Shadow modelling based upon Rayleigh scattering and Mie theory (original) (raw)

Shadow Detection via Rayleigh Scattering and Mie Theory

In this paper, we present a method to detect shadows in outdoor scenes. Here, we note that the shadow areas correspond to the diffuse skylight which arises from the scattering of the sunlight by particles in the atmosphere. This yields a treatment in which shadows in the image can be viewed as a linear combination of scattered light obeying Rayleigh scattering and Mie theory. This treatment allows for the computation of a ratio which permits casting the problem of recovering the shadowed areas in the image into a clustering setting making use of active contours. We illustrate the utility of the method for purposes of detecting shadows in real-world imagery and compare our results against a number of alternatives elsewhere in the literature.

Adding geometrical terms to shadow detection process

EUSIPCO (14th European Signal …, 2006

The elimination of strong shadow in outdoor scenes containing human activity is addressed in the paper. The main contribution of the introduced method is the integration of geometrical information into the shadow detection process. This novel approach takes into account the collinearity of shadow and light direction and completed with a simple colour based pre-filtering. The final classification step is carried out via a Bayesian iteration scheme which is general enough to handle further characteristics of the problem: weak shadow and reflection.

Active color image analysis for recognizing shadows

1992

Many existing computer vision modules assume that shadows in an image have been accounted for prior to their application. In spite of this, relatively little work has been done on recognizing shadows or on recognizing a single surface material when directly lit and in shadow. This is in part because shadows cannot be infallible recognized until a scene's lighting and geometry are known. However, color is a strong cue to the presence of shadows. We present a general color image segmentation algorithm whose output is amenable to the recovery of shadows as determined by an analysis of the physics of shadow radiance. Then, we show how an observer that can cast its own shadows can infer enough information about a scene's illumination to refine the segmentation results to determine where the shadows in the scene are with reasonable confidence. Having an observer that can actively cast shadows frees us from restrictive assumptions about the scene illumination or the reliance on high level scene knowledge. We present results of our methods on images of complex indoor and outdoor scenes.

Shadow detection using a physical basis

2008 IEEE Instrumentation and Measurement Technology Conference, 2008

Shadow detection is an important aspect of foreground/background classification. Many techniques exist, most of them assuming that only the intensity changes under shadow. In this paper we show that in most practical indoor and outdoor situations there will also be a color shift. We propose an algorithm for estimating this color shift from the images, and using it to remove shadow pixels. The proposed algorithm is compared experimentally to an existing algorithm using real image sequences. Results show a significant improvement of performance.

A Novel Approach for Cast Shadow Modelling and Detection

Several shadow detection and removal algorithms have been proposed to distinguish between objects and their shadows for computer vision applications, as the design of a fast and efficient algorithm remains a challenge. In this work, based on a physically-derived hypothesis for shadow identification, novel, simple and fast shadow detection algorithms are proposed and implemented in the spatial (Pixel) and frequency (Fourier) domains. It is shown that the algorithms effectively remove shadows under various lighting and environmental conditions. The proposed algorithms are able to detect shadows in both umbra and penumbra neighborhoods.t Available

Shadow Detection based on Colour Segmentation and Estimated Illumination

Procedings of the British Machine Vision Conference 2011, 2011

In this paper we show how to improve the detection of shadows in natural scenes using a novel combination of colour and illumination features. Detecting shadows is useful because they provide information about both light sources and the shapes of objects thereby illuminated. Recent shadow detection methods use supervised machine learning techniques with input from colour and texture features extracted directly from the original images (e.g. Lalonde et al. ECCV 2010, Zhu et al. CVPR 2010. It seems sensible to augment these with estimates of scene illumination, as can be obtained with an intrinsic image extraction algorithm. Intrinsic image extraction separates the illumination and reflectance components in a scene, and the resulting illumination maps contain robust intensity change features at shadow boundaries. In this paper, we make two main contributions. First we improve upon existing methods for extracting illumination maps. Second we show how to use these illumination maps together with colour segmentation to extend the Lalonde's approach to shadow detection. Illumination maps are extracted using a steerable filter framework based on global and local correlations in low and high frequency bands respectively. The illumination and colour features so extracted are then input to a decision tree trained to detect shadow edges using AdaBoost. We tested variations of our proposed approach on two public databases of natural scenes. This study showed that our approach improves on that of Lalonde both in terms of sensitivity to shadow edges and rejection of false positives. Following Lalonde we show that our detection results are further improved by imposing an edge continuity constraint via a conditional random field (CRF) model.

Automatic Shadow Detection and Removal from

We present a framework to automatically detect and remove shadows in real world scenes from a single image. Previous works on shadow detection put a lot of effort in designing shadow variant and invariant hand-crafted features. In contrast, our framework automatically learns the most relevant features in a supervised manner using multiple convolutional deep neural networks (ConvNets). The features are learned at the super-pixel level and along the dominant boundaries in the image. The predicted posteriors based on the learned features are fed to a conditional random field model to generate smooth shadow masks. Using the detected shadow masks, we propose a Bayesian formulation to accurately extract shadow matte and subsequently remove shadows. The Bayesian formulation is based on a novel model which accurately models the shadow generation process in the umbra and penumbra regions. The model parameters are efficiently estimated using an iterative optimization procedure. Our proposed framework consistently performed better than the state-of-the-art on all major shadow databases collected under a variety of conditions.

Shadow identification for digital imagery using colour and texture cues

IET Image Processing, 2012

Shadows cause a significant problem for automated systems which attempt to understand scenes, since shadow boundaries may be incorrectly recognised as a material change, and incorrectly recognised as an object. Shadow identification is therefore an important pre-processing step for applications such as shadow removal, shadow invariant object recognition and shadow invariant object tracking. Many existing shadow identification methods are often limited by the types of shadow boundaries (penumbra) which can be found, by the density (darkness) of the shadows and by the type of surface texture on which the shadows are cast. In addition many of these methods are limited to a specific type of scene, while others result in high levels of false positive (FP) shadow identification. To address these problems, a novel algorithm for automatic shadow identification is proposed, which makes use of a new tree-structured segmentation algorithm for candidate shadow region identification, as well as a combination of colour illumination invariance and texture analysis for shadow verification. The method is tested on a number of indoor and outdoor images exhibiting different types of shadows, surfaces and illumination sources. These results indicate that the proposed method performs well against the state of the art; in particular, the rate of FP identification is reduced from 26 to below 13% when compared with using illumination invariance alone.

Shadow detection approach combining spectral and geometrical properties

2012 International Conference on Multimedia Computing and Systems, 2012

In applications requiring objects extraction, cast shadows induce shape distortions and object fusions interfering performance of high level algorithms in video surveillance system. Shadow elimination allows to improve the performances of video object extraction, tracking and description tools. In this work, an approach to automatic shadow detection and extraction is proposed, which operates multiple properties derived from spectral, geometric and temporal analysis of shadows. A generic model that chooses the candidate shadow regions based on shadow direction is developed. Then, the validity of detected regions as shadows is verified using the capability of approach that allows associating to each photometric pixel its equivalent part of the shadow, while integrating the various parameters related to illumination and the surface. Simulation results show that the proposed approach is robust and efficient in detecting shadows for different background and changeable illumination conditions.