George Vosselman

University of Twente | UT · Department of Earth Observation Science (EOS)

Interactive image segmentation enables users to interact minimally with a machine, facilitating the gradual refinement of the segmentation mask for a target of interest. Previous studies have demonstrated impressive performance in extracting a single target mask through interactive segmentation. However, the information cues of previously interacte...

Autonomous navigation of drones using computer vision has achieved promising performance. Nano-sized drones based on edge computing platforms are lightweight, flexible, and cheap; thus, they are suitable for exploring narrow spaces. However, due to their extremely limited computing power and storage, vision algorithms designed for high-performance...

Scene recognition is a fundamental task in 3D scene understanding. It answers the question ‘What is this place?’. In an indoor environment, the answer can be an office, kitchen, lobby, and so on. As the number of point clouds increases, using embedded point information in scene recognition becomes computationally heavy to process. To achieve comput...

Geometric errors in LoD2 building models can be caused by the modeling algorithm but are often related to the quality of input data. One approach to tackling the modeling errors caused by the quality of input data is to collect additional data with a UAV and remodel the buildings. However, no flight planning approach exists specifically designed fo...

The ability of robots to autonomously navigate through 3D environments depends on their comprehension of spatial concepts, ranging from low-level geometry to high-level semantics, such as objects, places, and buildings. To enable such comprehension, 3D scene graphs have emerged as a robust tool for representing the environment as a layered graph of...

3D building generation with low data acquisition costs, such as single image-to-3D, becomes increasingly important. However, most of the existing single image-to-3D building creation works are restricted to those images with specific viewing angles, hence they are difficult to scale to general-view images that commonly appear in practical cases. To...

The ability of robots to autonomously navigate through 3D environments depends on their comprehension of spatial concepts, ranging from low-level geometry to high-level semantics, such as objects, places, and buildings. To enable such comprehension, 3D scene graphs have emerged as a robust tool for representing the environment as a layered graph of...

Interactive image segmentation aims to segment the target from the background with the manual guidance, which takes as input multimodal data such as images, clicks, scribbles, and bounding boxes. Recently, vision transformers have achieved a great success in several downstream visual tasks, and a few efforts have been made to bring this powerful ar...

Self-supervised monocular depth estimation that does not require ground truth for training has attracted attention in recent years. It is of high interest to design lightweight but effective models so that they can be deployed on edge devices. Many existing architectures benefit from using heavier backbones at the expense of model sizes. This paper...

Autonomous navigation of drones using computer vision has achieved promising performance. Nano-sized drones based on edge computing platforms are lightweight, flexible, and cheap, thus suitable for exploring narrow spaces. However, due to their extremely limited computing power and storage, vision algorithms designed for high-performance GPU platfo...

Visual question answering (VQA) is an important and challenging multimodal task in computer vision. Recently, a few efforts have been made to bring VQA task to aerial images, due to its potential real-world applications in disaster monitoring, urban planning, and digital earth product generation. However, not only the huge variation in the appearan...

Semantic segmentation has recently emerged as a prominent area of interest in Earth Observation. Several semantic segmentation datasets already exist, facilitating comparisons among different methods in complex urban scenes. However, most open high-resolution urban datasets are geographically skewed towards Europe and North America, while coverage...

Self-supervised monocular depth estimation that does not require ground-truth for training has attracted attention in recent years. It is of high interest to design lightweight but effective models, so that they can be deployed on edge devices. Many existing architectures benefit from using heavier backbones at the expense of model sizes. In this p...

Generating a 3D point cloud from a single 2D image is of great importance for 3D scene understanding applications. To reconstruct the whole 3D shape of the object shown in the image, the existing deep learning based approaches use either explicit or implicit generative modeling of point clouds, which, however, suffer from limited quality. In this w...

In this paper, we present an improved framework for the instance-aware semantic segmentation of road furniture in mobile laser scanning data. In our framework, we first detect road furniture from mobile laser scanning point clouds. Then we decompose the detected pieces of road furniture into poles and their attached components, and extract the inst...

Consumer-grade Unmanned Aerial Vehicles (UAVs) are poorly suited to monitor complex scenes where multiple analysis tasks need to be carried out in real-time and in parallel to fulfil time-critical requirements. Therefore, we developed an innovative UAV agnostic system that is able to carry out multiple road infrastructure monitoring tasks simultane...

