Multiscale Image Segmentation Research Articles

TPAFNet: Transformer-Driven Pyramid Attention Fusion Network for 3D Medical Image Segmentation.

The field of 3D medical image segmentation is witnessing a growing trend in the utilization of combined networks that integrate convolutional neural networks and transformers. Nevertheless, prevailing hybrid networks are confronted with limitations in their straightforward serial or parallel combination methods and lack an effective mechanism to fuse channel and spatial feature attention. To address these limitations, we present a robust multi-scale 3D medical image segmentation network, the Transformer-Driven Pyramid Attention Fusion Network, which is denoted as TPAFNet, leveraging a hybrid structure of CNN and transformer. Within this framework, we exploit the characteristics of atrous convolution to extract multi-scale information effectively, thereby enhancing the encoding results of the transformer. Furthermore, we introduce the TPAF block in the encoder to seamlessly fuse channel and spatial feature attention from multi-scale feature inputs. In contrast to conventional skip connections that simply concatenate or add features, our decoder is enriched with a TPAF connection, elevating the integration of feature attention between low-level and high-level features. Additionally, we propose a low-level encoding shortcut from the original input to the decoder output, preserving more original image features and contributing to enhanced results. Finally, the deep supervision is implemented using a novel CNN-based voxel-wise classifier to facilitate better network convergence. Experimental results demonstrate that TPAFNet significantly outperforms other state-of-the-art networks on two public datasets, indicating that our research can effectively improve the accuracy of medical image segmentation, thereby assisting doctors in making more precise diagnoses.

A Study on the Object-Based High-Resolution Remote Sensing Image Classification of Crop Planting Structures in the Loess Plateau of Eastern Gansu Province

The timely and accurate acquisition of information on the distribution of the crop planting structure in the Loess Plateau of eastern Gansu Province, one of the most important agricultural areas in Western China, is crucial for promoting fine management of agriculture and ensuring food security. This study uses multi-temporal high-resolution remote sensing images to determine optimal segmentation scales for various crops, employing the estimation of scale parameter 2 (ESP2) tool and the Ratio of Mean Absolute Deviation to Standard Deviation (RMAS) model. The Canny edge detection algorithm is then applied for multi-scale image segmentation. By incorporating crop phenological factors and using the L1-regularized logistic regression model, we optimized 39 spatial feature factors—including spectral, textural, geometric, and index features. Within a multi-level classification framework, the Random Forest (RF) classifier and Convolutional Neural Network (CNN) model are used to classify the cropping patterns in four test areas based on the multi-scale segmented images. The results indicate that integrating the Canny edge detection algorithm with the optimal segmentation scales calculated using the ESP2 tool and RMAS model produces crop parcels with more complete boundaries and better separability. Additionally, optimizing spatial features using the L1-regularized logistic regression model, combined with phenological information, enhances classification accuracy. Within the OBIC framework, the RF classifier achieves higher accuracy in classifying cropping patterns. The overall classification accuracies for the four test areas are 91.93%, 94.92%, 89.37%, and 90.68%, respectively. This paper introduced crop phenological factors, effectively improving the extraction precision of the shattered agricultural planting structure in the Loess Plateau of eastern Gansu Province. Its findings have important application value in crop monitoring, management, food security and other related fields.

Multi-scale medical image segmentation based on pixel encoding and spatial attention mechanism

In response to the issues of single-scale information loss and large model parameter size during the sampling process in U-Net and its variants for medical image segmentation, this paper proposes a multi-scale medical image segmentation method based on pixel encoding and spatial attention. Firstly, by redesigning the input strategy of the Transformer structure, a pixel encoding module is introduced to enable the model to extract global semantic information from multi-scale image features, obtaining richer feature information. Additionally, deformable convolutions are incorporated into the Transformer module to accelerate convergence speed and improve module performance. Secondly, a spatial attention module with residual connections is introduced to allow the model to focus on the foreground information of the fused feature maps. Finally, through ablation experiments, the network is lightweighted to enhance segmentation accuracy and accelerate model convergence. The proposed algorithm achieves satisfactory results on the Synapse dataset, an official public dataset for multi-organ segmentation provided by the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), with Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) scores of 77.65 and 18.34, respectively. The experimental results demonstrate that the proposed algorithm can enhance multi-organ segmentation performance, potentially filling the gap in multi-scale medical image segmentation algorithms, and providing assistance for professional physicians in diagnosis.

