or manual interpretation is generally chosen method for spatial feature extraction on map producing process in Indonesia, although the pixel-based feature extraction is used in particular step. The main problem of human-visual method is the dependency to operator capacity. Subjectivity may occur because each operator has different ability. In early 20th century, the image segmentation method was still developing and now Geographic Object-based Image Analysis (GEOBIA) method is introduced to mapping process. Researchers are still developing and applying GEOBIA for many mapping purposes. The advantage of GEOBIA is object-based segmentation which contextually influenced by spatial feature characteristics. GEOBIA provides more meaningful information than traditional pixel-based image analysis by allowing less well-defined edges or borders between different classes. On the resulting maps, there are divisions between different types of object classification, for example where some species of mangroves meet are not generally represented by a single object. The developing of remotely sensed imagery data quality requires the developing of extraction method as well. This article discusses the implementation of GEOBIA for coastal mapping in Indonesia. Some research combined pixel-based and GEOBIA method, and some get the overall accuracy > 70% of GEOBIA method. By developing a new segmentation accuracy measure, we evaluated that segmentation accuracies decrease with increasing segmentation scales and the negative impact of under-segmentation errors become significantly rise at large scale. The use of GEOBIA for coastal mapping in Indonesia are still lacking, locally applicable and still developing the transferability rule sets. The conclusion is that the innovation is needed to make GEOBIA method applicable for mass production of Indonesian coastal map.