Segmentation-based Approaches Research Articles

LAWSUIT: a LArge expert-Written SUmmarization dataset of ITalian constitutional court verdicts

AbstractLarge-scale public datasets are vital for driving the progress of abstractive summarization, especially in law, where documents have highly specialized jargon. However, the available resources are English-centered, limiting research advancements in other languages. This paper introduces LAWSUIT, a collection of 14K Italian legal verdicts with expert-authored abstractive maxims drawn from the Constitutional Court of the Italian Republic. LAWSUIT presents an arduous task with lengthy source texts and evenly distributed salient content. We offer extensive experiments with sequence-to-sequence and segmentation-based approaches, revealing that the latter achieve better results in full and few-shot settings. We openly release LAWSUIT to foster the development and automation of real-world legal applications.

Intracranial aneurysm detection: an object detection perspective.

Intracranial aneurysm detection from 3D Time-Of-Flight Magnetic Resonance Angiography images is a problem of increasing clinical importance. Recently, a streak of methods have shown promising performance by using segmentation neural networks. However, these methods may be less relevant in a clinical settings where diagnostic decisions rely on detecting objects rather than their segmentation. We introduce a 3D single-stage object detection method tailored for small object detection such as aneurysms. Our anchor-free method incorporates fast data annotation, adapted data sampling and generation to address class imbalance problem, and spherical representations for improved detection. A comprehensive evaluation was conducted, comparing our method with the state-of-the-art SCPM-Net, nnDetection and nnUNet baselines, using two datasets comprising 402 subjects. The evaluation used adapted object detection metrics. Our method exhibited comparable or superior performance, with an average precision of 78.96%, sensitivity of 86.78%, and 0.53 false positives per case. Our method significantly reduces the detection complexity compared to existing methods and highlights the advantages of object detection over segmentation-based approaches for aneurysm detection. It also holds potential for application to other small object detection problems.

Fast and Efficient Root Phenotyping via Pose Estimation.

Image segmentation is commonly used to estimate the location and shape of plants and their external structures. Segmentation masks are then used to localize landmarks of interest and compute other geometric features that correspond to the plant's phenotype. Despite its prevalence, segmentation-based approaches are laborious (requiring extensive annotation to train) and error-prone (derived geometric features are sensitive to instance mask integrity). Here, we present a segmentation-free approach that leverages deep learning-based landmark detection and grouping, also known as pose estimation. We use a tool originally developed for animal motion capture called SLEAP (Social LEAP Estimates Animal Poses) to automate the detection of distinct morphological landmarks on plant roots. Using a gel cylinder imaging system across multiple species, we show that our approach can reliably and efficiently recover root system topology at high accuracy, few annotated samples, and faster speed than segmentation-based approaches. In order to make use of this landmark-based representation for root phenotyping, we developed a Python library (sleap-roots) for trait extraction directly comparable to existing segmentation-based analysis software. We show that pose-derived root traits are highly accurate and can be used for common downstream tasks including genotype classification and unsupervised trait mapping. Altogether, this work establishes the validity and advantages of pose estimation-based plant phenotyping. To facilitate adoption of this easy-to-use tool and to encourage further development, we make sleap-roots, all training data, models, and trait extraction code available at: https://github.com/talmolab/sleap-roots and https://osf.io/k7j9g/.

Kernel-mask knowledge distillation for efficient and accurate arbitrary-shaped text detection

Recently, segmentation-based approaches have been proposed to tackle arbitrary-shaped text detection. The trade-off between speed and accuracy is still a challenge that hinders its deployment in practical applications. Previous methods adopt complex pipelines to improve accuracy while ignoring inference speed. Moreover, the performance of most efficient scene text detectors often suffers from weak feature extraction when equipping lightweight networks. In this paper, we propose a novel distillation method for efficient and accurate arbitrary-shaped text detection, termed kernel-mask knowledge distillation. Our approach equips a low computational-cost visual transformer module (VTM) and a feature adaptation layer to make full use of feature-based and response-based knowledge in distillation. More specifically, first, the text features are obtained by aggregating the multi-level information extracted in the respective backbones of the teacher and student networks. Second, the text features are respectively sent to the VTM to enhance the feature representation ability. Then, we distill the feature-based and response-based kernel knowledge of the teacher network to obtain an efficient and accurate arbitrary-shaped text detection model. Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method. It is worth noting that our method can achieve a competitive F-measure of 86.92% at 34.5 FPS on Total-text. Code is available at https://github.com/giganticpower/KKDnet.