GMAlignNet: multi-scale lightweight brain tumor image segmentation with enhanced semantic information consistency

Although the U-shaped architecture, represented by UNet, has become a major network model for brain tumor segmentation, the repeated convolution and sampling operations can easily lead to the loss of crucial information. Additionally, directly fusing features from different levels without distinction can easily result in feature misalignment, affecting segmentation accuracy. On the other hand, traditional convolutional blocks used for feature extraction cannot capture the abundant multi-scale information present in brain tumor images. This paper proposes a multi-scale feature-aligned segmentation model called GMAlignNet that fully utilizes Ghost convolution to solve these problems. Ghost hierarchical decoupled fusion unit and Ghost hierarchical decoupled unit are used instead of standard convolutions in the encoding and decoding paths. This transformation replaces the holistic learning of volume structures by traditional convolutional blocks with multi-level learning on a specific view, facilitating the acquisition of abundant multi-scale contextual information through low-cost operations. Furthermore, a feature alignment unit is proposed that can utilize semantic information flow to guide the recovery of upsampled features. It performs pixel-level semantic information correction on misaligned features due to feature fusion. The proposed method is also employed to optimize three classic networks, namely DMFNet, HDCNet, and 3D UNet, demonstrating its effectiveness in automatic brain tumor segmentation. The proposed network model was applied to the BraTS 2018 dataset, and the results indicate that the proposed GMAlignNet achieved Dice coefficients of 81.65%, 90.07%, and 85.16% for enhancing tumor, whole tumor, and tumor core segmentation, respectively. Moreover, with only 0.29 M parameters and 26.88G FLOPs, it demonstrates better potential in terms of computational efficiency and possesses the advantages of lightweight. Extensive experiments on the BraTS 2018, BraTS 2019, and BraTS 2020 datasets suggest that the proposed model exhibits better potential in handling edge details and contour recognition.

MSA-UNet: A Multiscale Lightweight U-Net Lung CT Image Segmentation Algorithm Under Attention Mechanism

Automatic and precise segmentation of lung images can assist doctors in locating and diagnosing lung lesions. However, current traditional lung CT image lesion segmentation algorithms suffer from the problem of low segmentation accuracy, while deep learning-based segmentation algorithms struggle to strike a better balance between lightweight and high accuracy. In response to this issue, a multi-scale and lightweight U-Net lung image segmentation algorithm with an attention mechanism is proposed. This algorithm introduces CA convolution after the convolution in the encoding stage to extract channel relationships and positional information from the feature maps. Furthermore, the RFB module is employed to extract features from different perspectives. Lastly, upward residual connections are introduced between the RFB modules in the encoder and decoder to enhance inter-network information interaction. Experiments conducted on the LUNA (lung nodule analysis) dataset and the COVID-QU-Ex dataset for COVID-19 pneumonia demonstrate that the proposed MSA-UNet algorithm achieves the best results in terms of Precision and Dice metrics. It outperforms mainstream models such as U-Net++ and DeeplabV3+ in terms of segmentation effectiveness and segmentation generality. The model has a floating-point operation count (FLOPs) of 18.15 G, a network parameter counts of 8.83×106, and achieves a Precision of 99.37%. The algorithm achieves a good balance between computational efficiency, model size, and segmentation accuracy.