Human detection in images using deep learning has been a popular research topic in recent years and has achieved remarkable performance. Training a human detection network is useful for first responders to search for trapped victims in debris after a disaster. In this paper, we focus on the detection of such victims using deep learning, and we find...

Deep detection networks trained with a large amount of annotated data achieve high accuracy in detecting various objects, such as pedestrians, cars, lanes, etc. These models have been deployed and used in many scenarios. A disaster victim detector is very useful when searching for victims who are partially buried by debris caused by earthquake or b...

The performance of deep learning models in semantic segmentation is dependent on the availability of a large amount of labeled data. However, the influence of label noise, in the form of incorrect annotations, on the performance is significant and mostly ignored. This is a big concern in remote sensing applications, wherein acquired datasets are sp...

While modern deep learning algorithms for semantic segmentation of airborne laser scanning (ALS) point clouds have achieved considerable success, the training process often requires a large number of labelled 3D points. Pointwise annotation of 3D point clouds, especially for large scale ALS datasets, is extremely time-consuming work. Weak supervisi...

Semantic segmentation using convolutional neural networks (CNNs) achieves higher accuracy than traditional methods, but it fails to yield satisfactory results under illumination variants when the training set is limited. In this paper we present a new data set containing both real and rendered images and a novel cascade network to study semantic se...

Simultaneous localization and mapping (SLAM) is the essential technique in mapping environments that are denied to the global navigation satellite systems (GNSSs), such as indoor spaces. In this article, we present a loop-closing continuous-time LIDAR-IMU SLAM for indoor environments. The design of the proposed SLAM is based on arbitrarily-oriented...

Semantic segmentation models are often affected by illumination changes, and fail to predict correct labels. Although there has been a lot of research on indoor semantic segmentation, it has not been studied in low-light environments. In this paper we propose a new framework, LISU, for Low-light Indoor Scene Understanding. We first decompose the lo...

Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation. Most of the semantic segmentation research focused on scenes captured in nadir view, in which objects have relatively smaller scale variation compared with scenes captured in oblique view. The huge scale variation of object...

Forest managers and nature conservationists rely on precise mapping of single trees from remote sensing data for efficient estimation of forest attributes. In recent years, additional quantification of dead wood in particular has garnered interest. However, tree-level approaches utilizing segmented single trees are still limited in accuracy and the...

Video object detection is a fundamental research task for scene understanding. Compared with object detection in images, object detection in videos has been less researched due to shortage of labelled video datasets. As frames in a video clip are highly correlated, a larger quantity of video labels are needed to have good data variation, which are...

Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and land use maps. In this paper, we present a local and global encoder network (LGENet) for semantic segmentation of ALS point clouds. Adapting the KPConv network, we first...

Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation. Most of the semantic segmentation research focused on scenes captured in nadir view, in which objects have relatively smaller scale variation compared with scenes captured in oblique view. The huge scale variation of object...

Multipath effects and signal obstruction by buildings in urban canyons can lead to inaccurate GNSS measurements and therefore errors in the estimated trajectory of Mobile Laser Scanning (MLS) systems; consequently, derived point clouds are distorted and lose spatial consistency. We obtain decimetre-level trajectory accuracy making use of correspond...

We present an unsupervised deep learning approach for post-disaster building damage detection that can transfer to different typologies of damage or geographical locations. Previous advances in this direction were limited by insufficient qualitative training data. We propose to use a state-of-the-art Anomaly Detecting Generative Adversarial Network...

Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and land use maps. In this paper, we present a local and global encoder network (LGENet) for semantic segmentation of ALS point clouds. Adapting the KPConv network, we first...

Supervised training of a deep neural network for semantic segmentation of point clouds requires a large amount of labelled data. Nowadays, it is easy to acquire a huge number of points with high density in large-scale areas using current LiDAR and photogrammetric techniques. However it is extremely time-consuming to manually label point clouds for...

Indoor 3D models are digital representations of building interiors reconstructed from scanned data acquired by laser scanners, digital depth (RGBD) cameras, and CAD drawings. Consequently, there is noise in the source data and a notable variety in the methods used to treat the noise and to process these data into reconstructed models. Alas, the cor...

