scholarly journals Automatic Shadow Detection in Urban Very-High-Resolution Images Using Existing 3D Models for Free Training

2019 ◽  
Vol 11 (1) ◽  
pp. 72 ◽  
Author(s):  
Kaixuan Zhou ◽  
Roderik Lindenbergh ◽  
Ben Gorte
Keyword(s):  
High Resolution ◽  
Image Interpretation ◽  
3D Models ◽  
Shadow Detection ◽  
Acquisition Time ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
Tree Construction ◽  
Training Samples ◽  
Very High

Up-to-date 3D city models are needed for many applications. Very-high-resolution (VHR) images with rich geometric and spectral information and a high update rate are increasingly applied for the purpose of updating 3D models. Shadow detection is the primary step for image interpretation, as shadow causes radiometric distortions. In addition, shadow itself is valuable geometric information. However, shadows are often complicated and environment-dependent. Supervised learning is considered to perform well in detecting shadows when training samples selected from these images are available. Unfortunately, manual labeling of images is expensive. Existing 3D models have been used to reconstruct shadows to provide free, computer-generated training samples, i.e., samples free from intensive manual labeling. However, accurate shadow reconstruction for large 3D models consisting of millions of triangles is either difficult or time-consuming. In addition, due to inaccuracy and incompleteness of the model, and different acquisition time between 3D models and images, mislabeling refers to training samples that are shadows but labeled as non-shadows and vice versa. We propose a ray-tracing approach with an effective KD tree construction to feasibly reconstruct accurate shadows for a large 3D model. An adaptive erosion approach is first provided to remove mislabeling effects near shadow boundaries. Next, a comparative study considering four classification methods, quadratic discriminant analysis (QDA) fusion, support vector machine (SVM), K nearest neighbors (KNN) and Random forest (RF), is performed to select the best classification method with respect to capturing the complicated properties of shadows and robustness to mislabeling. The experiments are performed on Dutch Amersfoort data with around 20% mislabels and the Toronto benchmark by simulating mislabels from inverting shadows to non-shadows. RF is tested to give robust and best results with 95.38% overall accuracy (OA) and a value of 0.9 for kappa coefficient (KC) for Amersfoort and around 96% OA and 0.92 KC for Toronto benchmarks when no more than 50% of shadows are inverted. QDA fusion and KNN are tested to be robust to mislabels but their capability to capture complicated properties of shadows is worse than RF. SVM is tested to have a good capability to separate shadow and non-shadows but is largely affected by mislabeled samples. It is shown that RF with free-training samples from existing 3D models is an automatic, effective, and robust approach for shadow detection from VHR images.

scholarly journals A Multi-Scale Filtering Building Index for Building Extraction in Very High-Resolution Satellite Imagery

2019 ◽  
Vol 11 (5) ◽  
pp. 482 ◽  
Author(s):  
Qi Bi ◽  
Kun Qin ◽  
Han Zhang ◽  
Ye Zhang ◽  
Zhili Li ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Common Knowledge ◽  
Remote Sensing Image ◽  
Morphological Operations ◽  
Building Extraction ◽  
Multi Scale ◽  
Training Samples ◽  
Image Building ◽  
Very High

Building extraction plays a significant role in many high-resolution remote sensing image applications. Many current building extraction methods need training samples while it is common knowledge that different samples often lead to different generalization ability. Morphological building index (MBI), representing morphological features of building regions in an index form, can effectively extract building regions especially in Chinese urban regions without any training samples and has drawn much attention. However, some problems like the heavy computation cost of multi-scale and multi-direction morphological operations still exist. In this paper, a multi-scale filtering building index (MFBI) is proposed in the hope of overcoming these drawbacks and dealing with the increasing noise in very high-resolution remote sensing image. The profile of multi-scale average filtering is averaged and normalized to generate this index. Moreover, to fully utilize the relatively little spectral information in very high-resolution remote sensing image, two scenarios to generate the multi-channel multi-scale filtering index (MMFBI) are proposed. While no high-resolution remote sensing image building extraction dataset is open to the public now and the current very high-resolution remote sensing image building extraction datasets usually contain samples from the Northern American or European regions, we offer a very high-resolution remote sensing image building extraction datasets in which the samples contain multiple building styles from multiple Chinese regions. The proposed MFBI and MMFBI outperform MBI and the currently used object based segmentation method on the dataset, with a high recall and F-score. Meanwhile, the computation time of MFBI and MBI is compared on three large-scale very high-resolution satellite image and the sensitivity analysis demonstrates the robustness of the proposed method.