Transformer guided self-adaptive network for multi-scale skin lesion image segmentation

BackgroundIn recent years, skin lesion has become a major public health concern, and the diagnosis and management of skin lesions depend heavily on the correct segmentation of the lesions. Traditional convolutional neural networks (CNNs) have demonstrated promising results in skin lesion segmentation, but they are limited in their ability to capture distant connections and intricate features. In addition, current medical image segmentation algorithms rarely consider the distribution of different categories in different regions of the image and do not consider the spatial relationship between pixels. ObjectivesThis study proposes a self-adaptive position-aware skin lesion segmentation model SapFormer to capture global context and fine-grained detail, better capture spatial relationships, and adapt to different positional characteristics. The SapFormer is a multi-scale dynamic position-aware structure designed to provide a more flexible representation of the relationships between skin lesion characteristics and lesion distribution. Additionally, it increases skin lesion segmentation accuracy and decreases incorrect segmentation of non-lesion areas. InnovationsSapFormer designs multiple hybrid transformers for multi-scale feature encoding of skin images and multi-scale positional feature sensing of the encoded features using a transformer decoder to obtain fine-grained features of the lesion area and optimize the regional feature distribution. The self-adaptive feature framework, built upon the transformer decoder module, dynamically and automatically generates parameterizations with learnable properties at different positions. These parameterizations are derived from the multi-scale encoding characteristics of the input image. Simultaneously, this paper utilizes the cross-attention network to optimize the features of the current region according to the features of other regions, aiming to increase skin lesion segmentation accuracy. Main resultsThe ISIC-2016, ISIC-2017, and ISIC-2018 datasets for skin lesions are used as the basis for the experiment. On these datasets, the proposed model has accuracy values of 97.9 %, 94.3 %, and 95.7 %, respectively. The proposed model's IOU values are, in order, 93.2 %, 86.4 %, and 89.4 %. The proposed model's DSC values are 96.4 %, 92.6 %, and 94.3 %, respectively. All three metrics surpass the performance of the majority of state-of-the-art (SOTA) models. SapFormer's metrics on these datasets demonstrate that it can precisely segment skin lesions. Notably, our approach exhibits remarkable noise resistance in non-lesion areas, while simultaneously conducting finer-grained regional feature extraction on the skin lesion image. ConclusionsIn conclusion, the integration of a transformer-guided position-aware network into semantic skin lesion segmentation results in a notable performance boost. The ability of our proposed network to capture spatial relationships and fine-grained details proves beneficial for effective skin lesion segmentation. By enhancing lesion localization, feature extraction, quantitative analysis, and classification accuracy, the proposed segmentation model improves the diagnostic efficiency of skin lesion analysis on dermoscopic images. It assists dermatologists in making more accurate and efficient diagnoses, ultimately leading to better patient care and outcomes. This research paves the way for advances in diagnosing and treating skin lesions, promoting better understanding and decision-making in the clinical setting.

A Multi-Scale Cross-Fusion Medical Image Segmentation Network Based on Dual-Attention Mechanism Transformer

The U-net network, with its simple and powerful encoder–decoder structure, dominates the field of medical image segmentation. However, convolution operations are limited by receptive fields. They do not have the ability to model long-range dependencies, but Transformer has the capability of long-term modeling thanks to its core self-attention mechanism, which has been widely applied in the field of medical image segmentation. However, both CNNs and Transformer can only perform correlation calculations for a single sample, ignoring the correlation between different samples. To address these problems, we propose a new Transformer, which we call the Dual-Attention Transformer (DAT). This module captures correlations within a single sample while also learning correlations between different samples. The current U-net and some of its variant models have the problem of inadequate feature fusion, so we also improve the skip connection to strengthen the association between feature maps at different scales, reduce the semantic gap between the encoder and decoder, and further improve the segmentation performance. We refer to this structure as DATUnet. We conducted extensive experiments on the Synapse and ACDC datasets to validate the superior performance of our network, and we achieved an average DSC (%) of 83.6 and 90.9 and an average HD95 of 13.99 and 1.466 for the Synapse and ACDC datasets, respectively.

Omni-Seg: A Scale-Aware Dynamic Network for Renal Pathological Image Segmentation.

