Shadow Detection Algorithm Research Articles

효과적인 그림자 복원을 위한 Matlab 기반의 그림자 검출 알고리즘 비교분석

디지털 영상에서 그림자는 객체와 광원 간의 상호작용으로 생성되는 표면 특징으로 장면이해를 위한 유용한 정보임에도 불구하고 객체 검출, 추적 및 인식 등의 컴퓨터 비전 절차에서 부정적인 영향을 미친다. 그림자 검출은 디지털 영상분석을 위한 전처리 과정에서 필수적으로 적용되어야 하며, 효과적인 그림자 복원을 위해 정확도가 높은 그림자 검출이 수행되어야 한다. 본 논문에서는 기존의 그림자 검출 알고리즘들에 적용된 컬러 공간들을 기술하고, 선행연구 알고리즘들의 비교분석을 통해 효과적인 그림자 검출 방법론을 고찰하였다. 기존의 그림자 검출 알고리즘들은 다양한 컬러 공간의 밝기 성분 영상을 이용하는 공통적인 특징을 가지고 있으며, 그림자 추정은 실험적 경험으로 획득한 다양한 임계값이 적용되었다. 따라서, 영상의 밝기 정보 이외의 윤곽, 질감 및 그림자와 그림자가 아닌 영역 간의 통계적 특성을 이용한 그림자 검출과 적응적인 임계값 추정 연구가 함께 수반되어야 한다.

A Radiative Transfer Model-Based Multi-Layered Regression Learning to Estimate Shadow Map in Hyperspectral Images

The application of Empirical Line Method (ELM) for hyperspectral Atmospheric Compensation (AC) premises the underlying linear relationship between a material’s reflectance and appearance. ELM solves the Radiative Transfer (RT) equation under specialized constraint by means of in-scene white and black calibration panels. The reflectance of material is invariant to illumination. Exploiting this property, we articulated a mathematical formulation based on the RT model to create cost functions relating variably illuminated regions within a scene. In this paper, we propose multi-layered regression learning-based recovery of radiance components, i.e., total ground-reflected radiance and path radiance from reflectance and radiance images of the scene. These decomposed components represent terms in the RT equation and enable us to relate variable illumination. Therefore, we assume that Hyperspectral Image (HSI) radiance of the scene is provided and AC can be processed on it, preferably with QUick Atmospheric Correction (QUAC) algorithm. QUAC is preferred because it does not account for surface models. The output from the proposed algorithm is an intermediate map of the scene on which our mathematically derived binary and multi-label threshold is applied to classify shadowed and non-shadowed regions. Results from a satellite and airborne NADIR imagery are shown in this paper. Ground truth (GT) is generated by ray-tracing on a LIDAR-based surface model in the form of contour data, of the scene. Comparison of our results with GT implies that our algorithm’s binary classification shadow maps outperform other existing shadow detection algorithms in true positive, which is the detection of shadows when it is in ground truth. It also has the lowest false negative i.e., detecting non-shadowed region as shadowed, compared to existing algorithms.

Simple and effective cloud- and shadow-detection algorithms for Landsat and Worldview images

Many conventional cloud- and shadow-detection algorithms require meta-data such as sun angle and date of image collection. Moreover, detection results can vary a lot in actual images. We present simple and effective algorithms that do not require meta-data for detecting clouds and shadows in Landsat and Worldview images. Comparison with existing state-of-the-art algorithms, including a deep learning-based algorithm as well as a commercial algorithm, using actual satellite images, shows that the simple algorithms have comparable or even better performance than existing algorithms.

Acoustic Shadow Detection: Study and Statistics of B-Mode and Radiofrequency Data

An acoustic shadow is an ultrasound artifact occurring at boundaries between significantly different tissue impedances, resulting in signal loss and a dark appearance. Shadow detection is important as shadows can identify anatomical features or obscure regions of interest. A study was performed to scan human participants (N = 37) specifically to explore the statistical characteristics of various shadows from different anatomy and with different transducers. Differences in shadow statistics were observed and used for shadow detection algorithms with a fitted Nakagami distribution on radiofrequency (RF) speckle or cumulative entropy on brightness-mode (B-mode) data. The fitted Nakagami parameter and entropy values in shadows were consistent across different transducers and anatomy. Both algorithms utilized adaptive thresholding, needing only the transducer pulse length as an input parameter for easy utilization by different operators or equipment. Mean Dice coefficients (± standard deviation) of 0.90 ± 0.07 and 0.87 ± 0.08 were obtained for the RF and B-mode algorithms, which is within the range of manual annotators. The high accuracy in different imaging scenarios indicates that the shadows can be detected with high versatility and without expert configuration. The understanding of shadow statistics can be used for more specialized techniques to be developed for specific applications in the future, including pre-processing for machine learning and automatic interpretation.

