Search
  • 網站搜尋
亞洲知識產權資訊網為知識產權業界提供一個一站式網上交易平台,協助業界發掘知識產權貿易商機,並與環球知識產權業界建立聯繫。無論你是知識產權擁有者正在出售您的知識產權,或是製造商需要購買技術以提高操作效能,又或是知識產權配套服務供應商,你將會從本網站發掘到有用的知識產權貿易資訊。
返回搜索結果

Apparatus and methods for determining the three-dimensional shape of an object using active illumination and relative blurring in two images due to defocus


總結

Lead Inventors: Shree Nayar, Minori Noguchi, Masahiro WantanabeProblem or Unmet Need:Problem or Unmet Need ~Assessing the depth of an object from a 2D image is a pertinent problem in computer vision. Active illumination combined with focus analysis has several advantages over other techniques as it allows multiple images of an object to be taken from the same view point. However, determining depth from defocus is complicated by the need to separate the data into multiple narrow frequency domains and its inability to resolve the depth of texture-less objects. In addition, the relationship between magnification and defocus have yet to be adequately addressed. Details of the Invention ~The following invention: Describes an apparatus for mapping three dimensional object from two-dimensional images with increased accuracy, using the depth from defocus method The method requires that the scene be illuminated with a preselected illumination pattern, and that at least two images of the scene be sensed, where the sensed images are formed with different imaging parameters The relative blur between corresponding elemental portions of the sensed images is measured, thereby to determine the relative depth of corresponding elemental portions of object The technology resolves issues of texture-less objects by using active illumination to impose texture Uses constant magnification defocusing


技術優勢

The approach produces precise, high resolution depth maps at frame rate. The approach uses inexpensive off-the-shelf imaging and processing hardware


技術應用

Security systems Military and police surveillance Navigation systems


詳細技術說明

Details of the Invention ~The following invention: Describes an apparatus for mapping three dimensional object from two-dimensional images with increased accuracy, using the depth from defocus method The method requires that the sce...


國家/地區

美國

欲了解更多信息,請點擊 這裡
Business of IP Asia Forum
桌面版