Automatic Glare Detection via Photometric, Geometric, and Global Positioning Information

Abstract

Glare due to sunlight, moonlight, or other light sources can be a serious impediment during autonomous or manual driving. Automatically detecting the presence, location, and severity of such glare can be of critical importance for an autonomous driving system, which may then give greater priority to other sensors or cues/parts of the scene. We present an algorithm for automatic real-time glare detection that uses a combination of: (1) the intensity, saturation, and local contrast of the input frame; (2) shape detection; and (3) solar azimuth and elevation computed based on the position and heading information from the GPS (used under daylight conditions). These data are used to generate a glare occurrence map that indicates the center location(s) and extent(s) of the glare region(s). Testing on a variety of daytime and nighttime scenes demonstrates that the proposed system is effective at glare detection and is capable of real-time operation.

Identifying Document Images with Glare Using Global and Localized Feature Fusion

“…Previous works on glare images were mainly focused on glare detection in outdoor scenes for navigation [1,2,3], night time photography [4], mitigating veiling glare [5] in high dynamic range images. Unlike natural photos, glare on documents are harder to detect because of the predominately white background.…”

An algorithm for glare detection via photometric, colorimetric, and global positioning features

“…of the input image. Our brightness feature map, denoted by V ∈ Z W ×H is given by the lightness values normalized to span the range [0, 1]: (9) for all pixel coordinates x and y in the ranges and…”

“…Although the detection of glare is an important problem, there are relatively few publications on glare detection using digital cameras. [3][4][5][6][7][8][9][10] The existing approaches to glare detection generally rely on one or two simplistic image properties, followed by ad-hoc thresholding. The obvious and most commonly used feature is light intensity, [3,4] which can certainly detect the light source(s), but which cannot differen-tiate these sources from other bright regions (e.g., clouds), as demonstrated in Figure 1.…”

“…[5,6] However, the color of the sun changes based on its elevation; thus, hue alone often fails to delineate the boundaries of the glare region(s), particularly when the image is subject to compression, as demonstrated in Figure 2. In our previous work, [9] we used saturation instead of hue, taking advantage of the fact that glare regions typically have low saturation; however, many other regions in the scene also have low saturation. Instead of analyzing the scene, another class of approach has focused on analyzing an image of the driver's face.…”

Fast Glare Detection in Document Images

“…Detection results can increase the text recognition quality capturing a better image without glares. Several methods have been proposed for image segmentation, but most of them focus on detecting glare in the outdoor environment [2], [3]. Also, the size of the glare region in the document image implies the usage of up to 40% of the image as the context for detection, which demands great computational resources.…”