scholarly journals High-Resolution U-Net: Preserving Image Details for Cultivated Land Extraction

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4064
Author(s):  
Wenna Xu ◽  
Xinping Deng ◽  
Shanxin Guo ◽  
Jinsong Chen ◽  
Luyi Sun ◽  
...  
Keyword(s):  
High Resolution ◽  
Random Forest ◽  
Land Cover ◽  
Image Texture ◽  
Support Vector ◽  
Spectral Variation ◽  
Cultivated Land ◽  
Resource Monitoring ◽  
K Nearest Neighbors ◽  
Image Details

Accurate and efficient extraction of cultivated land data is of great significance for agricultural resource monitoring and national food security. Deep-learning-based classification of remote-sensing images overcomes the two difficulties of traditional learning methods (e.g., support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF)) when extracting the cultivated land: (1) the limited performance when extracting the same land-cover type with the high intra-class spectral variation, such as cultivated land with both vegetation and non-vegetation cover, and (2) the limited generalization ability for handling a large dataset to apply the model to different locations. However, the “pooling” process in most deep convolutional networks, which attempts to enlarge the sensing field of the kernel by involving the upscale process, leads to significant detail loss in the output, including the edges, gradients, and image texture details. To solve this problem, in this study we proposed a new end-to-end extraction algorithm, a high-resolution U-Net (HRU-Net), to preserve the image details by improving the skip connection structure and the loss function of the original U-Net. The proposed HRU-Net was tested in Xinjiang Province, China to extract the cultivated land from Landsat Thematic Mapper (TM) images. The result showed that the HRU-Net achieved better performance (Acc: 92.81%; kappa: 0.81; F1-score: 0.90) than the U-Net++ (Acc: 91.74%; kappa: 0.79; F1-score: 0.89), the original U-Net (Acc: 89.83%; kappa: 0.74; F1-score: 0.86), and the Random Forest model (Acc: 76.13%; kappa: 0.48; F1-score: 0.69). The robustness of the proposed model for the intra-class spectral variation and the accuracy of the edge details were also compared, and this showed that the HRU-Net obtained more accurate edge details and had less influence from the intra-class spectral variation. The model proposed in this study can be further applied to other land cover types that have more spectral diversity and require more details of extraction.

scholarly journals Studying the Construction of Floor Mosaics in the Roman Villa of Pisões (Portugal) Using Noninvasive Methods: High-Resolution 3D GPR and Photogrammetry

2019 ◽  
Vol 11 (16) ◽  
pp. 1882 ◽  
Author(s):  
Bento Caldeira ◽  
Rui Jorge Oliveira ◽  
Teresa Teixidó ◽  
José Fernando Borges ◽  
Renato Henriques ◽  
...  
Keyword(s):  
High Resolution ◽  
Archaeological Site ◽  
3D Models ◽  
Noninvasive Methods ◽  
Noninvasive Sensors ◽  
Roman Villa ◽  
3D Gpr ◽  
Ground Penetrating ◽  
Structural Levels ◽  
Very High

