Image Segmentation Approach Research Articles

Deep-Learning-Based Approaches for Semantic Segmentation of Natural Scene Images: A Review

The task of semantic segmentation holds a fundamental position in the field of computer vision. Assigning a semantic label to each pixel in an image is a challenging task. In recent times, significant advancements have been achieved in the field of semantic segmentation through the application of Convolutional Neural Networks (CNN) techniques based on deep learning. This paper presents a comprehensive and structured analysis of approximately 150 methods of semantic segmentation based on CNN within the last decade. Moreover, it examines 15 well-known datasets in the semantic segmentation field. These datasets consist of 2D and 3D image and video frames, including general, indoor, outdoor, and street scenes. Furthermore, this paper mentions several recent techniques, such as SAM, UDA, and common post-processing algorithms, such as CRF and MRF. Additionally, this paper analyzes the performance evaluation of reviewed state-of-the-art methods, pioneering methods, common backbone networks, and popular datasets. These have been compared according to the results of Mean Intersection over Union (MIoU), the most popular evaluation metric of semantic segmentation. Finally, it discusses the main challenges and possible solutions and underlines some future research directions in the semantic segmentation task. We hope that our survey article will be useful to provide a foreknowledge to the readers who will work in this field.

Unsupervised Cross-modality Adaptation via Dual Structural-Oriented Guidance for 3D Medical Image Segmentation.

Deep convolutional neural networks (CNNs) have achieved impressive performance in medical image segmentation; however, their performance could degrade significantly when being deployed to unseen data with heterogeneous characteristics. Unsupervised domain adaptation (UDA) is a promising solution to tackle this problem. In this work, we present a novel UDA method, named dual adaptation-guiding network (DAG-Net), which incorporates two highly effective and complementary structural-oriented guidance in training to collaboratively adapt a segmentation model from a labelled source domain to an unlabeled target domain. Specifically, our DAG-Net consists of two core modules: 1) Fourier-based contrastive style augmentation (FCSA) which implicitly guides the segmentation network to focus on learning modality-insensitive and structural-relevant features, and 2) residual space alignment (RSA) which provides explicit guidance to enhance the geometric continuity of the prediction in the target modality based on a 3D prior of inter-slice correlation. We have extensively evaluated our method with cardiac substructure and abdominal multi-organ segmentation for bidirectional cross-modality adaptation between MRI and CT images. Experimental results on two different tasks demonstrate that our DAG-Net greatly outperforms the state-of-the-art UDA approaches for 3D medical image segmentation on unlabeled target images.

Giza pyramids construction algorithm with gradient contour approach for multilevel thresholding color image segmentation

Giza pyramids construction algorithm with gradient contour approach for multilevel thresholding color image segmentation

Review of Image Augmentation Used in Deep Learning-Based Material Microscopic Image Segmentation

The deep learning-based image segmentation approach has evolved into the mainstream of target detection and shape characterization in microscopic image analysis. However, the accuracy and generalizability of deep learning approaches are still hindered by the insufficient data problem that results from the high expense of human and material resources for microscopic image acquisition and annotation. Generally, image augmentation can increase the amount of data in a short time by means of mathematical simulation, and has become a necessary module for deep learning-based material microscopic image analysis. In this work, we first review the commonly used image augmentation methods and divide more than 60 basic image augmentation methods into eleven categories based on different implementation strategies. Secondly, we conduct experiments to verify the effectiveness of various basic image augmentation methods for the image segmentation task of two classical material microscopic images using evaluation metrics with different applicabilities. The U-Net model was selected as a representative benchmark model for image segmentation tasks, as it is the classic and most widely used model in this field. We utilize this model to verify the improvement of segmentation performance by various augmentation methods. Then, we discuss the advantages and applicability of various image augmentation methods in the material microscopic image segmentation task. The evaluation experiments and conclusions in this work can serve as a guide for the creation of intelligent modeling frameworks in the materials industry.