Shadow Detection Method Based on HMRF with Soft Edges for High-Resolution Remote-Sensing Images

Shadow detection is a crucial task in high-resolution remote-sensing image processing. Various shadow detection methods have been explored during the last decades. These methods did improve the detection accuracy but are still not robust enough to get satisfactory results for failing to extract enough information from the original images. To take full advantage of various features of shadows, a new method combining edges information with the spectral and spatial information is proposed in this paper. As known, edge is one of the most important characteristics in the high-resolution remote-sensing images. Unfortunately, in shadow detection, it is a high-risk strategy to determine whether a pixel is the edge or not strictly because intensity values on shadow boundaries are always between those in shadow and non-shadow areas. Therefore, a soft edge description model is developed to describe the degree of each pixel belonging to the edges or not. Sequentially, the soft edge description is incorporating to a fuzzy clustering procedure based on HMRF (Hidden Markov Random Fields), in which more appropriate spatial contextual information can be used. More concretely, it consists of two components: the soft edge description model and an iterative shadow detection algorithm. Experiments on several remote sensing images have shown that the proposed method can obtain more accurate shadow detection results.

An automatic shadow detection method for high-resolution remote sensing imagery based on polynomial fitting

ABSTRACTMost existing shadow detection models and algorithms require extensive calculations and have difficulties effectively removing features, such as water bodies, some dark objects and bluish ground objects. In this paper, we propose a high-resolution automatic shadow extraction algorithm based on the process of histogram fitting. First, the histogram of the whole image is fitted by fourth and fifth-degree polynomials according to the histogram difference of the near-infrared bands of different shadow areas in the remotely sensed image. Second, the shadow area is preliminarily extracted based on the relationships between the shadow features of the remote sensing image and the intersections of the fourth- and fifth-degree polynomials. Then, the normalized difference water index (NDWI) is applied to extract the water bodies. Finally, to obtain the shaded area, the scanning line seed filling algorithm is applied to remove the water bodies falsely detected as shadows in the preliminary shading extraction. The proposed algorithm is evaluated by using the various high-resolution images including GaoFen-1 (GF-1), GaoFen-2 (GF-2), QuickBird2, and ZiYuan-3 (ZY-3), as well as an elaborate comparison to histogram threshold segmentation algorithms such as Component 3 (C3) algorithm, multi-elements extraction algorithm multi-band detection algorithm, and spectral correlation algorithm based on spectral features. The results of experiment showed that the proposed algorithm could extract the shadows of various images, achieve satisfied results, and completely remove water bodies.

A Self-Supervised Learning Method for Shadow Detection in Remote Sensing Imagery

Recent research progress in shadow detection has leveraged the development of remote sensing and computer vision. Since shadows of buildings, trees, bridges in one image can provide useful information about the scene to help people understand the shape, feature or estimate their locations and orientations of original objects, especially for damaged objects. In this study, a novel shadow detection algorithm for remote sensing imagery, called self-supervised learning method is proposed. The aim of this work is to generate shadow ratio threshold automatically without human interaction. To alleviate the traditional drawbacks of shadow detection, we fully combine supervised and unsupervised shadow detection method to suggest a self-supervised learning method, which supports us a strongly clue with establishing the relation of shadow and its original object. Subsequently, we benefit from gray-scale histogram to extract shadow segments, then shadow outlines are obtained. Finally, we assess the shadow detection performance of the proposed approach by comparing our results with the state-of-the-art methods. The results reveal the applicability and precision of the proposed self-supervised learning shadow detection technique.

