Learning-Based Shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds

Ufuktepe, Deniz Kavzak; Collins, Jaired; Ufuktepe, Ekincan; Fraser, Joshua; Krock, Timothy; Palaniappan, Kannappan

doi:10.1109/iccvw54120.2021.00439

Cited by 5 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The existing datasets are not appropriate for training Deep Learning (DL)-based algorithms for real-world aerial shadow detection applications. Dealing with this shortcoming, Ufuktepe et al [31] introduced WAMI dataset containing 137k aerial images, which is the largest shadow detection dataset for aerial imagery. The shadows in the dataset were generated and superimposed using a 3D scene model approach, eliminating the need for tedious manual annotation.…”

Section: Shadow Detection Datasetsmentioning

confidence: 99%

“…Although the authors tried to cover various scenes and object classes, these datasets mostly contain images from ground perspective. Apart from the Wide Area Motion Imagery (WAMI) [31] dataset introduced recently, existing shadow detection datasets offer only a limited number of aerial images, which inadequately represent the real-world challenges of aerial imagery. As a result, the number of data-driven shadow detection methods for aerial imagery is limited.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Airborne-Shadow: Towards Fine-Grained Shadow Detection in Aerial Imagery

Azimi,

Bahmanyar

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Shadow detection is the first step in the process of shadow removal, which improves the understanding of complex urban scenes in aerial imagery for applications such as autonomous driving, infrastructure monitoring, and mapping. However, the limited annotation in existing datasets hinders the effectiveness of semantic segmentation and the ability of shadow removal algorithms to meet the fine-grained requirements of real-world applications. To address this problem, we present Airborne-Shadow (ASD), a meticulously annotated dataset for shadow detection in aerial imagery. Unlike existing datasets, ASD includes annotations for both heavy and light shadows, covering various structures ranging from buildings and bridges to smaller details such as poles and fences. Therefore, we define shadow detection tasks for multi-class, single class, and merging two classes. Extensive experiments show the challenges that state-of-the-art semantic segmentation and shadow detection algorithms face in handling different shadow sizes, scales, and fine details, while still achieving comparable results to conventional methods. We make the ASD dataset publicly available to encourage progress in shadow detection.

show abstract

Section: Shadow Detection Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Airborne-Shadow: Towards Fine-Grained Shadow Detection in Aerial Imagery

Azimi,

Bahmanyar

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

Shadow Detection of Remote Sensing Image by Fusion of Involution and Shunted Transformer

Wang,

Huang

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

SUShe: simple unsupervised shadow removal

Koutsiou

Savelonas

Iakovidis

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Shadow removal is an important problem in computer vision, since the presence of shadows complicates core computer vision tasks, including image segmentation and object recognition. Most state-of-the-art shadow removal methods are based on complex deep learning architectures, which require training on a large amount of data. In this paper a novel and efficient methodology is proposed aiming to provide a simple solution to shadow removal, both in terms of implementation and computational cost. The proposed methodology is fully unsupervised, based solely on color image features. Initially, the shadow region is automatically extracted by a segmentation algorithm based on Electromagnetic-Like Optimization. Superpixel-based segmentation is performed and pairs of shadowed and non-shadowed regions, which are nearest neighbors in terms of their color content, are identified as parts of the same object. The shadowed part of each pair is relighted by means of histogram matching, using the content of its non-shadowed counterpart. Quantitative and qualitative experiments on well-recognized publicly available benchmark datasets are conducted to evaluate the performance of proposed methodology in comparison to state-of-the-art methods. The results validate both its efficiency and effectiveness, making evident that solving the shadow removal problem does not necessarily require complex deep learning-based solutions.

show abstract

Learning-Based Shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds

Cited by 5 publications

References 41 publications

Airborne-Shadow: Towards Fine-Grained Shadow Detection in Aerial Imagery

Airborne-Shadow: Towards Fine-Grained Shadow Detection in Aerial Imagery

Shadow Detection of Remote Sensing Image by Fusion of Involution and Shunted Transformer

SUShe: simple unsupervised shadow removal

Contact Info

Product

Resources

About