Use of Gradient-Based Shadow Detection for Estimating Environmental Illumination Distribution

Abstract

Environmental illumination information is necessary to achieve a consistent integration of virtual objects in a given image. In this paper, we present a gradient-based shadow detection method for estimating the environmental illumination distribution of a given scene, in which a three-dimensional (3-D) augmented reality (AR) marker, a cubic reference object of a known size, is employed. The geometric elements (the corners and sides) of the AR marker constitute the candidate’s shadow boundary; they are obtained on a flat surface according to the relationship between the camera and the candidate’s light sources. We can then extract the shadow regions by collecting the local features that support the candidate’s shadow boundary in the image. To further verify the shadows passed by the local features-based matching, we examine whether significant brightness changes occurred in the intersection region between the shadows. Our proposed method can reduce the unwanted effects caused by the threshold values during edge-based shadow detection, as well as those caused by the sampling position during point-based illumination estimation.

Shadow Detection in Still Road Images Using Chrominance Properties of Shadows and Spectral Power Distribution of the Illumination

“…This observation is effective for applications where the spectral power distribution of the illumination (SPD) is similar for both shadowed and non-shadowed regions; thus, the surface color components vary linearly. Approaches based on this consideration are known as color-invariant methods and they are widely used in ADAS applications exploiting different color spaces such as red-green-blue (RGB) [26,27], normalized RGB [28], Hue-Saturation-Intensity (HSI) [29,30], Hue-Saturation-Value (HSV) [11,16,31], Improved-Hue-Saturation-Luminance (IHSL) [32], YUV [33][34][35], c1c2c3 [6], and l1l2l3 [36]. However, in outdoor scenes, the illumination is composed of sunlight and skylight, which have different SPDs.…”

User-Aware Audio Marker Using Low Frequency Ultrasonic Object Detection and Communication for Augmented Reality

“…In other words, each fingertip acted as a virtual marker to interact with virtual objects at close distances. Despite its usefulness for some AR applications, this approach could be considerably distracting under visual conditions affected by illumination or occlusion [6][7][8]. While recent AR applications tried to recognize visual environments without using a marker, in order to deploy virtual objects in natural ways [9], such attempts required substantial computations of the AR device; thus, their use was limited to a certain AR scenario [10].…”

Using Human Objects for Illumination Estimation and Shadow Generation in Outdoor Environments

“…Environmental illumination information is used to render CG objects with coherent virtual shadows. Many methods have been introduced for generating the shadows of CG objects according to the light distribution of indoor and outdoor environments, enabling users to have a more realistic AR experience [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. The goal of our study was to estimate the outdoor illumination information for a scene containing a human object.…”

“…In previous studies on the estimation of indoor illumination information [6][7][8], it has been important to determine the sampling positions on the shadow surface. Therefore, three-dimensional (3D) model information about the object that casts shadows is required, and then a sampling strategy with which to choose the sample points on the shadow regions according to the object's geometry.…”