Comprehensive semantic segmentation on renal pathological images is challenging due to the heterogeneous scales of the objects. For example, on a whole slide image (WSI), the cross-sectional areas of glomeruli can be 64 times larger than that of the peritubular capillaries, making it impractical to segment both objects on the same patch, at the same scale. To handle this scaling issue, prior studies have typically trained multiple segmentation networks in order to match the optimal pixel resolution of heterogeneous tissue types. This multi-network solution is resource-intensive and fails to model the spatial relationship between tissue types. In this article, we propose the Omni-Seg network, a scale-aware dynamic neural network that achieves multi-object (six tissue types) and multi-scale (5× to 40× scale) pathological image segmentation via a single neural network. The contribution of this article is three-fold: (1) a novel scale-aware controller is proposed to generalize the dynamic neural network from single-scale to multi-scale; (2) semi-supervised consistency regularization of pseudo-labels is introduced to model the inter-scale correlation of unannotated tissue types into a single end-to-end learning paradigm; and (3) superior scale-aware generalization is evidenced by directly applying a model trained on human kidney images to mouse kidney images, without retraining. By learning from 150,000 human pathological image patches from six tissue types at three different resolutions, our approach achieved superior segmentation performance according to human visual assessment and evaluation of image-omics (i.e., spatial transcriptomics).

MMS-Net: Multi-level multi-scale feature extraction network for medical image segmentation

Automatic segmentation of medical images can provide a reliable basis for clinical analysis and disease diagnosis. Due to the varying sizes and appearances of different pathological lesions, most convolutional neural networks (CNNs) approaches are unable to fully extract multi-scale features and usually lead to false positive and false negative segmentation. Multi-scale medical image segmentation still faces significant challenges. By designing different levels of skip connection modules (SCMs), local multi-scale context is proposed. We also adopted feature pyramid network (FPN) to connect SCMs to extract global multi-scale features. Local multi-scale context and global multi-scale feature constitute a multi-level multi-scale feature extraction network (MMS-Net). Multi-level multi-scale feature was extracted and accurate spatial information was also retained. Comprehensive experiments (training vs. testing: 8:2) on five public datasets show that the proposed MMS-Net achieved accurate segmentation and outperformed the state-of-the-art algorithms. Besides, when only using 50% and 20% of the training dataset, MMS-Net still obtained competitive segmentation results.

Multi-scale image depth fusion method based on superpixel-level convolutional neural network

In order to improve the image quality, reduce the image noise and improve the image definition, the image depth fusion processing is realized by using the sp CNN network (Super pixel level convolution neural network, sp CNN). The improved non-local mean method is used to de-noise the image to highlight the role of the center pixel of the image block; the de-noised image is segmented by the improved CV model (Chan-Vese, CV), and the globally optimal multi-scale image segmentation result is obtained after optimization; From the perspective of regional features, the similarity measurement of image regions is carried out to realize image preprocessing. The sp-CNN network is constructed, and with the help of the idea of pyramid pooling, the average pooling is used to extract the features of each layer from the global and local levels of the convolutional features, and the training data set is generated for training, thereby realizing multi-scale image fusion. The experimental results show that the optimal value of the root mean square error index of the proposed method is 0.58. The optimal value of structural similarity index is 41.22. On the average slope index, the optimal value is 21.39. The optimal value of cross entropy index is 2.21. This shows that the proposed method has high image definition and good visual effect, which verifies the effectiveness of the method.

Object-based multiscale segmentation incorporating texture and edge features of high-resolution remote sensing images.

