DaViewInTheBox

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Object Detection for Industrial Inspection

Supervision by: Dr. Slobodan Ilic

Project Description

In this project the student has to develop a working prototype of the vision based inspection system, which detects almost planar circular objects stacked in the box. These objects are separated by the deformable pad (interlayer), which also have to be detected. The setup is the following. A box with six defined circular stack regions, where the objects of interest are stacked on top of each other is filmed by the industrial RGB-D camera. The camera provides both depth and grey scale image. Circular target objects are separated by the deformable pads. Given one such image the following situations have to be recognized:

  • circular object is present
  • deformable pad is present
  • stack region is empty.

In situations 1) and 2) the algorithm has to return 3D pick-up point being on the object or on the pad. This position is given to the robotic arm, which then lifts the object. In empty regions no actions of the robot are done. The project doesn’t involve control of the robot, but only computer vision part where 3D pick-up points (in case of full stacks), or no pick-up point(in case of empty stack) are returned.

Requirements

  • We are looking for motivate student, with knowledge in C/C++ programming and preferably with some Computer Vision and/or Image processing experience. The library to be used is Halcon from MVTec company.
  • Duration 3-6 moths.

If you are interested please send your updated CV (including practical project experience) and the transcript of grades to Dr. Slobodan Ilic.

ProjectForm
Title: Object Detection for Industrial Inspection
Abstract: The project deals with the implementation of an algorithm for checking the presence/absence of circular flat objects stacked on top of one another in the box. The objects are separated by the soft pads which can deform and has also be detected. The system has to return 3D pick-up location of the objects. Kinect-like industrial RGB-D camera will be used and developement will be based on HALCON library.
Student:  
Director:  
Supervisor: Dr. Slobodan Ilic
Type: Hiwi
Area: Computer Vision
Status: finished
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.4 - 07 Oct 2016 - 05:42 - SlobodanIlic