Bin-picking, re-grasping, pick-and-place, kitting, etc. There are many
manipulation tasks in the fields of automation of factory, warehouse and so on.
The main problem of the automation is that the target objects (items/parts) have
various shapes, weights and surface materials. In my talk, I will show latest
machine vision systems and algorithms against the problem.
Segment Handling System (SHS) is the subsystem that is planned to be permanently implemented on Thirty Meter Telescope (TMT) telescope structure that enables fast, efficient, semi-automatic exchange of M1 segments. TMT plans challenging segment exchange (10 segments per 10 hours a day). To achieve these, MELCO develops innovative SHS by accommodating Factory Automation (FA) technology such as force control system and machine vision system into the system. Force control system used for install operation, achieves soft handling by detecting force exerted to mirror segment and automatically compensating the position error between handling segments and primary mirror. Machine vision system used for removal operation, achieves semi-automatic positioning between SHS and mirror segments to be handled. Prototype experience proves soft (extraneous force ~300N) and fast (~3 minutes) segment handling. The SHS will provide upcoming segmented large telescopes for cost-efficient, effortless, and safe segment exchange operation.
We propose a novel three-Dimensional measurement approach of flexible cables
for factory automation appliations, such as cable handling, connecter insertion
without conflicts with cables by using robotic arms. The approach is based on
motion stereo with a vision sensor. Laser slit beams are irradiated and make
landmalks on the cables to solve stereo correspondence problem efficiently.
These landmark points and interpolated points having rich texture are tracked in
a image sequence, and reconstructed as the cable shape. For stable feature point
tracking, a robust texture matching method which is Orientation Code Matching and
tracking stability analysis are applied. In our experiments, arch-like cables have been
reconstructed with an uncertainty of 1.5 % by this method.
Feature extraction and tracking are widely applied in the industrial world of today. It is still an important topic in Machine Vision. In this paper, we present a new feature extraction and tracking method which is robust against illumination change such as shading and highlighting, scaling and rotation of objects. The method is composed mainly of two algorithms: Entropy Filter and Orientation Code Matching (OCM). The Entropy Filter points up areas of images being messy distribution of orientation codes. The orientation code is determined by detecting the orientation of maximum intensity change around neighboring 8 pixels. It is defined as simply integral values. We can extract good features to track from the images by using the Entropy Filter. And then, the OCM, a template matching method using the orientation code, is applied to track the features each frame. We can track the features robustly against the illumination change by using the OCM. Moreover, updating these features (templates) each frame allows complicated motions of tracked objects such as scaling, rotation and so on. In this paper, we report the details of our algorithms and the evaluations of comparison with other well-known feature extraction and tracking methods. As an application example, planer landmarks and face tracking is tried. The results of them are also reported in context.