Truck loading, truck box with some objects, hardware for 3D ranging (MS Kinect, Asus Xtion PRO, Sick LRF)
MSc dissertation proposal 2013/2014
Volume
Measurement Using Depth Cameras
Introduction:
Constantly growing fuel costs imply that transporting goods using trucks
must be made more efficient than ever. Companies must keep as small as possible
the empty spaces of the truck containers.
This MSc project proposal is mainly concerned with designing an automatic volume
estimator applied to truck containers, using recent high resolution
cameras or depth sensors such as Sick [Sick-LRF] or Hokuyo Laser Range Finders
[Hokuyo-LRF].
Objectives:
In this work the main objective is assembling a system that allows a precise
measurement of the free volume of a truck container.
Detailed description:
Transporting goods using trucks is ubiquitous. The traditional package
sending by postal offices is nowadays widely spread among numerous cargo transporters.
Commonly, cargo transporters provide the trucks and rely on local warehouses to
perform cargo loading / unloading at their own loading docks. Cargo
transporters are constantly seeking for ways of optimizing their business by
augmenting the transported volume per truck. Assessing the not filled (free)
volume of a truck container is therefore a key tool for business optimization.
Traditionally, the free volume has been evaluated visually by expert
dock labourers. In this MSc work proposal, the main objective is designing a
precise free volume measuring system. The system incorporates a
range measuring device, such as a depth measuring camera (e.g. MS Kinect), or a pair of high resolution cameras, or a laser
(Laser Range Finder - LRF), and a computer to control the data acquisition
device and perform the free volume computation.
Alternatively to estimating free volume, one may also compute the filled volume
by accumulating the volumes of the objects which are going to be loaded into
the truck. Knowing the free volume of a empty truck and
subtracting the filled volume, one obtains once more the free volume in a loaded
truck. This second methodology is expected to be compared with the first one.
The main steps of the work are therefore the following:
- Data
acquisition of depth maps using Kinect
like or LRF cameras
- Implement of the free volume estimator
- Precise definition of the nearest face of the free volume
- Comparison
of free vs filled volume estimator methodologies
Note: The hardware to use is the one already available at IST/ISR,
namely MS Kinect cameras [MS-Kinect], high resolution cameras [PointGrey],
Sick LRF [Sick-LRF] and Hokuyo LRF [Hokuyo-LRF].
References:
[ISR-galery] Some images of
unicycle type robots at ISR: see labmate, scouts, pioneers, ... in "Mini galeria
de fotografias de projectos
@ IST/ISR", http://users.isr.ist.utl.pt/~jag/infoforum/isr_galeria/
[MS-Kinect] http://en.wikipedia.org/wiki/Kinect
[ARDC10] "Workshop on RGB-D: Advanced Reasoning
with Depth Cameras", June 27, 2010 @
[3DPR11] "European Robotics Forum 2011 WORKSHOP
RGB-D Workshop on 3D Perception in Robotics", April 8, 2011,
[CDC4CV11] "First IEEE Workshop on Consumer Depth
Cameras for Computer Vision" http://www.vision.ee.ethz.ch/CDC4CV/
November 12, 2011 @
[WDIA12] "International Workshop on Depth Image
Analysis (WDIA 2012)", In Conjunction with 21th
International Conference on Pattern Recognition 2012, November 11th, 2012,
[PointGrey] Point Grey
Research, Inc , http://www.ptgrey.com/
[Sick-LRF] http://www.sick.com/group/EN/home/products/product_portfolio/optoelectronic_protective_devices/Pages/safety_laser_scanners.aspx
(model available at IST/ISR: SICK LMS 291 )
[Hokuyo-LRF] http://www.hokuyo-aut.jp/02sensor/
(model available at IST/ISR: Hokuyo URG-04LX-UG01)
Requirements (grades, required courses, etc):
-
Expected results:
At the end of the work, the students will have enriched their experience
in computer vision, particularly in the aspect of free volume measurement.
In the end of the work is expected the publication of report(s) in the
form of research paper(s).
Place for conducting the work-proposal:
ISR / IST
More MSc dissertation
proposals on Computer and Robot Vision in:
http://omni.isr.ist.utl.pt/~jag