Generalization of the shortest path approach for superpixel segmentation of omnidirectional images

With the growing use of image capture devices using wide angles and the need for fast and accurate image analysis in computer vision, there is a demand for dedicated under-representation methods. Most decomposition methods segment an image into a small number of irregular homogeneous regions, called superpixels. Nevertheless, these approaches are generally designed to process natural 2D planar images, i.e., captured with a 90o angle view without distortion. In this work, we present SphSPS, a new general decomposition method (for Spherical Shortest Path-based Superpixels)11Available code at: https://github.com/rgiraud/sphsps, that is dedicated to wide 360o omnidirectional or spherical images. The produced superpixels respect both the geometry of the 3D spherical acquisition space, and the boundaries of image objects. To fastly extract relevant clustering features, we generalize the shortest path approach between a pixel and a superpixel center. We demonstrate that considering the geometry of the acquisition space to compute the shortest path enables to jointly improve the segmentation accuracy and the shape regularity of superpixels. To evaluate this regularity property, we propose a generalization of a standard 2D regularity metric to the spherical space, addressing the limitations of the only existing spherical compactness measure. Finally, SphSPS is validated on reference 360o images from the PSD (Panorama Segmentation Dataset) and also on synthetic road omnidirectional images. Our method significantly outperforms both planar and spherical state-of-the-art approaches in terms of segmentation accuracy, robustness to noise and regularity, providing a very interesting tool for superpixel-based applications on 360o images.

Regional perception and multi-scale feature fusion network for cardiac segmentation

Objective. Cardiovascular disease (CVD) is a group of diseases affecting cardiac and blood vessels, and short-axis cardiac magnetic resonance (CMR) images are considered the gold standard for the diagnosis and assessment of CVD. In CMR images, accurate segmentation of cardiac structures (e.g. left ventricle) assists in the parametric quantification of cardiac function. However, the dynamic beating of the heart renders the location of the heart with respect to other tissues difficult to resolve, and the myocardium and its surrounding tissues are similar in grayscale. This makes it challenging to accurately segment the cardiac images. Our goal is to develop a more accurate CMR image segmentation approach. Approach. In this study, we propose a regional perception and multi-scale feature fusion network (RMFNet) for CMR image segmentation. We design two regional perception modules, a window selection transformer (WST) module and a grid extraction transformer (GET) module. The WST module introduces a window selection block to adaptively select the window of interest to perceive information, and a windowed transformer block to enhance global information extraction within each feature window. The WST module enhances the network performance by improving the window of interest. The GET module grids the feature maps to decrease the redundant information in the feature maps and enhances the extraction of latent feature information of the network. The RMFNet further introduces a novel multi-scale feature extraction module to improve the ability to retain detailed information. Main results. The RMFNet is validated with experiments on three cardiac data sets. The results show that the RMFNet outperforms other advanced methods in overall performance. The RMFNet is further validated for generalizability on a multi-organ data set. The results also show that the RMFNet surpasses other comparison methods. Significance. Accurate medical image segmentation can reduce the stress of radiologists and play an important role in image-guided clinical procedures.

Four-dimensional reconstruction and characterization of bladder deformations

Background and ObjectivePelvic floor disorders are prevalent diseases and patient care remains difficult as the dynamics of the pelvic floor remains poorly understood. So far, only 2D dynamic observations of straining exercises at excretion are available in the clinics and 3D mechanical defects of pelvic organs are not well studied. In this context, we propose a complete methodology for the 3D representation of non-reversible bladder deformations during exercises, combined with a 3D representation of the location of the highest strain areas on the organ surface. MethodsNovel image segmentation and registration approaches have been combined with three geometrical configurations of up-to-date rapid dynamic multi-slice MRI acquisitions for the reconstruction of real-time dynamic bladder volumes. ResultsFor the first time, we proposed real-time 3D deformation fields of the bladder under strain from in-bore forced breathing exercises. The potential of our method was assessed on eight control subjects undergoing forced breathing exercises. We obtained average volume deviations of the reconstructed dynamic volume of bladders around 2.5% and high registration accuracy with mean distance values of 0.4 ± 0.3 mm and Hausdorff distance values of 2.2 ± 1.1 mm. ConclusionsThe proposed framework provides proper 3D+t spatial tracking of non-reversible bladder deformations. This has immediate applicability in clinical settings for a better understanding of pelvic organ prolapse pathophysiology. This work can be extended to patients with cavity filling or excretion problems to better characterize the severity of pelvic floor pathologies or to be used for preoperative surgical planning.

An efficient memory reserving-and-fading strategy for vector quantization based 3D brain segmentation and tumor extraction using an unsupervised deep learning network.

