Jiaojiao Tian

German Aerospace Center (DLR) | DLR · Department of Photogrammetry and Image Analysis

Nowadays, deep learning allows to automatically learn features from data. Buildings are one of the most important objects in urban environments. They are used in applications such as inputs to building reconstruction, disaster monitoring, city planing and environment modelling for autonomous driving. However, it is not enough to represent them in r...

The anthropogenic climate crisis results in the gradual loss of tree species in locations where they were previously able to grow. This leads to increasing workloads and requirements for foresters and arborists as they are forced to restructure their forests and city parks. The advancements in computer vision (CV)—especially in supervised deep lear...

Accurate estimation of above-ground biomass (AGB) in forested areas is essential for studying forest ecological functions, surface carbon cycling, and global carbon balance. Over the past decade, models that harness the distinct features of multi-source remote sensing observations for estimating AGB have gained significant popularity. It is worth e...

Accurate segmentation of individual tree crowns (ITC) segmentation is essential for investigating tree-level based growth trends and assessing tree vitality. ITC segmentation using remote sensing data faces challenges due to crown heterogeneity, overlapping crowns and data quality. Currently, both classical and deep learning methods have been emplo...

In this article, we propose a multimodal co-learning framework for building change detection. This framework can be adopted to jointly train a Siamese bitemporal image network and a height difference map (HDiff) network with labeled source data and unlabeled target data pairs. Three co-learning combinations (vanilla co-learning, fusion co-learning,...

In large-scale disaster events, the planning of optimal rescue routes depends on the object detection ability at the disaster scene, with one of the main challenges being the presence of dense and occluded objects. Existing methods, which are typically based on the RGB modality, struggle to distinguish targets with similar colors and textures in cr...

Deep learning has been the state-of-the-art solution to numerous remote sensing tasks, especially for building extraction. However, the performance of learning based building extraction approaches depend to a large extend on the similarity of the source and target domain data. To alleviate the dependency on annotated data, and to exploit the potent...

Multispectral sensors are important instruments for Earth observation. In remote sensing applications, the near-infrared (NIR) band, together with the visible spectrum (RGB), provide abundant information about ground objects. However, the NIR band is typically not available on low-cost camera systems, which presents challenges for the vegetation ex...

Accurate building extraction from remotely sensed images is essential for topographic mapping, urban planning, disaster management, navigation, and many other applications [1]. [...]

Although deep learning techniques have brought unprecedented accuracy to automatic building extraction, several main issues still constitute an obstacle to effective and practical applications. The industry is eager for higher accuracy and more flexible data usage. In this paper, we present a co-learning framework applicable to building extraction...

Remote sensing-based forest investigation and monitoring have become more affordable and applicable in the past few decades. The current bottleneck limiting practical use of the vast volume of remote sensing data lies in the lack of affordable, reliable, and detailed field references, which are required for necessary calibrations of satellite and a...

Convolutional Neural Networks have been widely introduced to building rooftop segmentation using satellite and aerial imagery. Preparing efficient training data is still among the critical issues on this topic. Therefore, adopting available annotated cross-domain multisource dataset is needed. This paper evaluates the performance of fusing the stat...

GaoFen-7 (GF-7) satellite mission is further expanding the very high resolution 3D mapping application. Carrying the first civilian Chinese sub-meter resolution stereo satellite sensors, GF-7 satellite was launched on November 7, 2019. With 0.65 meter resolution on backward view and 0.8 meter resolution forward view, GF-7 has been designed to meet...

Dense matching plays a crucial role in computer vision and remote sensing, to rapidly provide stereo products using inexpensive hardware. Along with the development of deep learning, the Guided Aggregation Network (GA-Net) achieves state-of-the-art performance via the proposed Semi-Global Guided Aggregation layers and reduces the use of costly 3D c...

Detection and vectorization of windows from building façades are important for building energy modeling, civil engineering, and architecture design. However, current applications still face the challenges of low accuracy and lack of automation. In this paper we propose a new two-steps workflow for window segmentation and vectorization from façade i...

Increased frequencies of storms and droughts due to climate change are changing central European forests more rapidly than in previous decades. To monitor these changes, multispectral 3D remote sensing (RS) data can provide relevant information for forest management and inventory. In this case study, data of the multispectral 3D-capable satellite s...