Multiscale segmentation (MSS) is crucial in object-based image analysis methods (OBIA). How to describe the underlying features of remote sensing images and combine multiple features for object-based multiscale image segmentation is a hotspot in the field of OBIA. Traditional object-based segmentation methods mostly use spectral and shape features of remote sensing images and pay less attention to texture and edge features. We analyze traditional image segmentation methods and object-based MSS methods. Then, on the basis of comparing image texture feature description methods, a method for remote sensing image texture feature description based on time-frequency analysis is proposed. In addition, a method for measuring the texture heterogeneity of image objects is constructed on this basis. Using bottom-up region merging as an MSS strategy, an object-based MSS algorithm for remote sensing images combined with texture feature is proposed. Finally, based on the edge feature of remote sensing images, a description method of remote sensing image edge intensity and an edge fusion cost criterion are proposed. Combined with the heterogeneity criterion, an object-based MSS algorithm combining spectral, shape, texture, and edge features is proposed. Experiment results show that the comprehensive features object-based MSS algorithm proposed in this article can obtain more complete segmentation objects when segmenting ground objects with rich texture information and slender shapes and is not prone to over-segmentation. Compare with the traditional object-based segmentation algorithm, the average accuracy of the algorithm is increased by 4.54%, and the region ratio is close to 1, which will be more conducive to the subsequent processing and analysis of remote sensing images. In addition, the object-based MSS algorithm proposed in this article can effectively obtain more complete ground objects and can be widely used in scenes such as building extraction.

Enhancing the Thermal Images of the Upper Scarp of the Poggio Baldi Landslide (Italy) by Physical Modeling and Image Analysis

We present new methods for physical interpretation and mathematical treatment of the imaging contrast observed in thermal images of the rocky upper scarp of the Poggio Baldi landslide (Italy), which is part of a natural laboratory. Exemplar thermal images have been acquired with a high-performance camera at a distance of around 500 m, in a geometry where reflection is expected to dominate over thermal emission. The digital pixel intensities have therefore been considered as wavelength-integrated infrared spectral reflectance, irrespective of the temperature scale loaded into the camera software. Sub-portions of the scarp producing a lower signal have been identified by a multiscale image segmentation algorithm and overlaid on the visible image to provide an interpretation for the different thermal imaging contrast mechanisms that may be exploited for landslide monitoring in the future.

Research on Image Classification and Key Technologies Based on 3D Feature Extraction Algorithm

Image classification and recognition has a very wide range of applications in computer vision, which involves many fields, such as image retrieval, image analysis, and robot positioning. Especially with the rise of brain science and cognitive science research, as well as the increasing diversification of imaging means, three-dimensional image data mainly based on magnetic resonance image plays an increasingly important role in image classification and recognition, especially in medical image classification and recognition. However, due to the high dimensional characteristics of human magnetic resonance images, human readability is reduced. Therefore, classification and recognition of 3-dimensional images is still a challenge. In order to better extract local features from images and effectively use their spatial information, this paper improved the “feature bag” and “spatial pyramid matching” algorithms on the basis of 3D feature extraction algorithm and proposed an image classification framework based on 3D feature extraction algorithm. Firstly, the multiresolution “3D spatial pyramid” algorithm, the multiscale image segmentation and image representation method, and the SVM classifier and feature fusion method are described. Secondly, the gender information contained in the magnetic resonance images is classified and recognized on the three databases selected in the experiment. Experimental results show that this method can effectively utilize the spatial information of three-dimensional images and achieve satisfactory results in the classification and recognition of human magnetic resonance images.

Multi-scale organs image segmentation method improved by squeeze-and-attention based on partially supervised learning

Radiotherapy is one of most treatments for tumors. To accurately control the radiation dose distribution and lessen the radiation damage to normal tissues and organs in radiotherapy, it is essential to delineate organs at risk (OARs) precisely. However, manual delineating and some traditional methods are labor-intensive and time-consuming. There is an urgent need for fast and precise segmentation methods in radiotherapy. This paper proposes a fully automatic segmentation method based on the 3D U-Net for multi-organ in head and neck. It introduces squeeze-and-attention blocks to gather multi-scale context information and the receptive field block to balance the performance between large-sized and small-sized organs. Furthermore, it is trained by the marginal and exclusion loss function in a partially supervised learning mode. We evaluated the model with dice similarity coefficient (DSC), 95% Hausdorff distance (95HD) and inference time. Its average DSC is 0.829, which is 4.5%, 3.2%, and 2.4% higher than AnatomyNet's, nnU-net's, and FocusNet's, respectively, and its average 95HD is 2.19. Moreover, its inference time and parameters are 63% and 60% less than FocusNetv2's. For the segmentation of OARs in head and neck, our model is more accurate than AnatomyNet, faster than FocusNetv2, and better balances between segmentation accuracy and inference time. It demonstrates that our method is more applicable for clinical treatment.