Deep learning networks are state-of-the-art approaches for 3D brain image segmentation, and the radiological characteristics extracted from tumors are of great significance for clinical diagnosis, treatment planning, and treatment outcome evaluation. However, two problems have been the hindering factors in brain image segmentation techniques. One is that deep learning networks require large amounts of manually annotated data. Another issue is the computational efficiency of 3D deep learning networks. In this study, we propose a vector quantization (VQ)-based 3D segmentation method that employs a novel unsupervised 3D deep embedding clustering (3D-DEC) network and an efficiency memory reserving-and-fading strategy. The VQ-based 3D-DEC network is trained on volume data in an unsupervised manner to avoid manual data annotation. The memory reserving-and-fading strategy beefs up model efficiency greatly. The designed methodology makes deep learning-based model feasible for biomedical image segmentation. The experiment is divided into two parts. First, we extensively evaluate the effectiveness and robustness of the proposed model on two authoritative MRI brain tumor databases (i.e., IBSR and BrainWeb). Second, we validate the model using real 3D brain tumor data collected from our institute for clinical practice significance. Results show that our method (without data manual annotation) has superior accuracy ( Tanimoto coefficient on IBSR, 97.5% TP and 97.7% TN on BrainWeb, and 91% Dice, 88% sensitivity and 87% specificity on real brain data) and remarkable efficiency (speedup ratio is 18.72 on IBSR, 31.16 on BrainWeb, 31.00 on real brain data) compared to the state-of-the-art methods. The results show that our proposed model can address the lacks of manual annotations, and greatly increase computation speedup with competitive segmentation accuracy compared to other state-of-the-art 3D CNN models. Moreover, the proposed model can be used for tumor treatment follow-ups every 6months, providing critical details for surgical and postoperative treatment by correctly extracting numerical radiomic features of tumors.

A novel medical image segmentation approach by using multi-branch segmentation network based on local and global information synchronous learning

In recent years, there have been several solutions to medical image segmentation, such as U-shaped structure, transformer-based network, and multi-scale feature learning method. However, their network parameters and real-time performance are often neglected and cannot segment boundary regions well. The main reason is that such networks have deep encoders, a large number of channels, and excessive attention to local information rather than global information, which is crucial to the accuracy of image segmentation. Therefore, we propose a novel multi-branch medical image segmentation network MBSNet. We first design two branches using a parallel residual mixer (PRM) module and dilate convolution block to capture the local and global information of the image. At the same time, a SE-Block and a new spatial attention module enhance the output features. Considering the different output features of the two branches, we adopt a cross-fusion method to effectively combine and complement the features between different layers. MBSNet was tested on five datasets ISIC2018, Kvasir, BUSI, COVID-19, and LGG. The combined results show that MBSNet is lighter, faster, and more accurate. Specifically, for a 320 times 320 input, MBSNet’s FLOPs is 10.68G, with an F1-Score of 85.29% on the Kvasir test dataset, well above 78.73% for UNet++ with FLOPs of 216.55G. We also use the multi-criteria decision making method TOPSIS based on F1-Score, IOU and Geometric-Mean (G-mean) for overall analysis. The proposed MBSNet model performs better than other competitive methods. Code is available at https://github.com/YuLionel/MBSNet.

3D reconstruction of the cerebellar germinal layer reveals tunneling connections between developing granule cells.

The difficulty of retrieving high-resolution, in vivo evidence of the proliferative and migratory processes occurring in neural germinal zones has limited our understanding of neurodevelopmental mechanisms. Here, we used a connectomic approach using a high-resolution, serial-sectioning scanning electron microscopy volume to investigate the laminar cytoarchitecture of the transient external granular layer (EGL) of the developing cerebellum, where granule cells coordinate a series of mitotic and migratory events. By integrating image segmentation, three-dimensional reconstruction, and deep-learning approaches, we found and characterized anatomically complex intercellular connections bridging pairs of cerebellar granule cells throughout the EGL. Connected cells were either mitotic, migratory, or transitioning between these two cell stages, displaying a chronological continuum of proliferative and migratory events never previously observed in vivo at this resolution. This unprecedented ultrastructural characterization poses intriguing hypotheses about intercellular connectivity between developing progenitors and its possible role in the development of the central nervous system.

