A Multispectral Bidirectional Reflectance Distribution Function Study of Human Skin for Improved Dismount Detection
A Multispectral Bidirectional Reflectance Distribution Function Study of Human Skin for Improved Dismount Detection
复制标题
用于改进下车检测的人体皮肤多光谱双向反射率分布函数研究
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
B. M. Koch
中科院分区：
文献类型：
--
作者：
B. M. Koch
反恐战争带来了许多挑战，其中之一是战斗人员不穿标准制服，融入城市人口。为了协助敌人的探测和跟踪，获取光谱信息的成像系统揭示了场景中曾经无法探测到的许多特征。我们的研究利用多光谱技术来更好地利用自然现象来识别战斗人员。2008年，美国空军理工学院的传感器开发研究小组开始利用皮肤的光谱特性来检测和分类人类。此后，开发了多光谱皮肤检测系统，以利用人体皮肤在电磁波谱可见光和近红外波段的光学特性。基于规则的检测器，从光谱上分析图像，目前将其皮肤像素选择标准基于漫反射皮肤模型。然而，当在太阳直射下观察皮肤时，皮肤上的闪光是常见的，这表明有反射性。具有高度镜面反射的皮肤区域会导致误判。我们表明，皮肤的特点是漫反射和镜面反射，这两个组件都依赖于场景配置。虽然我们不能总是依赖于人直接面对相机或恒定的照明条件，但重要的是要根据场景的变化灵活地使用基于规则的检测器。我们的研究更好地表征了皮肤反射率作为源和检测器角度位置的函数，以改进基于规则的检测器。我们的研究方法首先通过直接测量来表征皮肤的镜面反射率。双向反射分布函数模型与测量的拟合误差约为8.2%，使我们能够将镜面反射成分纳入现有的漫反射模型中。一种提取数字化三维物体表面反射率的方法，为模拟具有代表性的检测场景的许多不同条件铺平了道路。结果是一种模拟改变场景配置对皮肤反射的影响和我们可靠地进行皮肤检测的能力的方法。
The war on terrorism has brought with it many challenges, one of which being combatants wearing no standard uniform and blending into the urban population. To assist with enemy detection and tracking, imaging systems that acquire spectral information bring to light many features in a scene which were once undetectable. Our research utilizes multispectral technology to better exploit naturally occurring phenomena to identify combatants. In 2008, the Sensors Exploitation Research Group at the Air Force Institute of Technology began using spectral properties of skin for the detection and classification of humans. Since then, a multispectral skin detection system was developed to exploit the optical properties of human skin at wavelengths in the visible and near infrared region of the electromagnetic spectrum. A rules-based detector, analyzing an image spectrally, currently bases its skin pixel selection criteria on a diffuse skin reflectance model. However, when observing skin in direct view of the sun, a glint of light off skin is common and indicates specularity. The areas of skin with a high degree of specular reflectance result in misdetections. We show that skin is characterized by diffuse and specular reflectance, with both components dependent on the scene configuration. While we cannot always rely on the person to directly face the camera or have constant illumination conditions, it is important to have flexibility with the rules-based detector as the scene changes. Our research better characterizes skin reflectance as a function of source and detector angular locations to improve on the rules-based detector. Our research approach first characterizes skin’s specular reflectance with direct measurements. The fitting of a bidirectional reflectance distribution function model to iv the measurements with approximately 8.2% error allows us to incorporate the specular reflection component into the existing diffuse model. A method for extracting surface reflectance of a digitized three dimensional subject, paves the way for simulating many different conditions for a representative detection scenario. The result is a method to model the effects that changing scene configuration has on skin reflection and our ability to reliably do skin detection.