Over the past decade, high-resolution noninvasive sensors have been widely used in explorations of the first few meters underground at archaeological sites. However, remote sensing actions aimed at the study of structural elements that require a very high resolution are rare. In this study, layer characterization of the floor mosaic substrate of the Pisões Roman archaeological site was carried out. This work was performed with two noninvasive techniques: 3D ground penetrating radar (3D GPR) operating with a 1.6 GHz central frequency antenna, which is a very high-resolution geophysical method, and photogrammetry with imagery obtained by an unmanned aerial vehicle (UAV), which is a very high-resolution optical method. The first method allows penetration up to 30–40 cm depth and 3D models can be obtained, and with the second method, very high detail surface images and digital surface models can be obtained. In this study, we analyze a combination of data from both sensors to study a portion of the floor mosaic of the Pisões Roman Villa (Beja, Portugal) to obtain evidence of the inner structure. In this context, we have detected the main structural levels of the Roman mosaic and some internal characteristics, such as etched guides, internal cracking, and detection of higher humidity areas. The methodology that we introduce in this work can be referenced for the documentation of ancient pavements and may be used prior to carrying out preservation activities. Additionally, we intend to show that a Roman mosaic, understood as an archaeological structure, does not consist of only beautiful superficial drawings defined by the tesserae, but these mosaics are much more complex elements that must be considered in their entirety for preservation.

Photogrammetric processing and application of multi-temporal satellite imagery stereopairs

2021 ◽  
Vol 974 (8) ◽  
pp. 36-44
Author(s):  
R.V. Permyakov
Keyword(s):  
High Resolution ◽  
Satellite Imagery ◽  
Weather Conditions ◽  
3D Models ◽  
High Resolution Imagery ◽  
Multi Temporal ◽  
Unfavourable Weather ◽  
High Resolution Satellite Imagery ◽  
Very High Resolution Imagery ◽  
Very High

Stereopairs of very-high resolution satellite imagery constitute one of the key high-accurate data sources on heights. A stereophotogrammetric technique is a key method of processing these data. Despite that a number of spacecrafts gathering very-high-resolution imagery in a stereo mode constantly increases, the area of the Earth regularly covered by such data and stored in the archives of RSD operators remains relatively small and, as a rule, is limited only to large urban agglomerations. The new collection may not suit the customer for several reasons. Firstly, the materials of the new stereo collection are more expensive than those of the archived one. Secondly, due to unfavourable weather conditions and a busy schedule of satellites, the completion of the new collection may go beyond the deadline specified by the customer. Well known and brand-new criteria to form multi-temporal, stereopairs are analyzed. The specific of photogrammetric processing multi-temporal stereopairs is demonstrated. Application of multi-temporal stereopairs is described. In conclusion it is confirmed that 3D-models and high accurate DTMs can be generated basing on stereo models from multi-temporal satellite imagery in the absence of the following data

scholarly journals A Mixed Property-Based Automatic Shadow Detection Approach for VHR Multispectral Remote Sensing Images

2018 ◽  
Vol 8 (10) ◽  
pp. 1883 ◽  
Author(s):  
Hongyin Han ◽  
Chengshan Han ◽  
Xucheng Xue ◽  
Changhong Hu ◽  
Liang Huang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Near Infrared ◽  
Shadow Detection ◽  
Detection Methods ◽  
Remote Sensing Images ◽  
Multispectral Remote Sensing ◽  
The Difference ◽  
Mixed Property ◽  
Very High

Shadows in very high-resolution multispectral remote sensing images hinder many applications, such as change detection, target recognition, and image classification. Though a wide variety of significant research has explored shadow detection, shadow pixels are still more or less omitted and are wrongly confused with vegetation pixels in some cases. In this study, to further manage the problems of shadow omission and vegetation misclassification, a mixed property-based shadow index is developed for detecting shadows in very high-resolution multispectral remote sensing images based on the difference of the hue component and the intensity component between shadows and nonshadows, and the difference of the reflectivity of the red band and the near infrared band between shadows and vegetation cover in nonshadows. Then, the final shadow mask is achieved, with an optimal threshold automatically obtained from the index image histogram. To validate the effectiveness of our approach for shadow detection, three test images are selected from the multispectral WorldView-3 images of Rio de Janeiro, Brazil, and are tested with our method. When compared with other investigated standard shadow detection methods, the resulting images produced by our method deliver a higher average overall accuracy (95.02%) and a better visual sense. The highly accurate data show the efficacy and stability of the proposed approach in appropriately detecting shadows and correctly classifying shadow pixels against the vegetation pixels for very high-resolution multispectral remote sensing images.

Sign in / Sign up

Export Citation Format

Share Document