Multi-Point-Source Describing Large Earthquake Based on Rupture Process Inversion and Image Segmentation

The rupture process of large earthquakes is generally complex and contains multiple sub-faults planes with different focal mechanisms. The focal mechanisms inversion of these sub-faults by applying the Multi-Point-Source Faulting Representations (MPSFR) are essential for seismic stress analysis and earthquake disaster assessment. The MPSFR method is time-consuming and often with unstable results. In this study, we develop an Image Segmentation and Iterative Inversion (ISII) approach to calculate the MPSFR for large earthquakes by inverting near-field strong motion data. This new approach analyzes the rupture image of the earthquake and divides the entire rupture surface into several sub-rupture segments as a point source in the MPSFR. We approach the ISII model to the 2010 El-Mayor Cucapah (EMC) earthquake and the 2016 Kaikoura earthquake, respectively. In the EMC earthquake, the overall misfit was reduced from 0.58 (earthquake rupture model with the same focal mechanism) to 0.47 (IISI model with four different focal mechanisms). In the Kaikoura earthquake, the overall misfit was reduced from 0.67 to 0.55. The rupture process inverted by the ISII model is consistent with the joint multi-method inversion and the operation process is high efficiency. The test results indicate the ISII model can accurately and quickly invert the complex earthquakes rupture process and provide valuable information for earthquake disaster assessment.

DBCU-Net: deep learning approach for segmentation of coronary angiography images.

Coronary angiography (CAG) is the "gold standard" for diagnosing coronary artery disease (CAD). However, due to the limitation of current imaging methods, the CAG image has low resolution and poor contrast with a lot of artifacts and noise, which makes it difficult for blood vessels segmentation. In this paper, we propose a DBCU-Net for automatic segmentation of CAG images, which is an extension of U-Net, DenseNet with bi-directional ConvLSTM(BConvLSTM). The main contribution of our network is that instead of convolution in the feature extraction of U-Net, we incorporate dense connectivity and the bi-directional ConvLSTM to highlight salient features. We conduct our experiment on our private dataset, and achieve average Accuracy, Precision, Recall and F1-score for coronary artery segmentation of 0.985, 0.913, 0.847 and 0.879 respectively.

Multi-threshold image segmentation based on an improved differential evolution: Case study of thyroid papillary carcinoma

The scholarly world has demonstrated an immense enthusiasm for medical image segmentation due to its intricate nature and critical role in medical diagnosis and treatment systems. Multi-threshold image segmentation (MTIS) is a popular technique for this purpose, due to its simplicity and straightforwardness. This paper presents an improved Differential Evolution (DE) algorithm called AGDE, which is based on MTIS and was used to evaluate its high capability at IEEE CEC 2017. Comparisons with classical and advanced algorithms were conducted as part of the experiments. An AGDE-based multi-threshold image segmentation method utilizing a non-local mean 2D histogram in combination with Rényi's entropy was applied to segment images from the Berkeley Segmentation Datasets 500 (BSDS500) and microscopic images of thyroid papillary carcinoma (TPC). The experimental results showed that the proposed image segmentation method outperformed its competitors, making it a promising approach for medical image segmentation.

Efficient Approach to Color Image Segmentation Based on Multilevel Thresholding Using EMO Algorithm by Considering Spatial Contextual Information.

The process of image segmentation is partitioning an image into its constituent parts and is a significant approach for extracting interesting features from images. Over a couple of decades, many efficient image segmentation approaches have been formulated for various applications. Still, it is a challenging and complex issue, especially for color image segmentation. To moderate this difficulty, a novel multilevel thresholding approach is proposed in this paper based on the electromagnetism optimization (EMO) technique with an energy curve, named multilevel thresholding based on EMO and energy curve (MTEMOE). To compute the optimized threshold values, Otsu's variance and Kapur's entropy are deployed as fitness functions; both values should be maximized to locate optimal threshold values. In both Kapur's and Otsu's methods, the pixels of an image are classified into different classes based on the threshold level selected on the histogram. Optimal threshold levels give higher efficiency of segmentation; the EMO technique is used to find optimal thresholds in this research. The methods based on an image's histograms do not possess the spatial contextual information for finding the optimal threshold levels. To abolish this deficiency an energy curve is used instead of the histogram and this curve can establish the spatial relationship of pixels with their neighbor pixels. To study the experimental results of the proposed scheme, several color benchmark images are considered at various threshold levels and compared with other meta-heuristic algorithms: multi-verse optimization, whale optimization algorithm, and so on. The investigational results are illustrated in terms of mean square error, peak signal-to-noise ratio, the mean value of fitness reach, feature similarity, structural similarity, variation of information, and probability rand index. The results reveal that the proposed MTEMOE approach overtops other state-of-the-art algorithms to solve engineering problems in various fields.

