Pole detection in aerial orthophotos is a critical yet challenging task due to the small size of poles (often reduced to just 1-2 pixels), limited vertical profile visibility, and varying lighting conditions in aerial imagery. Existing approaches primarily rely on bounding box detection, which lacks the precision needed for practical applications such as urban infrastructure mapping and autonomous navigation. In contrast, this paper introduces YOLO-Pole, a novel end-to-end deep learning framework based on YOLOv7 architecture, specifically designed for high-precision pole localization in aerial orthophotos. Instead of providing a coarse bounding box, YOLO-Pole directly predicts the precise pole footprint using a single-stage process. To further refine localization, we introduce a pointwise loss function based on Euclidean distance. Experimental results on a custom dataset with 20 cm ground sample distance (GSD) demonstrate significant improvements in localization accuracy of poles over the standard YOLO model, confirming that precise pole localization is achievable and offering potential for imagebased geolocalization.

Building instances play a pivotal role in understanding population distribution and assessing vulnerability in the face of potential risks. Building instance segmentation is a valuable technique for identifying individual structures, however, complex urban environments pose great challenges, especially in the informal areas. In this study, we utilize a building instance segmentation method specifically designed to discern single buildings in both formal and informal settlements. Employing a SkipFuse-UResNet34 model, we generate building instances for Medellín, Colombia, resulting in a more comprehensive building mask compared to conventional official data sources. This enhanced mask serves as a vital tool for estimating the population at risk, enabling a thorough comparison with official data and addressing current spatial knowledge gaps.

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 crowded environments and are unable to identify obscured objects. To this end, we first construct two multimodal dense and occlusion vehicle detection datasets for large-scale events, utilizing RGB and height map modalities. Based on these datasets, we propose a multimodal collaboration network for dense and occluded vehicle detection, MuDet for short. MuDet hierarchically enhances the completeness of discriminable information within and across modalities and differentiates between simple and complex samples. MuDet includes three main modules: Unimodal Feature Hierarchical Enhancement (Uni-Enh), Multimodal Cross Learning (Mul-Lea), and Hard-easy Discriminative (He-Dis) Pattern. Uni-Enh and Mul-Lea enhance the features within each modality and facilitate the cross-integration of features from two heterogeneous modalities. He-Dis effectively separates densely occluded vehicle targets with significant intra-class differences and minimal inter-class differences by defining and thresholding confidence values, thereby suppressing the complex background. Experimental results on two re-labeled multimodal benchmark datasets, the 4K-SAI-LCS dataset, and the ISPRS Potsdam dataset, demonstrate the robustness and generalization of the MuDet.

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, and detached fusion co-learning) are proposed and investigated with two types of co-learning loss functions within our framework. Our experimental results demonstrate that the proposed methods are able to take advantage of unlabeled target data pairs and therefore enhance the performance of single-modal neural networks on the target data. In addition, our synthetic-to-real experiments demonstrate that the recently published synthetic dataset SMARS is feasible to be used in real change detection scenarios, where the optimal result is with the F1 score of 79.29%.

We demonstrate an atomic-sized Pd tunneling junction memory that can operate in a vacuum, N2, or ambient environment. The device was fabricated by a simple 2-step electron-beam lithography/lift-off process and an electromigration process. Calculation based on quantum point contact model indicated the size of the tunneling gap is between 0.1 and 2nm, and the switching between high-resistance state and low-resistance state is achieved by a migration of a few atoms near the junction. The device’s RESET speed is 25ns, and the ON/OFF ratio is from 2 to 103, with an endurance of 1000 cycles. We proposed a phenomenological model to explain the reason for the imperfection of device performance, which could be useful for circuit design. It may be derived from two different migration processes, dominated by rapid changing electric field and current-induced Joule heat accumulation to affect the device performance, respectively. Compared to other reported works, our devices have the same fast RESET speed, better endurance, and potential for low power applications.

This paper describes the contribution of the DLR team ranking 3rdin Track 1 of the 2020 IEEE GRSS Data Fusion Contest, with results ranking 2ndin Track 2 of the same contest being reported in a companion paper. The classifications are based on refinements of low-resolution MODIS labeling using available higher resolution Sentinel-1 and Sentinel-2 data. Results are initialized with a handcrafted decision tree integrating output from a random forest classifier, and subsequently boosted by detectors for specific classes.

This paper describes the contribution of the DLR team ranking 2ndin 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. The classification is initialized with a handcrafted decision tree integrating output from a random forest classifier, and subsequently boosted by detectors for specific classes. The results of the team ranking 3rdin Track 1 of the same contest are reported in a companion paper.

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 might lead to the poor model generalization and degraded network learning ability. To this end, a weakly-supervised deep network (WSDN) is developed for geospatial object detection by applying a digital surface model (DSM)-aided auto-labeling and a pre-trained network learned from the task-independent dataset. Experimental results conducted on the stereo aerial imagery of a large camping site are performed to demonstrate that the proposed WSDN yields better detection results, with 62.78% precision and 55.13% recall.