DAN: A Segmentation-Free Document Attention Network for Handwritten Document Recognition.

Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ 2016 dataset at page level, as well as double-page level with a CER of 3.43% and 3.70%, respectively. We also provide results for the RIMES 2009 dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN.

Abstract 5445: Segmentation-free analysis of multiplexed images with unbiased spatial analytics and explainable AI for predicting disease outcomes

Abstract Background: The spatial intratumor heterogeneity (ITH) is widely acknowledged as driving therapeutic response and providing fuel for drug resistance. Currently, patient selection for immunotherapy is driven mostly by PD-1/PD-L1 based IHC tests and mutational analysis. These oversimplified approaches fail to predict the risk of recurrence, therapeutic response and drug resistance with high accuracy. We hypothesize that functional responses of heterogeneous non-random spatial arrangements of tumor, stromal and immune cells in the tumor microenvironment are determined by distinct combinations of their internal states and spatial interactions within neighborhoods. The interactions generate distinct cell-cell communication networks forming functional spatial configurations of cells, termed microdomains, as organizational units of spatial ITH. Deriving the spatial networks within each microdomain with unbiased spatial analytics and the underlying network biology through explainable AI, is key to understanding tumor initiation, tumor progression, and response to therapy. Problem: There has been an explosion of spatial imaging technologies using immunofluorescence and/or mass spectrometry for intact tissues measuring protein expressions, DNA and RNA probes. To extract high-value knowledge from these multiplexed datasets, a key first step is to segment cells accurately. Despite decades of research, this step remains elusive due to imaging artifacts arising from issues with tile stitching, incorrect registration, signal oversaturation, non-uniform illumination, poor or high-background nuclei signal, defocus, varying cell and nuclear shapes, fluorescence emission efficiency variation, overlapping and/or superimposed nuclei and low resolution (e.g., mass cytometry). Those artifacts may lead to incorrect cell phenotypes, incomplete cell phenotype atlases, and missing rare cell, fusion cell or transition cell types. Solution: We present TumorMapr™, a segmentation-free, unbiased spatial analytics and explainable AI platform that extracts information and creates knowledge from patient disease pathology samples imaged with any technology including fluorescence, mass spectrometry etc. Results: We apply TumorMapr on hyperplexed immunofluorescence dataset of colorectal cancer and hyperplexed imaging mass cytometry dataset of triple negative breast cancer to discover functional cell prototypes involving spatial collections of neighboring pixels highly predictive of disease progression and response to therapy, tumor promoting and tumor restraining microdomains and microdomain-specific network biology predictive of disease outcomes. We further compare these results with segmentation-based approaches to showcase the discovery of novel cell prototypes. Citation Format: Filippo Pullara, Brian Falkenstein, Bruce Campbell, Samantha Panakkal, Akif Burak Tosun, Jeffrey Fine, S. Chakra Chennubhotla. Segmentation-free analysis of multiplexed images with unbiased spatial analytics and explainable AI for predicting disease outcomes. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5445.

ResAttn-recon: Residual self-attention based cortical surface reconstruction

Introduction: The accurate cerebral cortex surface reconstruction is crucial for the study of neurodegenerative diseases. Existing voxelwise segmentation-based approaches like FreeSurfer and FastSurfer are limited by the partial volume effect, meaning that reconstruction details highly rely on the resolution of the input volume. In the computer version area, the signed distance function has become an efficient method for 3D shape representation, the inherent continuous nature makes it easy to capture the fine details of the target object at an arbitrary resolution. Additionally, as one of the most valuable breakthroughs in deep learning research, attention is a powerful mechanism developed to enhance the performance of the encoder-decoder architecture.Methods: To further improve the reconstruction accuracy of the cortical surface, we proposed ResAttn-Recon, a residual self-attention based encoder-decoder framework. In this framework, we also developed a lightweight decoder network with skip connections. Furthermore, a truncated and weighted L1 loss function are proposed to accelerate network convergence, compared to simply applying the L1 loss function.Results: The intersection over union curve in the training process achieved a steeper slope and a higher peak (0.948 vs. 0.920) with a truncated L1 loss. Thus, the average symmetric surface distance (AD) for the inner and outer surfaces is 0.253 ± 0.051 and the average Hausdorff distance (HD) is 0.629 ± 0.186, which is lower than that of DeepCSR, whose absolute distance equals 0.283 ± 0.059 and Hausdorff distance equals 0.746 ± 0.245.Discussion: In conclusion, the proposed residual self-attention-based framework can be a promising approach for improving the cortical surface reconstruction performance.