Ancient mural segmentation based on a deep separable convolution network

Traditional methods for ancient mural segmentation have drawbacks, including fuzzy target boundaries and low efficiency. Targeting these problems, this study proposes a pyramid scene parsing MobileNetV2 network (PSP-M) by fusing a deep separable convolution-based lightweight neural network with a multiscale image segmentation model. In this model, deep separable convolution-fused MobileNetV2, as the backbone network, is embedded in the image segmentation model, PSPNet. The pyramid scene parsing structure, particularly owned by the two models, is used to process the background features of images, which aims to reduce feature loss and to improve the efficiency of image feature extraction. In the meantime, atrous convolution is utilized to expand the perceptive field, aiming to ensure the integrity of image semantic information without changing the number of parameters. Compared with traditional image segmentation models, PSP-M increases the average training accuracy by 2%, increases the peak signal-to-noise ratio by 1–2 dB and improves the structural similarity index by 0.1–0.2.

Integrating Sentinel-1/2 Data and Machine Learning to Map Cotton Fields in Northern Xinjiang, China

Timely and accurate information of cotton planting areas is essential for monitoring and managing cotton fields. However, there is no large-scale and high-resolution method suitable for mapping cotton fields, and the problems associated with low resolution and poor timeliness need to be solved. Here, we proposed a new framework for mapping cotton fields based on Sentinel-1/2 data for different phenological periods, random forest classifiers, and the multi-scale image segmentation method. A cotton field map for 2019 at a spatial resolution of 10 m was generated for northern Xinjiang, a dominant cotton planting region in China. The overall accuracy and kappa coefficient of the map were 0.932 and 0.813, respectively. The results showed that the boll opening stage was the best phenological phase for mapping cotton fields and the cotton fields was identified most accurately at the early boll opening stage, about 40 days before harvest. Additionally, Sentinel-1 and the red edge bands in Sentinel-2 are important for cotton field mapping, and there is great potential for the fusion of optical images and microwave images in crop mapping. This study provides an effective approach for high-resolution and high-accuracy cotton field mapping, which is vital for sustainable monitoring and management of cotton planting.

Crack Detection on Concrete Surfaces Using Deep Encoder-Decoder Convolutional Neural Network: A Comparison Study Between U-Net and DeepLabV3+

Maintenance of infrastructures is a crucial activity to ensure safety using crack detection methods on concrete structures. However, most practice of crack detection is carried out manually, which is unsafe, highly subjective, and time-consuming. Therefore, a more accurate and efficient system needs to be implemented using artificial intelligence. Convolutional neural network (CNN), a subset of artificial intelligence, is used to detect cracks on concrete surfaces through semantic image segmentation. The purpose of this research is to compare the effectiveness of cutting-edge encoder-decoder architectures in detecting cracks on concrete surfaces using U-Net and DeepLabV3+ architectures with potential in biomedical, and sparse multiscale image segmentations, respectively. Neural networks were trained using cloud computing with a high-performance Graphics Processing Unit NVIDIA Tesla V100 and 27.4 GB of RAM. This study used internal and external data. Internal data consisted of simple cracks and were used as the training and validation data. Meanwhile, external data consisted of more complex cracks, which were used for further testing. Both architectures were compared based on four evaluation metrics in terms of accuracy, F1, precision, and recall. U-Net achieved segmentation accuracy = 96.57%, F1 = 87.55%, precision = 88.15%, and recall = 88.94%, while DeepLabV3+ achieved segmentation accuracy = 96.47%, F1 = 85.29%, precision = 92.07%, and recall = 81.84%. Experiment results (internal and external data) indicated that both architectures were accurate and effective in segmenting cracks. Additionally, U-Net and DeepLabV3+ exceeded the performance of previously tested architecture, namely FCN.