The prediction of regional land use and land cover change is important to the local human life and economic development. To build a prediction model faces two challenges: one is to select appropriate driving factors; the other is to improve model accuracy. In this paper, we selected seven driving factors of natural, economic and social aspects and proposed a coupling model combining ANN and Markov_CA model to predict the land use and cover changes (LUCC) in Beijing, China. Using ANN to get the transition rules for CA model can improve the accuracy of prediction. We verified the accuracy of the model by compare the simulated result with the actual data, and the error of the model was within the limitation of the requirement. The Markov_ANN_CA model was applied to predict the LUCC of Beijing in 2020. The prediction is reasonable for the city planning.

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) are fused into a DSM. Semantic segmentation is performed with an ensemble of FCN networks taking as input RGB, multi-spectral and height data. Their results are then merged with pixel-wise detectors for the classes water and high vegetation. Compared to the second and third placed teams (mIOU-3 scores of 0.73 and 0.7295), our contribution reached a significantly higher score of 0.745.

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 deformations, particularly objective scaling and rotation. To this end, we propose a novel object detection framework, called Optical Remote Sensing Imagery detector (ORSIm detector), integrating diverse channel features extraction, feature learning, fast image pyramid matching, and boosting strategy. An ORSIm detector adopts a novel spatial-frequency channel feature (SFCF) by jointly considering the rotation-invariant channel features constructed in the frequency domain and the original spatial channel features (e.g., color channel and gradient magnitude). Subsequently, we refine SFCF using learning-based strategy in order to obtain the high-level or semantically meaningful features. In the test phase, we achieve a fast and coarsely scaled channel computation by mathematically estimating a scaling factor in the image domain. Extensive experimental results conducted on the two different airborne data sets are performed to demonstrate the superiority and effectiveness in comparison with the previous state-of-the-art methods.

One of the challenges of remote sensing image based building change detection is distinguishing building changes from other types of land cover alterations. Height information can be a great assistance for this task but its performance is limited to the quality of the height. Yet, the standard automatic methods for this task are still lacking. We propose a very high resolution stereo series data based building change detection approach that focuses on the use of time series information. In the first step, belief functions are explored to fuse the change features from the 2D and height maps to obtain an initial change detection result. In the second step, the building probability maps (BPMs) from the series data are adopted to refine the change detection results based on Dempster-Shafer theory. The final step is to fuse the series building change detection results in order to obtain a final change map. The advantages of the proposed approach are demonstrated by testing it on a set of time series data captured in North Korea.

This article describes the workflow of the classification algorithm which ranked at 2ndplace in the 2018 GRSS Data Fusion Contest. The objective of the contest was to provide a classification map with 20 classes on a complex urban scenario. The available multi-modal data were acquired from hyperspectral, LiDAR and very high-resolution RGB sensors flown on the same platform over the city of Houston, TX, USA. The classification was obtained by merging deep convolutional and shallow fully-connected neural networks on a simplified set of classes, complemented by a series of specific detectors and ad hoc classifiers.

Building change detection is a major issue for urban area monitoring. Due to different imaging conditions and sensor parameters, 2-D information delivered by satellite images from different dates is often not sufficient when dealing with building changes. Moreover, due to the similar spectral characteristics, it is often difficult to distinguish buildings from other man-made constructions, like roads and bridges, during the change detection procedure. Therefore, stereo imagery is of importance to provide the height component which is very helpful in analyzing 3-D building changes. In this paper, we propose a change detection method based on stereo imagery and digital surface models (DSMs) generated with stereo matching methodology and provide a solution by the joint use of height changes and Kullback-Leibler divergence similarity measure between the original images. The Dempster-Shafer fusion theory is adopted to combine these two change indicators to improve the accuracy. In addition, vegetation and shadow classifications are used as no-building change indicators for refining the change detection results. In the end, an object-based building extraction method based on shape features is performed. For evaluation purpose, the proposed method is applied in two test areas, one is in an industrial area in Korea with stereo imagery from the same sensor and the other represents a dense urban area in Germany using stereo imagery from different sensors with different resolutions. Our experimental results confirm the efficiency and high accuracy of the proposed methodology even for different kinds and combinations of stereo images and consequently different DSM qualities.

The goal of this paper is to develop an efficient method for forest change detection using multitemporal stereo panchromatic imagery. Due to the lack of spectral information, it is difficult to extract reliable features for forest change monitoring. Moreover, the forest changes often occur together with other unrelated phenomena, e.g., seasonal changes of land covers such as grass and crops. Therefore, we propose an approach that exploits kernel Minimum Noise Fraction (kMNF) to transform simple change features into high-dimensional feature space. Digital surface models (DSMs) generated from stereo imagery are used to provide information on height difference, which is additionally used to separate forest changes from other land-cover changes. With very few training samples, a change mask is generated with iterated canonical discriminant analysis (ICDA). Two examples are presented to illustrate the approach and demonstrate its efficiency. It is shown that with the same amount of training samples, the proposed method can obtain more accurate change masks compared with algorithms based on k-means, one-class support vector machine, and random forests.