<italic>A Priori</italic> Surface Reflectance-Based Cloud Shadow Detection Algorithm for Landsat 8 OLI

Prior knowledge of the background land surface reflectance (LSR) constitutes one of the most important factors affecting the precision of cloud shadow detection. To resolve this problem, a surface reflectance-based cloud shadow detection (SRCSD) algorithm is proposed for multitemporal Landsat images. Monthly surface reflectance data sets constructed from MODIS surface reflectance products (MOD09A1) were used to provide the background LSR for cloud shadow detection. Based on the background LSR, the possible variation in the top of atmosphere (TOA) reflectance for each clear pixel can be estimated using the radiative transfer equation under different atmospheric conditions. If a pixel has a smaller TOA reflectance than the minimum value of the possible range under clear conditions, it is identified as being shadow covered. One hundred and twenty-five Landsat 8 Operational Land Imager scenes covered by various surface types were selected to evaluate the feasibility of the algorithm. A validation using manual cloud shadow masks showed that the average producer’s accuracy and user’s accuracy were approximately 0.805 and 0.893, respectively. A comparison of the results of the SRCSD algorithm with those of an object-based cloud shadow detection algorithm (Fmask) recently developed for Landsat images revealed that SRCSD generally detects cloud shadows better than Fmask. The most significant improvement of the SRCSD algorithm is the better detection capability for thin and broken cloud shadows, and this algorithm can be extended to multiple types of satellite data after proper modification.

Cast shadow detection based on the YCbCr color space and topological cuts

In order to solve the moving objects shadow problem in foreground extraction of surveillance video images, a new cast shadow detection algorithm based on the YCbCr color space and topological cutting was proposed. Preliminary shadow removal was first performed based on the difference of the three components in the YCbCr color space of shadows and foregrounds. Besides, the maximum-flow/minimum-cut algorithm for image segmentation was optimized considering the topological constraints. The optimal segmentation of the foreground image was obtained during the continuous updating of the label. Finally, two sets of experiments were performed in video image sequences, including real surveillance videos and a well-known benchmark test set. By comparing with two other existing algorithms, the feasibility and effectiveness of the cast shadow detection algorithm were verified by the smooth border and higher recognition accuracy. In addition, the adaptability to foreground object density and different light intensities was measured in an airport terminal, showing that this algorithm can provide a high quality of moving foreground detection in surveillance video images and can be applied in monitoring of public places.

A robust object-based shadow detection method for cloud-free high resolution satellite images over urban areas and water bodies

Unwanted contrast in high resolution satellite images such as shadow areas directly affects the result of further processing in urban remote sensing images. Detecting and finding the precise position of shadows is critical in different remote sensing processing chains such as change detection, image classification and digital elevation model generation from stereo images. The spectral similarity between shadow areas, water bodies, and some dark asphalt roads makes the development of robust shadow detection algorithms challenging. In addition, most of the existing methods work on pixel-level and neglect the contextual information contained in neighboring pixels. In this paper, a new object-based shadow detection framework is introduced. In the proposed method a pixel-level shadow mask is built by extending established thresholding methods with a new C4 index which enables to solve the ambiguity of shadow and water bodies. Then the pixel-based results are further processed in an object-based majority analysis to detect the final shadow objects. Four different high resolution satellite images are used to validate this new approach. The result shows the superiority of the proposed method over some state-of-the-art shadow detection method with an average of 96% in F-measure.

Efficient shadow detection by using PSO segmentation and region-based boundary detection technique

The presence of shadows in satellite images is inevitable, and hence, shadow detection and removal has become very essential. In this paper, a shadow detection algorithm based on PSO has been used to identify shadows in very high-resolution satellite images. The image is first preprocessed using a bilateral filter to eliminate the noise followed by which PSO-based shadow segmentation is used to segment the shadow regions. Canny edge detection is done to identify the edges of the objects in the image. The results of the edge detection and segmentation are combined using a logical operator to generate the final shadow segmented image with well-defined boundaries. The accuracy is validated using precision and recall parameters.