Deep learning models achieve excellent semantic segmentation results for airborne laser scanning (ALS) point clouds, if sufficient training data are provided. Increasing amounts of annotated data are becoming publicly available thanks to contributors from all over the world. However, models trained on a specific dataset typically exhibit poor perfo...

Deep learning models achieve excellent semantic segmentation results for airborne laser scanning (ALS) point clouds, if sufficient training data are provided. Increasing amounts of annotated data are becoming publicly available thanks to contributors from all over the world. However, models trained on a specific dataset typically exhibit poor perfo...

Individual tree crown (ITC) segmentation supports numerous applications in forest management and ecology. In the latter context, special attention is dedicated to the study of angular reflection effects, caused by the interaction of incident sunlight with a canopy. High precision airborne analysis of these effects requires multi-view sensor systems...

Geeignete Bewirtschaftungskonzepte für den Wald von morgen können durch FernerkundungsDaten ergänzt werden. Benötigt werden 3D-Daten zur Strukturabschätzung und MultispektralDaten zur Baumarten-Annäherung. Nur die Fernerkundung gibt es nicht, genauso wenig ein Universalrezept zur Bewirtschaftung von Nutzwäldern. Da viele in der Wissenschaft gängige...

This paper describes the contribution of the DLR team ranking 2nd in Track 2 of the 2020 IEEE GRSS Data Fusion Contest. The semantic classification of multimodal earth observation data proposed is based on the refinement of low resolution MODIS labels, using as auxiliary training data higher resolution labels available for a validation data set. Th...

Vehicle detection in remote sensing images has attracted increasing interest in recent years. However, its detection ability is limited due to lack of well-annotated samples, especially in densely crowded scenes. Furthermore, since a list of remotely sensed data sources is available, efficient exploitation of useful information from multi-source da...

Near infrared bands (NIR) provide rich information for many remote sensing applications. In addition to deriving useful indices to delineate water and vegetation, near infrared channels could also be used to facilitate image pre-processing. However, synthesizing bands from RGB spectrum is not an easy task. The inter-correlations between bands are n...

This paper describes the contribution of the DLR team ranking 3rd in Track 1 of the 2020 IEEE GRSS Data Fusion Contest, with results ranking 2nd in Track 2 of the same contest are reported in a companion paper. The classifications are based on refinements of low-resolution MODIS labeling on available higher resolution Sentinel-1 and Sentinel-2 data...

Deep learning and convolutional neural networks (CNN) have obtained a great success in image processing, by means of its powerful feature extraction ability to learn specific tasks. Many deep learning based algorithms have been developed for dense image matching, which is a hot topic in the community of computer vision. These methods are tested for...

Near infrared bands (NIR) provide rich information for many remote sensing applications. In addition to deriving useful indices to delineate water and vegetation, near infrared channels could also be used to facilitate image pre-processing. However, synthesizing bands from RGB spectrum is not an easy task. The inter-correlations between bands are n...

The project ‘Application of remote sensing for the early detection of drought stress at vulnerable forest sites (ForDroughtDet)’ is funded by the German Federal Agency of Agriculture and Food and aims to detect drought stress in an early phase using remote sensing techniques. In this project, three test sites in the south and middle part of Germany...

Vehicle detection in remote sensing images has attracted increasing interest in recent years. However, its detection ability is limited due to lack of well-annotated samples, especially in densely crowded scenes. Furthermore, since a list of remotely sensed data sources is available, efficient exploitation of useful information from multi-source da...

Semi-Global Matching (SGM) approximates a 2D Markov Random Field (MRF) via multiple 1D scanline optimizations, which serves as a good trade-off between accuracy and efficiency in dense matching. Nevertheless, the performance is limited due to the simple summation of the aggregated costs from all 1D scanline optimizations for the final disparity est...

Ripe with possibilities offered by deep-learning tech-niques and useful in applications related to remote sensing, computer vision, and robotics, 3D point cloud semantic segmentation (PCSS) and point cloud segmen-tation (PCS) are attracting increasing interest. This article summarizes available data sets and relevant studies on re-cent developments...

Building extraction from remote sensing data plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications [...]