Relational reasoning network for anatomical landmarking.

We perform anatomical landmarking for craniomaxillofacial (CMF) bones without explicitly segmenting them. Toward this, we propose a simple, yet efficient, deep network architecture, called relational reasoning network (RRN), to accurately learn the local and the global relations among the landmarks in CMF bones; specifically, mandible, maxilla, and nasal bones. The proposed RRN works in an end-to-end manner, utilizing learned relations of the landmarks based on dense-block units. For a given few landmarks as input, RRN treats the landmarking process similar to a data imputation problem where predicted landmarks are considered missing. We applied RRN to cone-beam computed tomography scans obtained from 250 patients. With a fourfold cross-validation technique, we obtained an average root mean squared error of per landmark. Our proposed RRN has revealed unique relationships among the landmarks that help us in inferring informativeness of the landmark points. The proposed system identifies the missing landmark locations accurately even when severe pathology or deformations are present in the bones. Accurately identifying anatomical landmarks is a crucial step in deformation analysis and surgical planning for CMF surgeries. Achieving this goal without the need for explicit bone segmentation addresses a major limitation of segmentation-based approaches, where segmentation failure (as often is the case in bones with severe pathology or deformation) could easily lead to incorrect landmarking. To the best of our knowledge, this is the first-of-its-kind algorithm finding anatomical relations of the objects using deep learning.

A framework for brain tumor detection based on segmentation and features fusion using MRI images

Irregular growth of cells in the skull is recognized as a brain tumor that can have two types such as benign and malignant. There exist various methods which are used by oncologists to assess the existence of brain tumors such as blood tests or visual assessments. Moreover, the noninvasive magnetic resonance imaging (MRI) technique without ionizing radiation has been commonly utilized for diagnosis. However, the segmentation in 3-dimensional MRI is time-consuming and the outcomes mainly depend on the operator’s experience. Therefore, a novel and robust automated brain tumor detector has been suggested based on segmentation and fusion of features. To improve the localization results, we pre-processed the images using Gaussian Filter (GF), and SynthStrip: a tool for brain skull stripping. We utilized two known benchmarks for training and testing i.e., Figshare and Harvard. The proposed methodology attained 99.8% accuracy, 99.3% recall, 99.4% precision, 99.5% F1 score, and 0.989 AUC. We performed the comparative analysis of our approach with prevailing DL, classical, and segmentation-based approaches. Additionally, we also performed the cross-validation using Harvard dataset attaining 99.3% identification accuracy. The outcomes exhibit that our approach offers significant outcomes than existing methods and outperforms them.

Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion.

Recently, segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field, because of their superiority in detecting the text instances of arbitrary shapes and extreme aspect ratios, profiting from the pixel-level descriptions. However, the vast majority of the existing segmentation-based approaches are limited to their complex post-processing algorithms and the scale robustness of their segmentation models, where the post-processing algorithms are not only isolated to the model optimization but also time-consuming and the scale robustness is usually strengthened by fusing multi-scale feature maps directly. In this paper, we propose a Differentiable Binarization (DB) module that integrates the binarization process, one of the most important steps in the post-processing procedure, into a segmentation network. Optimized along with the proposed DB module, the segmentation network can produce more accurate results, which enhances the accuracy of text detection with a simple pipeline. Furthermore, an efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively. By incorporating the proposed DB and ASF with the segmentation network, our proposed scene text detector consistently achieves state-of-the-art results, in terms of both detection accuracy and speed, on five standard benchmarks.

