Recognition of Partially Obstructed 3D Objects using Hough Voting

نویسندگان

  • Derek Liu
  • Josh Gyory
  • Kevin Chiu
چکیده

Motivated by a 3D printing company, ExOne, the goal of this project is to recognize 3D objects from partially observed surface data. Given point cloud data of a buried object from a Kinect, as well as the entire CAD model of the object, the aim is to determine the object's orientation in space. To accomplish this task, we implemented a Hough Voting algorithm for object detection and localization. This algorithm determines the transformation between local feature points that it then applies to the scene to determine where the object is located. This method was chosen for its robust nature as well as its ability to locate objects even when partially obstructed within the scene. The resulting implementation of this algorithm is successful in its initial stages, but has many possible avenues for improvement and integration into the final system.

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

Successive Pose Clustering for Steroscopic Object Recognition

The concept of generalized trihedral vertex (GTV) is proposed for 3d object representation. The concept covers not only polygonal objects but also curved objects including rounded edges and rounded corners. An effective algorithm is shown for matching two GTVs, one of which is constructed from stereoscopic images and the other of which is precompiled in the G T I database. Finally, we construct...

متن کامل

Rapid Object Indexing and Recognition Using Enhanced Geometric Hashing

We address the problem of 3D object recognition from a single 2D image using a model database. We develop a new method called enhanced geometric hashing. This approach allows us to solve for the indexing and the matching problem in one pass with linear complexity. Use of quasi-invariants allows us to index images in a new type of geometric hashing table. They include topological information of ...

متن کامل

Furniture Recognition using Implicit Shape Models on 3D Data pdfsubject

The recognition and classification of objects in 3D scene data is still a very challenging task in computer vision. For robots acting in domestic environments especially the correct recognition of furniture objects is important because these belong to the main things they need to consider, either for navigating around or for using them. In this work an approach for the recognition of furniture ...

متن کامل

Depth-Encoded Hough Voting for Joint Object Detection and Shape Recovery

Detecting objects, estimating their pose and recovering 3D shape information is a critical problem in many vision and robotics applications. This paper addresses the above needs by proposing a new method called DEHV Depth-Encoded Hough Voting detection scheme. Inspired by the Hough voting scheme introduced in [13], DEHV incorporates depth information into the process of learning distributions o...

متن کامل

Learning to Rank 3D Features

Representation of three dimensional objects using a set of oriented point pair features has been shown to be effective for object recognition and pose estimation. Combined with an efficient voting scheme on a generalized Hough space, existing approaches achieve good recognition accuracy and fast operation. However, the performance of these approaches degrades when the objects are (self-)similar...

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