A Survey on Shadow Detection Techniques in a Single Image

Shadows are inescapable elements in a scene formed due to the presence of an object between the light source and the surface on which it is cast. Appearance of shadows often cause severe issues in computer vision applications like object extraction, surveillance etc. Researchers have made effort to device techniques to locate and remove shadows from images and videos. This paper attempts to survey the various shadow detection algorithms for a single image. For the purpose of survey, the notable research work in the literature is classified under five major categories: invariant-based detection, feature-based detection, region-based detection, color model based detection and interactive shadow detection. The survey also includes a qualitative and quantitative evaluation of the methods discussed. As outcomes of the survey, it is observed that, (i) though the works discussed under each of these categories are capable of detecting shadows in different scenarios, the accuracy and time taken need further improvements to make the shadow detection process acceptable for practical applications; (ii) detection of self shadows and heavily scattered shadows are challenging;(iii) the risk of misclassifying dark objects as shadows should be addressed; (iv) soft shadows that span multiple surfaces pose challenge in accurate detection of shadows. DOI: http://dx.doi.org/10.5755/j01.itc.47.1.15012

An Extended Moving Target Detection Approach for High-Resolution Multichannel SAR-GMTI Systems Based on Enhanced Shadow-Aided Decision

This paper develops a framework based on enhanced shadow-aided decision for multichannel synthetic aperture radar-based ground moving target indication system according to the relationships between the moving target and its shadow information in position, dimensions, and intensity. As a sort of feature information available, the moving target shadow may improve the ground target detection performance. A critical precondition for shadow utilization is to obtain the good detection performance for the moving target shadow. However, shadow detection performance will deteriorate inevitably as a result of target motion that blurs its shadow. To address this issue, a knowledge-aided shadow detection algorithm with adaptive thresholds is proposed to improve the shadow detection performance in the developed framework. Furthermore, the theoretical performance analysis is performed, which indicates that the proposed knowledge-aided shadow detection algorithm has a better performance than that of the conventional shadow detection algorithm with a fixed threshold. Finally, numerical simulation experiments are presented to demonstrate that the developed framework can obtain good results for extended ground moving target detection.

Extended Random Walker for Shadow Detection in Very High Resolution Remote Sensing Images

The existence of shadows in very high resolution satellite images obstructs image interpretation and the following applications, such as target detection and recognition. Traditional shadow detection methods consider only the pixel-level properties, such as color and intensity of image pixels, and thus, may produce errors around object boundaries. To overcome this problem, a novel shadow detection algorithm based on extended random walker (ERW) is proposed by jointly integrating both shadow property and spatial correlations among adjacent pixels. First, a set of training samples is automatically generated via an improved Otsu-based thresholding method. Then, the support vector machine is applied to obtain an initial detection map, which categorizes all the pixels in the scene into shadow and nonshadow. Finally, the initial detection map is refined with the ERW model, which can simultaneously characterize the shadow property and spatial information in satellite images to further improve shadow detection accuracy. Experiments performed on five real remote sensing images demonstrate the superiority of the proposed method over several state-of-the-art methods in terms of detection accuracy.

Cast Shadow Detection to Quantify the Aerosol Optical Thickness for Atmospheric Correction of High Spatial Resolution Optical Imagery

The atmospheric correction of optical remote sensing data requires the determination of aerosol and gas optical properties. A method is presented which allows the detection of the aerosol scattering effects from optical remote sensing data at spatial sampling intervals below 5 m in cloud-free situations from cast shadow pixels. The derived aerosol optical thickness distribution is used for improved atmospheric compensation. In a first step, a novel spectral cast shadow detection algorithm determines the shadow areas using spectral indices. Evaluation of the cast shadow masks shows an overall classification accuracy on an 80% level. Using the such derived shadow map, the ATCOR atmospheric compensation method is iteratively applied on the shadow areas in order to find the optimum aerosol amount. The aerosol optical thickness is found by analyzing the physical atmospheric correction of fully shaded pixels in comparison to directly illuminated areas. The shadow based aerosol optical thickness estimation method (SHAOT) is tested on airborne imaging spectroscopy data as well as on photogrammetric data. The accuracy of the reflectance values from atmospheric correction using the such derived aerosol optical thickness could be improved from 3–4% to a level of better than 2% in reflectance for the investigated test cases.

Sample-based integrated background subtraction and shadow detection

This paper presents an integrated background subtraction and shadow detection algorithm to identify background, shadow, and foreground regions in a video sequence, a fundamental task in video analytics. The background is modeled at pixel level with a collection of previously observed background pixel values. An input pixel is classified as background if it finds the required number of matches with the samples in the model. The number of matches required with the samples in the model to classify an incoming pixel as background is continuously adapted at pixel level according to the stability of pixel observations over time, thereby making better use of samples in dynamic as well as stable regions of the background. Pixels which are not classified as background in the background subtraction step are compared with a pixel-level shadow model. The shadow model is similar to the background model in that it consists of actually observed shadowed pixel values. Sample-based shadow modeling is a novel approach that solves the highly difficult problem of accurately modeling all types of shadows. Shadow detection by matching with the samples in the model exploits the recurrence of similar shadow values at pixel level. Evaluation tests on various public datasets demonstrate near state-of-the-art background subtraction and state-of-the-art shadow detection performance. Even though the proposed method contains shadow detection processing, the implementation cost is small compared with existing methods.