Computer vision for road imaging and pothole detection: a state-of-the-art review of systems and algorithms

Abstract Computer vision algorithms have been utilized for 3-D road imaging and pothole detection for over two decades. Nonetheless, there is a lack of systematic survey articles on state-of-the-art (SoTA) computer vision techniques, especially deep learning models, developed to tackle these problems. This article first introduces the sensing systems employed for 2-D and 3-D road data acquisition, including camera(s), laser scanners and Microsoft Kinect. It then comprehensively reviews the SoTA computer vision algorithms, including (1) classical 2-D image processing, (2) 3-D point cloud modelling and segmentation and (3) machine/deep learning, developed for road pothole detection. The article also discusses the existing challenges and future development trends of computer vision-based road pothole detection approaches: classical 2-D image processing-based and 3-D point cloud modelling and segmentation-based approaches have already become history; and convolutional neural networks (CNNs) have demonstrated compelling road pothole detection results and are promising to break the bottleneck with future advances in self/un-supervised learning for multi-modal semantic segmentation. We believe that this survey can serve as practical guidance for developing the next-generation road condition assessment systems.

SSAM-lite: A Light-Weight Web App for Rapid Analysis of Spatially Resolved Transcriptomics Data.

The combination of a cell’s transcriptional profile and location defines its function in a spatial context. Spatially resolved transcriptomics (SRT) has emerged as the assay of choice for characterizing cells in situ. SRT methods can resolve gene expression up to single-molecule resolution. A particular computational problem with single-molecule SRT methods is the correct aggregation of mRNA molecules into cells. Traditionally, aggregating mRNA molecules into cell-based features begins with the identification of cells via segmentation of the nucleus or the cell membrane. However, recently a number of cell-segmentation-free approaches have emerged. While these methods have been demonstrated to be more performant than segmentation-based approaches, they are still not easily accessible since they require specialized knowledge of programming languages and access to large computational resources. Here we present SSAM-lite, a tool that provides an easy-to-use graphical interface to perform rapid and segmentation-free cell-typing of SRT data in a web browser. SSAM-lite runs locally and does not require computational experts or specialized hardware. Analysis of a tissue slice of the mouse somatosensory cortex took less than a minute on a laptop with modest hardware. Parameters can interactively be optimized on small portions of the data before the entire tissue image is analyzed. A server version of SSAM-lite can be run completely offline using local infrastructure. Overall, SSAM-lite is portable, lightweight, and easy to use, thus enabling a broad audience to investigate and analyze single-molecule SRT data.

Segmentation-Based vs. Regression-Based Biomarker Estimation: A Case Study of Fetus Head Circumference Assessment from Ultrasound Images.

The fetus head circumference (HC) is a key biometric to monitor fetus growth during pregnancy, which is estimated from ultrasound (US) images. The standard approach to automatically measure the HC is to use a segmentation network to segment the skull, and then estimate the head contour length from the segmentation map via ellipse fitting, usually after post-processing. In this application, segmentation is just an intermediate step to the estimation of a parameter of interest. Another possibility is to estimate directly the HC with a regression network. Even if this type of segmentation-free approaches have been boosted with deep learning, it is not yet clear how well direct approach can compare to segmentation approaches, which are expected to be still more accurate. This observation motivates the present study, where we propose a fair, quantitative comparison of segmentation-based and segmentation-free (i.e., regression) approaches to estimate how far regression-based approaches stand from segmentation approaches. We experiment various convolutional neural networks (CNN) architectures and backbones for both segmentation and regression models and provide estimation results on the HC18 dataset, as well agreement analysis, to support our findings. We also investigate memory usage and computational efficiency to compare both types of approaches. The experimental results demonstrate that even if segmentation-based approaches deliver the most accurate results, regression CNN approaches are actually learning to find prominent features, leading to promising yet improvable HC estimation results.

RNGDet: Road Network Graph Detection by Transformer in Aerial Images

Road network graphs provide critical information for autonomous-vehicle applications, such as drivable areas that can be used for motion planning algorithms. To find road network graphs, manually annotation is usually inefficient and labor-intensive. Automatically detecting road network graphs could alleviate this issue, but existing works still have some limitations. For example, segmentation-based approaches could not ensure satisfactory topology correctness, and graph-based approaches could not present precise enough detection results. To provide a solution to these problems, we propose a novel approach based on transformer and imitation learning in this paper. In view of that high-resolution aerial images could be easily accessed all over the world nowadays, we make use of aerial images in our approach. Taken as input an aerial image, our approach iteratively generates road network graphs vertex-by-vertex. Our approach can handle complicated intersection points with various numbers of incident road segments. We evaluate our approach on a publicly available dataset. The superiority of our approach is demonstrated through the comparative experiments. Our work is accompanied with a demonstration video which is available at \url{https://tonyxuqaq.github.io/projects/RNGDet/}.