3D Point Cloud Semantic Segmentation (PCSS) is attracting increasing interest, due to its applicability in remote sensing, computer vision and robotics, and due to the new possibilities offered by deep learning techniques. In order to provide a needed up-to-date review of recent developments in PCSS, this article summarizes existing studies on this...

Precise and detailed reconstruction of 3D plant models is an important goal in computer vision. Based on these models, important parameters can be extracted, which would be very useful for monitoring the tree health situation. This paper has firstly constructed the 3D plant model based on MC-CNN using close-range photogrammetric imagery, and then a...

3D Point Cloud Semantic Segmentation (PCSS) is attracting increasing interest, due to its applicability in remote sensing, computer vision and robotics, and due to the new possibilities offered by deep learning techniques. In order to provide a needed up-to-date review of recent developments in PCSS, this article summarizes existing studies on this...

With the breakthrough of the spatial resolution of optical remote sensing images at the sub-meter level and the explosive development of deep learning, geospatial object detection has achieved a growing interest in remote sensing community. However, labeling large training datasets in object level is still an expensive and tedious procedure. This m...

This paper describes the winning contribution to the 2019 IEEE GRSS Data Fusion Contest Multi-view Semantic Stereo Challenge. In this challenge, a digital surface model(DSM) and a semantic segmentation should be derived from a large number of multi-spectral WorldView-3 images. Results from 50 stereo pairs matched using Semi-Global Matching (SGM) ar...

Buildings are one of the main objects in urban remote sensing and photogrammetric computer vision applications using satellite data. In this paper a superpixel-based approach is presented to refine 3D building models from stereo satellite imagery. First, for each epoch in time, a multispectral very high resolution (VHR) satellite image is segmented...

individual tree crown segmentation, digital surface model

Detection and delineation of forest trees in airborne observational data has been under study for decades, starting with images. With the advent of 3D point cloud generation techniques, much research has been spent for point cloud segmentation. From a cost perspective, aerial images are still advantageous. In this paper, two individual tree crown s...

Change detection using remote sensing data is one of the most essential processing steps for monitoring urban and forest areas. And it provides an invaluable tool for archaeological sites in times of war or natural disasters. However, until now the visual interpretation is still the main technique in analyzing changes from these images. In this cha...

Stereo matching can provide complete and dense threedimensional reconstruction to study plant growth. Recently, high-quality stereo matching results were achieved combining semiglobal matching with deep learning. However, due to a lack of suitable training data, this technique is not readily applicable for plant reconstruction. We propose a self-su...

This paper proposes a new approach for building change detection using multi-temporal satellite stereo data. This approach is composed of three main steps. Firstly building probably map can be derived based on the state-of-the-art deep learning approach. In the second step, a decision fusion based fusion model is proposed to highlight the building...

Currently available very high resolution space borne imagery can be used for mapping and 3D modeling of archaeologic sites and monuments from all over the world. This allows also the continuous monitoring, protection from natural and human threatening and may also be the base for virtual or real reconstruction of monuments. As an example it is show...

With the rapid development of spaceborne imaging techniques, object detection in optical remote sensing imagery has drawn much attention in recent decades. While many advanced works have been developed with powerful learning algorithms, the incomplete feature representation still cannot meet the demand for effectively and efficiently handling image...

With the rapid development of spaceborne imaging techniques, object detection in optical remote sensing imagery has drawn much attention in recent decades. While many advanced works have been developed with powerful learning algorithms, the incomplete feature representation still cannot meet the demand for effectively and efficiently handling image...

Large-scale events represent a special challenge for crisis management. To ensure that participants can enjoy an event safely and carefree, it must be comprehensively prepared and attentively monitored. Remote sensing can provide valuable information to identify potential risks and take appropriate measures in order to prevent a disaster, or initia...

Superpixels, as a state-of-the-art segmentation paradigm, have recently been widely used in computer vision and pattern recognition. Despite the effectiveness of these algorithms, there are still many limitations and challenges dealing with Very High-Resolution (VHR) satellite images especially in complex urban scenes. In this paper, we develop a s...

The extraction of building changes from very high resolution satellite images is an important but challenging task in remote sensing. Digital Surface Models (DSMs) generated from stereo imagery have proved to be valuable additional data sources for this task. In order to efficiently use the change information from the DSMs and spectral images, beli...

