Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance

نویسندگان

  • Hang Zhang
  • Kristin J. Dana
  • Ko Nishino
چکیده

Images are the standard input for vision algorithms, but one-shot infield reflectance measurements are creating new opportunities for recognition and scene understanding. In this work, we address the question of what reflectance can reveal about materials in an efficient manner. We go beyond the question of recognition and labeling and ask the question: What intrinsic physical properties of the surface can be estimated using reflectance? We introduce a framework that enables prediction of actual friction values for surfaces using one-shot reflectance measurements. This work is a first of its kind vision-based friction estimation. We develop a novel representation for reflectance disks that capture partial BRDF measurements instantaneously. Our method of deep reflectance codes combines CNN features and fisher vector pooling with optimal binary embedding to create codes that have sufficient discriminatory power and have important properties of illumination and spatial invariance. The experimental results demonstrate that reflectance can play a new role in deciphering the underlying physical properties of real-world scenes.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

DIFFUSE REFLECTANCE MEASUREMENTS FROM DIFFERENT SURFACES

Relative diffuse reflection measurements from the original and ground surfaces using a He-Ne laser are reported. The intensity measurements for the metallic, transparent dielectric, matte plastic surfaces and colored papers are presented. Our results indicate that among metallic surfaces tested, aluminum has the highest diffuse reflectance; while the original stainless steel surface shows the l...

متن کامل

SOIL SPECTRAL PROPERTIES OF ARID REGION, KASHAN AREA, IRAN

This study determined some spectral characteristics and relationship between Landsat spectral reflectance and soil surface color in the arid region of Iran (Kashan). The study carried out in the kashan area that covers 90000 ha. Consisting of mountain, hills and flood plain. Enhanced Thematic Mapper (ETM+) data collected on July 2002 were used for this research. The color composite images produ...

متن کامل

Improving the clay, silt and sand of soil prediction by removing the influence of moisture on reflectance using EPO

Moisture is one of the most important factors that affects soil reflectance spectra. Time and spatial variability of soil moisture leads to reducing the capability of spectroscopy in soil properties estimation. Developing a method that could lessen the effect of moisture on soil properly prediction using spectrometry, is necessary. This paper utilises an external parameter orthogonalisation (EP...

متن کامل

Simple Surface Reflectance Estimation of Diffuse Outdoor Object using Spherical Images

This paper proposes a new, efficient method to estimate reflectance parameters of diffuse outdoor objects from only one measurement with a spherical camera. The camera we used captures nearly 75 percent of a 360-degree field of view; thus, it captures the radiance of an object and illumination environment at one shot. By taking the known object’s shape into account, the illumination effect is c...

متن کامل

Determination of Leaf Relative Water Content of Two Genotypes of Sesame Using Visible and Near- Infrared (VIS/NIR) Spectrometry to Detect Drought Stress

Relative water content (RWC) in plants is one of the most important biochemical parameters and its deficiency limits efficiency of photosynthesis and crop productivity. The scientific reports on using spectroscopy in detecting drought stress for sesame plants are very rare. In this study, the possibility of identifying water stress in two sensitive (Naz-Takshakhe) and resistant (Yekta) genotype...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016