Abstract

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.

Highlights

  • quadratic discriminant analysis (QDA) fusion and K nearest neighbors (KNN) are tested to be robust to mislabels but their capability to capture complicated properties of shadows is worse than Random forest (RF)

  • 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

  • The same disk-shaped erosion filter is applied to remove the boundary parts of shadows and non-shadows

Read more

Summary

Motivation

Automatic 3D city model reconstruction has been intensively investigated in recent decades. The national point clouds in the Netherlands, Actueel Hoogtebestand Nederland (AHN), have an update rate of 5–10 years. To keep 3D models up to date, VHR aerial images are the first choice for two reasons: first, VHR aerial images are often updated annually Their high spatial resolution, even to the centimeter, provides rich and valuable geometric and color information. Shadows reconstructed from existing 3D models differing from shadows detected from newly acquired images could indicate changes. In this context, both miss- or over-detection of shadows immediately results in miss- or over-detection of changes. Our study concentrates on detecting shadows from VHR images in urban areas

Related Work
Contribution of Our Study
Study Area and Data Preparation
VHR Image Description
Ray Tracing
KD Tree
Adaptive Erosion Filtering
Classifications from Automatically Selected Samples
QDA Classification with Decision Fusion
Support Vector Machine
K Nearest Neighbors
Random Forest
Evaluation of Classification
Experiments and Comparisons
Feasibility of Shadow Reconstruction for Free-Training Samples
Method Comparison for Classification from Free-Training Samples
Shadow Classification Results for Amersfoort
Shadow Classification Results for Toronto
Mislabeling Simulation on Toronto Dataset
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.