Evaluation of shadow features

Shadow features such as colour ratio, texture, and chromaticity have proved to be quite effective in shadow detection. Many shadow detection methods have been proposed on the basis of different features. However, previous works for shadow detection mainly focus on designing an effective classifier for existing shadow features, but pay less attention on the analysis of shadow features themselves. The majority of studies simply report the final shadow detection results rather than make an evaluation on each feature. Readers often do not know which features are more effective or whether these shadow features are complementary. The following problems are still unsolved: the robustness of each feature, which feature plays the most important role in a detection method, and what is the best performance that current features can reach. The purpose of this study is to answer these questions, and the authors hope that this study can offer guidance for future shadow detection algorithms via the evaluation of frequently used shadow features. Several useful and interesting conclusions are obtained after conducting extensive comparison experiments on a large dataset.

An improvement for the foreground recognition method using shadow removal technique for indoor environments

In this paper, we present an efficient and simple shadow detection algorithm for indoor environments, as well as give a brief description on the advantages of this method. In this method, we use three types of approaches: image enhancement, chromaticity consistency, and gradient features. Multiple shadow direction is becoming an increasingly challenging task for many moving shadow detection algorithms because some objects have large self-shadows. Our system is able to achieve good performance solving spread shadow problems in indoor scenes, leading to improved foreground segmentation in surveillance scenarios. The image enhancement approach is first employed to input images to generate high-quality images for artificial light source indoor areas. Afterwards, the chromaticity information is utilized to create a mask of possible candidate shadow pixels. Subsequently, gradient features are applied to remove foreground pixels that have been incorrectly included in the mask. In comparison with existing algorithms, the proposed method can correctly detect and remove shadow pixels to identify original foreground shapes without distortion for delivering object recognition and tracking tasks.

Terrestrial Hyperspectral Image Shadow Restoration through Lidar Fusion

Acquisition of hyperspectral imagery (HSI) from cameras mounted on terrestrial platforms is a relatively recent development that enables spectral analysis of dominantly vertical structures. Although solar shadowing is prevalent in terrestrial HSI due to the vertical scene geometry, automated shadow detection and restoration algorithms have not yet been applied to this capture modality. We investigate the fusion of terrestrial laser scanning (TLS) spatial information with terrestrial HSI for geometric shadow detection on a rough vertical surface and examine the contribution of radiometrically calibrated TLS intensity, which is resistant to the influence of solar shadowing, to HSI shadow restoration. Qualitative assessment of the shadow detection results indicates pixel level accuracy, which is indirectly validated by shadow restoration improvements when sub-pixel shadow detection is used in lieu of single pixel detection. The inclusion of TLS intensity in existing shadow restoration algorithms that use regions of matching material in sun and shade exposures was found to have a marginal positive influence on restoring shadow spectrum shape, while a proposed combination of TLS intensity with passive HSI spectra boosts restored shadow spectrum magnitude precision by 40% and band correlation with respect to a truth image by 45% compared to existing restoration methods.

Comparative Analysis of Single Image Shadow Detection and Removal in Aerial Images

The article for the specific region segmentation is discussed here. This paper compares the work done on the contour model based shadow detection algorithm with the random field model based shadow detection method. The contouring based shadow detection model adapts the traditional geometric active contours that the contour is steadily subjective toward the shaded region and the shadowy regions in the picture. The shadow region segmentation follows the post processing for optimal threshold calculation. The complexity metric is constructed to separate the boundary of true shadow regions. Whereas the random field model based on shadow exposure process uses a superficial outside descriptor, and colour shade area, to describe the colour surface variants. The conditional random field is combined with the colour descriptors to locate lighting pair and acquire the shaded portion. The shadow region riddance by neighbourhood shade constancy utilizes anisotropic dispersion to guess the local image pixel illumination in shadow region and provides the better performance in shadow region illumination enhancement.