Machine learning and multi-sensor data fusion for mapping lithology: A case study of Kowli-kosh area, SW Iran

Lithological maps derived from traditional pixel-based image analysis are widely established in remote sensing. Recent development of new segmentation-based approaches such as object-based image analysis (OBIA) has led to significant improvements of accuracy in land cover classifications. However, additional enhancements have been reported by coupling OBIA with machine learning (ML) techniques. ML which automates computer algorithms and model building, enables learning, reasoning, and decision making through analysis and interpretation of data patterns and structures. This study is an attempt for evaluating and comparing the performances of four ML classifiers, including support vector machine (SVM), normal Bayes (NB), k-nearest neighbor (k-NN), and random forest (RF). This approach was tested with medium resolution imagery using an object-based classification procedure in a metamorphic complex, SW Iran. The multi-band input datasets were assembled form individual and multi-sensor layers from ASTER, Landsat 8 OLI, Sentinel-1 and Sentinel-2A. Results revealed that combined data sets obtain more reasonable classes for lithology, and combination of ASTER + simulated panchromatic of Sentinel-2A data shows the most efficient results. We also showed that, in general, RF and SVM algorithms were the most advantageous classifiers when using an object-based image analysis approach. When integrating the data sets aiming improvement of spatial resolution, the maximum accuracies of RF, SVM, k-NN and NB algorithms increased from 90% to 98%, 81% to 97%, 52 to 75%, and 40% to 64%, respectively. We also revealed that the integration of Sentinel-1 and Sentinel-2A data was promising and allowed for additional extraction of rock relief.

Segmentation-based analysis of single-cell immunoblots.

From genomics to transcriptomics to proteomics, microfluidic tools underpin recent advances in single-cell biology. Detection of specific proteoforms-with single-cell resolution-presents challenges in detection specificity and sensitivity. Miniaturization of protein immunoblots to single-cell resolution mitigates these challenges. For example, in microfluidic western blotting, protein targets are separated by electrophoresis and subsequently detected using fluorescently labeled antibody probes. To quantify the expression level of each protein target, the fluorescent protein bands are fit to Gaussians; yet, this method is difficult to use with noisy, low-abundance, or low-SNR protein bands, and with significant band skew or dispersion. In this study, we investigate segmentation-based approaches to robustly quantify protein bands from single-cell protein immunoblots. As compared to a Gaussian fitting pipeline, the segmentation pipeline detects >1.5×more protein bands for downstream quantification as well as more of the low-abundance protein bands (i.e., with SNR ∼3). Utilizing deep learning-based segmentation approaches increases the recovery of low-SNR protein bands by an additional 50%. However, we find that segmentation-based approaches are less robust at quantifying poorly resolved protein bands (separation resolution, Rs <0.6). With burgeoning needs for more single-cell protein analysis tools, we see microfluidic separations as benefitting substantially from segmentation-based analysis approaches.

Fabric Defect Detection Using Computer Vision Techniques: A Comprehensive Review

There are different applications of computer vision and digital image processing in various applied domains and automated production process. In textile industry, fabric defect detection is considered as a challenging task as the quality and the price of any textile product are dependent on the efficiency and effectiveness of the automatic defect detection. Previously, manual human efforts are applied in textile industry to detect the defects in the fabric production process. Lack of concentration, human fatigue, and time consumption are the main drawbacks associated with the manual fabric defect detection process. Applications based on computer vision and digital image processing can address the abovementioned limitations and drawbacks. Since the last two decades, various computer vision-based applications are proposed in various research articles to address these limitations. In this review article, we aim to present a detailed study about various computer vision-based approaches with application in textile industry to detect fabric defects. The proposed study presents a detailed overview of histogram-based approaches, color-based approaches, image segmentation-based approaches, frequency domain operations, texture-based defect detection, sparse feature-based operation, image morphology operations, and recent trends of deep learning. The performance evaluation criteria for automatic fabric defect detection is also presented and discussed. The drawbacks and limitations associated with the existing published research are discussed in detail, and possible future research directions are also mentioned. This research study provides comprehensive details about computer vision and digital image processing applications to detect different types of fabric defects.