Tree species information is crucial in sectors such as forest management and nature conservation. It is often required over a large area. In this study, tree species classification was performed using hyperspectral data and the Digital Surface Model generated from DLR-3K aerial borne stereo camera System. In the classification step, pixelbased appr...

A challenge in remote sensing image based building change detection is separating building changes from other kinds of land cover changes. Height information can be a great assistance for this task but its performance is limited to the height quality. Yet, standard automatic methods for this task are still lacking. We propose a very high resolution...

3D reconstruction of plants is hard to implement, as the complex leaf distribution highly increases the difficulty level in dense matching. Semi-Global Matching has been successfully applied to recover the depth information of a scene, but may perform variably when different matching cost algorithms are used. In this paper two matching cost computa...

3D reconstruction of plants is hard to implement, as the complex leaf distribution highly increases the difficulty level in dense matching. Semi-Global Matching has been successfully applied to recover the depth information of a scene, but may perform variably when different matching cost algorithms are used. In this paper two matching cost computa...

Automatic extraction of building changes is important for many applications like disaster monitoring and city planning. Although a lot of research work is available based on 2D as well as 3D data, an improvement in accuracy and efficiency is still needed. The introducing of digital surface models (DSMs) to building change detection has strongly imp...

Automatic rooftop extraction is one of the most challenging problems in remote sensing image analysis. Classical 2D image processing techniques are expensive due to the high amount of features required to locate buildings. This problem can be avoided when 3D information is available. In this paper, we show how to fuse the spectral and height inform...

Digital surface models (DSMs) derived from spaceborne and airborne sensors enable the monitoring of the vertical structures for forests in large areas. Nevertheless, due to the lack of an objective performance assessment for this task, it is difficult to select the most appropriate data source for DSM generation. In order to fill this gap, this pap...

Automatic rooftop extraction is one of the most challenging problems in remote sensing image analysis. Classical 2D image processing techniques are expensive due to the high amount of features required to locate buildings. This problem can be avoided when 3D information is available. In this paper, we show how to fuse the spectral and height inform...

Automatic extraction of building changes is important for many applications like disaster monitoring and city planning. Although a lot of research work is available based on 2D as well as 3D data, an improvement in accuracy and efficiency is still needed. The introducing of digital surface models (DSMs) to building change detection has strongly imp...

Due to the unprecedented technology development of sensors, platforms and algorithms for 3D data acquisition and generation, 3D spaceborne, airborne and close-range data, in the form of image based, Light Detection and Ranging (LiDAR) based point clouds, Digital Elevation Models (DEM) and 3D city models, become more accessible than ever before. Cha...

Due to the unprecedented technology development of sensors, platforms and algorithms for 3D data acquisition and generation, 3D spaceborne, airborne and close-range data, in the form of image based, Light Detection and Ranging (LiDAR) based point clouds, Digital Elevation Models (DEM) and 3D city models, become more accessible than ever before. Cha...

Due to the unprecedented technology development of sensors, platforms and algorithms for 3D data acquisition and generation, 3D spaceborne, airborne and close-range data, in the form of image based, Light Detection and Ranging (LiDAR) based point clouds, Digital Elevation Models (DEM) and 3D city models, become more accessible than ever before. Cha...

The intentional damage to local Cultural Heritage sites carried out in recent months by the Islamic State have received wide coverage from the media worldwide. Earth Observation data provide important information to assess this damage in such non-accessible areas, and automated image processing techniques will be needed to speed up the analysis if...

The intentional damages to local Cultural Heritage sites carried out in recent months by the Islamic State have received wide coverage from the media worldwide. Earth Observation data provide important information to assess these damages in such non-accessible areas, and automated image processing techniques would be needed to speed up the analysis...

The intentional damages to local Cultural Heritage sites carried out in recent months by the Islamic State (IS) have received wide coverage from the media worldwide. Earth Observation data is an important tool to assess these damages in such non-accessible areas: If a fast response is desired, automated image processing techniques would be needed t...

We propose an image processing workflow to extract rectangular building footprints using georeferenced stereo-imagery and a derivative digital surface model (DSM) product. The approach applies a line segment detection procedure to the imagery and subsequently verifies identified line segments individually to create a footprint on the basis of the D...

The intentional damages to local Cultural Heritage sites carried out in recent