Extraction of metamorphic minerals by multiscale segmentation combined with random forest

The identification of metamorphic minerals is the basis of metamorphic rock research. Extraction of mineral information by remote sensing technology has been widely used. Digital image processing technology is also effectively applied to remote sensing image processing. Results show that the band ratio of remote sensing images can enhance mineral information, while the variogram function can describe the spatial correlation and variability of image pixels and extract more detailed texture information. The metamorphic minerals are found to present a block or strip distribution. The object-oriented remote sensing image information extraction method can avoid the salt and pepper phenomenon based on pixel extraction. Meanwhile, the random forest classification method has a fast calculation speed and high parameter accuracy. It is not sensitive to the noise caused by more lithologic components and its classification effect is found to be stable. To improve the extraction accuracy of metamorphic minerals from remote sensing images and further improve the recognition effect of metamorphic zones, this paper combined the ratio operation, multiscale segmentation, and random forest classification to extract metamorphic mineral information from ASTER images in Beishan area in Gansu Province. Initially, the image was enhanced by the ratio formula of the characteristic spectral structure of the target mineral. Multiscale image segmentation was then performed based on the spectrum and variogram. Finally, the accuracy was evaluated by the thin film identification results of the field exploration samples after the extraction of the target mineral by random forest. Results show that biotite, muscovite, and amphibole have identification characteristics on the ASTER image with an extraction accuracy of 85.4088%, 84.7640%, and 85.7308%, respectively. The extraction accuracy of other metamorphic minerals with less content are found to reach more than 60%. Multiscale segmentation can make full use of the clustering features of minerals and the variogram texture can enhance the ability of morphological features to distinguish the minerals. Random forest is not sensitive to noise and the extraction results are observed to be stable.

Object-based approach for urban land cover mapping using high spatial resolution data

This paper deals with object-oriented image analysis applied for an urban area. Very high-resolution images in conjunction with object-oriented image analysis have been used for land cover detection. Using the eCognition software with object-oriented methods, not only the spectral information but also the shape, compactness and other parameters can be used to extract meaningful objects. The spectral and geometric diversity of urban surfaces is a very complex research issue. It is the main reason why additional information is needed to improve the outcome of classification. The most consistent and relevant characteristic of buildings is their height. Therefore, elevation data (converted from LIDAR data) are used for building extraction, segmentation and classification. The study deals with the problem, how to determine the most appropriate parameters of segmentation, feature extraction and classification methods. The data extraction includes two phases, the first part consists the following steps: data pre-processing, rule set development, multi-scale image segmentation, the definition of features used to map land use, classification based on rule set and accuracy evaluation. The second part of the data process based on classical raster analysis GIS tools like focal and zonal function.

Object-Scale Adaptive Convolutional Neural Networks for High-Spatial Resolution Remote Sensing Image Classification

Object-based image analysis (OBIA) is regarded as an effective technology for high-spatial resolution (HSR) image classification due to its clear and intuitive technical process. However, OBIA depends on the manual tuning of image classification features, which is a tricky job. Deep learning (DL) technology autolearns image features from massive images and obtains higher image classification accuracy than traditional techniques. In this article, a novel method called object-scale adaptive convolutional neural network (OSA-CNN), which combines OBIA with CNN, is proposed for HSR image classification. First, OSA-CNN collects the image patches along the main axes of the object primitives obtained through image segmentation; the size of the former is automatically determined through the axis widths of the latter. This step generates the input units required for the CNN classification. Second, the Squeeze-and-Excitation block is extracted from the SE network into the network structure of GoogleNet, which realizes the weighted fusion of the multiscale convolutional features, enhances useful features, and suppresses useless ones. In the classification stage, multiscale image segmentation and CNN classification are fused using an object-scale adaptive mechanism. Finally, object primitives are classified through majority voting on the image patches. The network structure modifications, multiscale classification fusion, and other improvements are verified by gradually incorporating these steps into the original GoogleNet. The experiments show that these improvements effectively enhance the image classification accuracy. This article presents an effective way of combining OBIA and DL techniques to utilize the advantages of both approaches and facilitate HSR image classification.