The severe accident at the Chornobyl Nuclear Power Plant (ChNPP) in 1986 resulted in extraordinary contamination of the surrounding territory, which necessitated the creation of the Chornobyl Exclusion Zone (ChEZ). During the accident, liquidation materials contaminated by radioactive fallout (e.g., contaminated soil and trees) were buried in so-ca...

Knowledge of tree species mapping and of dead wood in particular is fundamental to managing our forests. Although individual tree-based approaches using lidar can successfully distinguish between deciduous and coniferous trees, the classification of multiple tree species is still limited in accuracy. Moreover, the combined mapping of standing dead...

Degradation and damage detection provides essential information to maintenance workers in routine monitoring and to first responders in post-disaster scenarios. Despite advance in Earth Observation (EO), image analysis and deep learning techniques, the quality and quantity of training data for deep learning is still limited. As a result, no robust...

With the development of LiDAR and photogrammetric techniques, more and more point clouds are available with high density and in large areas. Point cloud interpretation is an important step before many real applications like 3D city modelling. Many supervised machine learning techniques have been adapted to semantic point cloud segmentation, aiming...

In recent years, the importance of indoor mapping increased in a wide range of applications, such as facility management and mapping hazardous sites. The essential technique behind indoor mapping is simultaneous localization and mapping (SLAM) because SLAM offers suitable positioning estimates in environments where satellite positioning is not avai...

In-situ slum upgrading projects include infrastructural improvements such as new roads, which are perceived to improve the quality of life for the residents and encourage structural improvements at a household level. Although these physical changes are easily visible in satellite imagery, it is more difficult to track incremental improvements under...

Semantic segmentation has been one of the leading research interests in computer vision recently. It serves as a perception foundation for many fields, such as robotics and autonomous driving. The fast development of semantic segmentation attributes enormously to the large scale datasets, especially for the deep learning related methods. There alre...

Remote sensing images have long been recognized as useful for the detection of building damages, mainly due to their wide coverage, revisit capabilities and high spatial resolution. The majority of contributions aimed at identifying debris and rubble piles, as the main focus is to assess collapsed and partially collapsed structures. However, these...

Video object detection targets to simultaneously localize the bounding boxes of the objects and identify their classes in a given video. One challenge for video object detection is to consistently detect all objects across the whole video. As the appearance of objects may deteriorate in some frames, features or detections from the other frames are...

There exists a demand for effective land administration systems that can support the protection of unrecorded land rights, thereby assisting to reduce poverty and support national development—in alignment with target 1.4 of UN Sustainable Development Goals (SDGs). It is estimated that only 30% of the world’s population has documented land rights re...

Indoor mapping techniques are highly important in many applications, such as human navigation and indoor modelling. As satellite positioning systems do not work in indoor applications, several alternative navigational sensors and methods have been used to provide accurate indoor positioning for mapping purposes, such as inertial measurement units (...

Cadastral boundaries are often demarcated by objects that are visible in remote sensing imagery. Indirect surveying relies on the delineation of visible parcel boundaries from such images. Despite advances in automated detection and localization of objects from images, indirect surveying is rarely automated and relies on manual on-screen delineatio...

Detecting topographic changes in an urban environment and keeping city-level point clouds up-to-date are important tasks for urban planning and monitoring. In practice, remote sensing data are often available only in different modalities for two epochs. Change detection between airborne laser scanning data and photogrammetric data is challenging du...

In recent years, the task of segmenting foreground objects from background in a video, i.e. video object segmentation (VOS), has received considerable attention. In this paper, we propose a single end-to-end trainable deep neural network, convolutional gated recurrent Mask-RCNN, for tackling the semi-supervised VOS task. We take advantage of both t...

Road furniture recognition has become a prevalent issue in the past few years because of its great importance in smart cities and autonomous driving. Previous research has especially focussed on pole-like road furniture, such as traffic signs and lamp posts. Published methods have mainly classified road furniture as individual objects. However, mos...