Validation of a novel cardiac motion correction algorithm for x-ray computed tomography: From phantom experiments to initial clinical experience.

A novel cardiac motion correction algorithm has been introduced recently. Unlike other segmentation-based approaches it is fully automatic and capable of correcting motion artifacts of myocardial wall and other moving structures as well as coronary arteries of the heart. In addition, it requires raw data of only less than a single rotation for motion estimation and correction, which is a significant advantage from the perspective of x-ray exposure and workflow. The aim of this study is to explore the capability of the proposed method through phantoms and in-vivo experiments. Motion correction of coronary arteries and other heart structures including myocardial wall is the main focus of the evaluation. First, we provide a brief introduction to the concept of the motion correction algorithm. Next we address the procedure of our studies using an XCAT phantom and commercially available physical phantoms. Results of XCAT phantom demonstrate that our solution significantly improves the structural similarity of coronary arteries compared to FBP (proposed: 0.94, FBP: 0.77, p<0.001). Besides, it provides significantly lower root mean square error (proposed: 20.27, FBP: 25.33, p = 0.01) of the whole heart image. Mocomo phantom study shows that the proposed method improves the visualization of coronary arteries estimated based on motion score (1: worst, 5: best) from two experienced radiologists (proposed: 3.5, FBP: 2.1, p<0.001). The results of these phantom studies reveal that the proposed has a great potential in handling motion artifacts of other heart structures as well as coronary arteries. Finally, we provide the results of in-vivo animal and human studies. The 3D and 4D heart images show a consistently superior performance in the visualization of coronary arteries along with myocardial wall and other cardiothoracic structures. Based on these findings of our studies, we are of the opinion that our solution has a considerable potential to improve temporal resolution of cardiac CT imaging. This would open the door to innovations in structural or functional diagnosis of the heart.

Systematic Quantification of Synapses in Primary Neuronal Culture.

SummaryMost neurological disorders display impaired synaptic connectivity. Hence, modulation of synapse formation may have therapeutic relevance. However, the high density and small size of synapses complicate their quantification. To improve synapse-oriented screens, we analyzed the labeling performance of synapse-targeting antibodies on neuronal cell cultures using segmentation-independent image analysis based on sliding window correlation. When assessing pairwise colocalization, a common readout for mature synapses, overlap was incomplete and confounded by spurious signals. To circumvent this, we implemented a proximity ligation-based approach that only leads to a signal when two markers are sufficiently close. We applied this approach to different marker combinations and demonstrate its utility for detecting synapse density changes in healthy and compromised cultures. Thus, segmentation-independent analysis and exploitation of resident protein proximity increases the sensitivity of synapse quantifications in neuronal cultures and represents a valuable extension to the analytical toolset for in vitro synapse screens.

UAV-Based Structural Damage Mapping: A Review

Structural disaster damage detection and characterization is one of the oldest remote sensing challenges, and the utility of virtually every type of active and passive sensor deployed on various air- and spaceborne platforms has been assessed. The proliferation and growing sophistication of unmanned aerial vehicles (UAVs) in recent years has opened up many new opportunities for damage mapping, due to the high spatial resolution, the resulting stereo images and derivatives, and the flexibility of the platform. This study provides a comprehensive review of how UAV-based damage mapping has evolved from providing simple descriptive overviews of a disaster science, to more sophisticated texture and segmentation-based approaches, and finally to studies using advanced deep learning approaches, as well as multi-temporal and multi-perspective imagery to provide comprehensive damage descriptions. The paper further reviews studies on the utility of the developed mapping strategies and image processing pipelines for first responders, focusing especially on outcomes of two recent European research projects, RECONASS (Reconstruction and Recovery Planning: Rapid and Continuously Updated Construction Damage, and Related Needs Assessment) and INACHUS (Technological and Methodological Solutions for Integrated Wide Area Situation Awareness and Survivor Localization to Support Search and Rescue Teams). Finally, recent and emerging developments are reviewed, such as recent improvements in machine learning, increasing mapping autonomy, damage mapping in interior, GPS-denied environments, the utility of UAVs for infrastructure mapping and maintenance, as well as the emergence of UAVs with robotic abilities.