Hybrid Multilevel Thresholding Image Segmentation Approach for Brain MRI.

A brain tumor is an abnormal growth of tissues inside the skull that can interfere with the normal functioning of the neurological system and the body, and it is responsible for the deaths of many individuals every year. Magnetic Resonance Imaging (MRI) techniques are widely used for detection of brain cancers. Segmentation of brain MRI is a foundational process with numerous clinical applications in neurology, including quantitative analysis, operational planning, and functional imaging. The segmentation process classifies the pixel values of the image into different groups based on the intensity levels of the pixels and a selected threshold value. The quality of the medical image segmentation extensively depends on the method which selects the threshold values of the image for the segmentation process. The traditional multilevel thresholding methods are computationally expensive since these methods thoroughly search for the best threshold values to maximize the accuracy of the segmentation process. Metaheuristic optimization algorithms are widely used for solving such problems. However, these algorithms suffer from the problem of local optima stagnation and slow convergence speed. In this work, the original Bald Eagle Search (BES) algorithm problems are resolved in the proposed Dynamic Opposite Bald Eagle Search (DOBES) algorithm by employing Dynamic Opposition Learning (DOL) at the initial, as well as exploitation, phases. Using the DOBES algorithm, a hybrid multilevel thresholding image segmentation approach has been developed for MRI image segmentation. The hybrid approach is divided into two phases. In the first phase, the proposed DOBES optimization algorithm is used for the multilevel thresholding. After the selection of the thresholds for the image segmentation, the morphological operations have been utilized in the second phase to remove the unwanted area present in the segmented image. The performance efficiency of the proposed DOBES based multilevel thresholding algorithm with respect to BES has been verified using the five benchmark images. The proposed DOBES based multilevel thresholding algorithm attains higher Peak Signal-to-Noise ratio (PSNR) and Structured Similarity Index Measure (SSIM) value in comparison to the BES algorithm for the benchmark images. Additionally, the proposed hybrid multilevel thresholding segmentation approach has been compared with the existing segmentation algorithms to validate its significance. The results show that the proposed algorithm performs better for tumor segmentation in MRI images as the SSIM value attained using the proposed hybrid segmentation approach is nearer to 1 when compared with ground truth images.

IU-Net: a hybrid structured network with a novel feature fusion approach for medical image segmentation

In recent years, convolutional neural networks (CNNs) have made great achievements in the field of medical image segmentation, especially full convolutional neural networks based on U-shaped structures and skip connections. However, limited by the inherent limitations of convolution, CNNs-based methods usually exhibit limitations in modeling long-range dependencies and are unable to extract large amounts of global contextual information, which deprives neural networks of the ability to adapt to different visual modalities. In this paper, we propose our own model, which is called iU-Net bacause its structure closely resembles the combination of i and U. iU-Net is a multiple encoder-decoder structure combining Swin Transformer and CNN. We use a hierarchical Swin Transformer structure with shifted windows as the primary encoder and convolution as the secondary encoder to complement the context information extracted by the primary encoder. To sufficiently fuse the feature information extracted from multiple encoders, we design a feature fusion module (W-FFM) based on wave function representation. Besides, a three branch up sampling method(Tri-Upsample) has developed to replace the patch expand in the Swin Transformer, which can effectively avoid the Checkerboard Artifacts caused by the patch expand. On the skin lesion region segmentation task, the segmentation performance of iU-Net is optimal, with Dice and Iou reaching 90.12% and 83.06%, respectively. To verify the generalization of iU-Net, we used the model trained on ISIC2018 dataset to test on PH2 dataset, and achieved 93.80% Dice and 88.74% IoU. On the lung feild segmentation task, the iU-Net achieved optimal results on IoU and Precision, reaching 98.54% and 94.35% respectively. Extensive experiments demonstrate the segmentation performance and generalization ability of iU-Net.