STATE OF THE ART 3D Deep Neural Networks (DNNs): • DNNs are widely used for the semantic labeling and classification of 3D irregular and unordered point clouds. • Innovative point-based DNNs (i.e. PointNet++, SPG, PointCNN) have been developed that directly operate on the 3D point cloud without the need for a prior rasterization or voxelization (Fi...

Most methods for the mapping of tree species are based on the segmentation of single trees that are subsequently classified using a set of hand-crafted features and an appropriate classifier. The classification accuracy for coniferous and deciduous trees just using airborne laser scanning (ALS) data is only around 90% in case the geometric informat...

Mobile mapping enables highly accurate as well as high-resolution image data capture at low cost and high speed. As a terrestrial acquisition technique predominately employed in urban, and thus built-up areas, non-line-of-sight and multipath effects challenge its absolute positioning capabilities provided by GNSS. In conjunction with IMU drift, the...

Poor GNSS measurements in urban areas caused by blocked GNSS signals and multi-path is a well-known problem, which leads to an inaccurate trajectory estimation of Mobile Laser Scanning (MLS) platforms. Consequently, the MLS point cloud contains positioning errors. This paper presents a new method for the automatic extraction of accurate 3D tie poin...

The ISPRS Geospatial Week 2019 is a combination of 13 workshops organised by 30 ISPRS Working Groups active in areas of interest of ISPRS. The Geospatial Week 2019 is held from 10–14 June 2019, and is convened by the University of Twente acting as local organiser. The Geospatial Week 2019 is the fourth edition, after Antalya Turkey in 2013, La Gran...

Mobile mapping relies on satellite-based positioning, which suffers from line-of- sight and multipath issues. As an alternative, this paper presents a fully automatic approach for the co-registration of mobile mapping and oblique aerial images to introduce highly accurate and reliable ground control for mobile mapping data adjustment. An oblique vi...

Over the past decades, a special interest has been given to remote-sensing imagery to automate the detection of damaged buildings. Given the large areas it may cover and the possibility of automation of the damage detection process, when comparing with lengthy and costly ground observations. Currently, most image-based damage detection approaches r...

The ISPRS Geospatial Week 2019 is a combination of 13 workshops organised by 30 ISPRS Working Groups active in areas of interest of ISPRS. The Geospatial Week 2019 is held from 10–14 June 2019, and is convened by the University of Twente acting as local organiser. The Geospatial Week 2019 is the fourth edition, after Antalya Turkey in 2013, La Gran...

Indoor navigation can be a tedious process in a complex and unknown environment. It gets more critical when the first responders try to intervene in a big building after a disaster has occurred. For such cases, an accurate map of the building is among the best supports possible. Unfortunately, such a map is not always available, or generally outdat...

Airborne photogrammetry and airborne laser scanning are two commonly used technologies used for topographical data acquisition at the city level. Change detection between airborne laser scanning data and photogrammetric data is challenging since the two point clouds show different characteristics. After comparing the two types of point clouds, this...

Indoor mobile mapping systems are important for a wide range of applications starting from disaster management to straightforward indoor navigation. This paper presents the design and performance of a low-cost backpack indoor mobile mapping system (ITC-IMMS) that utilizes a combination of laser range-finders (LRFs) to fully recover the 3D building...

Multimodal information (e.g., visible and thermal) can generate robust pedestrian detections to facilitate around-the-clock computer vision applications, such as autonomous driving and video surveillance. However, it still remains a crucial challenge to train a reliable detector working well in different multispectral pedestrian datasets without ma...

The extraction of object outlines has been a research topic during the last decades. In spite of advances in photogrammetry, remote sensing and computer vision, this task remains challenging due to object and data complexity. The development of object extraction approaches is promoted through publically available benchmark datasets and evaluation f...

Mobile mapping relies on satellite-based positioning, which suffers from line-of-sight and multipath issues. As an alternative, this paper presents a fully automatic approach for the co-registration of mobile mapping and oblique aerial images to introduce highly accurate and reliable ground control for mobile mapping data adjustment. An oblique vie...

Following the first initiatives taken by the International Programme Committee of the XXIIIrd ISPRS Congress in Prague (Czech Republic) in 2016, modifications of the reviewing process of ISPRS events were further considered during the years 2017 and 2018. This evolution first targets to better fit such a process to the currents requirements and exp...