Is the fluid volume fraction equal to the water content in tendons? Insights on biphasic modeling

The mass density of highly hydrated soft tissues is generally assumed to be very close to that of the water, resulting that the fluid mass fraction (water content) being equal to the fluid volume fraction. Within this context, the present study aims to investigate whether such an assumption actually holds for tendon tissues and to what extent it may affect the constitutive characterizations based on biphasic (poroelastic) models. Once the water content was assessed by a classical drying assay, the fluid volume fraction was obtained based on an image segmentation approach. The main achieved results point out that the fluid volume fraction is ∼20% higher than the water content in the studied tendons (flexor digitorum profundus bovine tendons). Based on this, it is shown that the use of the water content instead of the fluid volume fraction may considerably bias the results drawn by biphasic modeling of tendons. Accordingly, a proper measurement of the fluid volume fraction is then required.

A new soil-plant image segmentation approach using K-means applied to experimental plots

The image segmentation procedure is fundamental in the phenotyping of plant images. Supervised algorithms have been used for pixel soil plant segmentation. Recent research has used the K-means algorithm to evaluate the segmentation of agronomic images in different crops with different databases. The algorithm has shown good performance in the pixel clustering process despite not being able to classify them directly. The present research intends to propose the use of the K-means algorithm in image segmentation and pixel classification in sugarcane images. 37,430-pixel samples referring to soil and vegetation were manually extracted from some images. This information was used to train and evaluate supervised models. The model with the best performance was considered the "standard" model. A rule that can serve as empirical support to interpret the clusters formed by K-means by assigning a label to each pixel was proposed. Then K-means was used to segment all images and classify the pixels. The vegetation index was used as features and the standard model classification was used as a true label. The measures recall, F1Score, precision, and accuracy were used as a performance measure of K-means, and the mask of each produced to compare the final result of the two approaches, highlighting the vegetation. Using K-means provided better-defined edges than Logistic Regression (standard model) and considerably distinguished the occurrence of soil between the leaves, with precision ranging from 0.77 to 0.92. These results expressed the importance of vegetation index to the clusterization process and showed that K-means ally to an interpretation clusters rule, which could be used to classify pixels in images.

Acute lymphoblastic leukemia image segmentation based on modified HSV model

Image segmentation is a critical step in computer-aided diagnosis that could speed up Leukemia detection. Leukemia is a cancer of the blood that has a reputation for being particularly lethal. Based on the immunohistochemical method, the leukocytes can be manually counted in a stained peripheral blood smear image to detect Acute Lymphoblastic Leukemia (ALL). Regrettably, the manual diagnosis process takes about 3 to 24 hours to complete, which is insufficient. This paper introduced a new and straightforward ALL image segmentation approach based on color image transformation. First, Leukemia, ALL-IDB1, ALL-IDB2, and ALL image datasets were used in this paper. The Leukemia dataset includes 208 ALL-IDB1 and ALL-IDB2 images, while The ALL dataset has 3256 images. Next, we use the HSV model to transform ALL images. In addition, we modified the HSV model by pre-processing the saturation channel for better results. Then, the pre-processed images were segmented based on a fixed threshold. After that, various metrics are utilized to measure the output of the proposed method. Finally, the proposed methodology is compared to currently used benchmarks. The proposed method outperforms previous approaches regarding accuracy, specificity, sensitivity, and time. In addition, results show that the proposed technique improves performance measures significantly.

Coastal Dune Invaders: Integrative Mapping of Carpobrotus sp. pl. (Aizoaceae) Using UAVs

Coastal dune ecosystems are highly threatened, and one of the strongest pressures is invasive alien plants (IAPs). Mitigating the negative effects of IAPs requires development of optimal identification and mapping protocols. Remote sensing offers innovative tools that have proven to be very valuable for studying IAPs. In particular, unmanned aerial vehicles (UAVs) can be very promising, especially in the study of herbaceous invasive species, yet research in UAV application is still limited. In this study, we used UAV images to implement an image segmentation approach followed by machine learning classification for mapping a dune clonal invader (Carpobrotus sp. pl.), calibrating a total of 27 models. Our study showed that: (a) the results offered by simultaneous RGB and multispectral data improve the prediction of Carpobrotus; (b) the best results were obtained by mapping the whole plant or its vegetative parts, while mapping flowers was worse; and (c) a training area corresponding to 20% of the total area can be adequate for model building. Overall, our results highlighted the great potential of using UAVs for Carpobrotus mapping, despite some limitations imposed by the particular biology and ecology of these taxa.