FP7 1 1-12-2014 Sensors DSLR camera (Nikon D4, 16.2 MP, 60 mm - - PDF document

1-12-2014 1

Florian Kleber, Christopher Pramerdorfer, Martin Kampel (CVL) Brindus Comanescu and Elena Stanciu (S.C. Optoelectronica)

FP7

 Setup for vision based analysis of electronics

waste

• Printed Circuit Boards (PCB)
• Components of PCBs

 Define sensor requirements  Classification of PCBs and components  Laser-Induced Breakdown Spectroscopy (LIBS)

for chemical pre-analysis

• Define components which contain desired material

1-12-2014 2

FP7

 Sensors

• DSLR camera (Nikon D4,

16.2 MP, 60 mm focal length)

• IP camera (Axis P1346,

up to 1080 P, 30 fps)

• 3D sensor (Asus Xtion

PRO Live)

• MS camera (Hamamatsu

C9300-124, 10 MP, 300-1000nm)

• TOF (Bluetechnix M100)

Evaluation of different optical sensors necessary to

• ) determine what sensors are suitable for recognition
• ) identify strengths, weaknesses, and complementary effects

FP7

 Bicolor LEDs with configurable color temp  Heureka LED with 11 different wavelengths

1-12-2014 3

FP7

 Polarization filters for lights and sensors  Filter specular reflections  Achieve uniform illumination

FP7

 High resolution (spatial and radiometric)  Images vary depending on wavelength

• Readability of labels, visibility of PCB traces

 Limited frame rate (up to 2 fps)  Suitable for detailed analysis

• Resolution similar to Nikon, but less noise
• Wider sensitivity range increases flexibility

(UV, IR)

Ibrahim et al. 2009

1-12-2014 4

FP7

Caption of one IC at all different wavelengths (same position) Label of QFP elements at VIS (first row) and Amber, 570 nm (second row) Influence of the incident angle of the light is illustrated Printed circuits at VIS and IR (870 nm)

FP7



Evaluation of Asus Xtion Pro Live and Bluetechnix TOF sensors



Advantages: object geometry available, invariant to illumination



Disadvantages: low resolution, specular surfaces not reliably measurable

• Combination of multiple frames and interpolation of missing data mandatory



Asus Xtion Pro Live superior to TOF (higher resolution, less noise)

Combination

1-12-2014 5

FP7 FP7



Professional DSLR camera



16.2 MP resolution (4928x3280)



Lens with 60mm focal length



12 or 14 bit depth in RAW mode



IP camera



Up to 1080p resolution at 30fps

1-12-2014 6

FP7

 Identification of PCBs via

comparison to database

• Comparison using both geometry and

appearance

 Identifying PCBs allows for

• Determining whether they contain

valuable SMDs

• Knowing what SMDs they contain and

where they are located

• An individual treatment of PCBs for
• ptimized recycling

 Method can be extended to detect

groups of components

Feature Extraction Database

FP7

 Input: live stream from IP camera (1280 x 960

px, appr. 50 dpi)

 Detect & track objects in the waste stream  Extract a reference image (same viewpoint) Obtained reference images

1-12-2014 7

FP7

 Recognition via sparse descriptor matching

• SURF keypoints and descriptors [2]

 Robust wrt. illumination, object orientation  Robust wrt. partial data corruptions

• Occlusions, partially broken PCBs

 Identification of PCBs via database comparison

FP7

 Promising first results

• Each of 25 test PCBs matched against all others
• Various rotations applied to PCBs
• 100% recognition rate using Axis images

 Summary

• Knowing the identity of a PCB allows for

 Determining whether it is valuable  What SMDs it contains and where they are located  An individual treatment for optimized recycling

1-12-2014 8

FP7

 Outlook

• Evaluation of

keypoint detectors and descriptors:

• SIFT, SURF, ORB,

BRISK, FREAK, AKAZE

FP7

 Sensor comparison

• IP camera
• DSLR

 Recognition is

based on the same method as presented for PCB recognition

 Results

1-12-2014 9

FP7

 Based on chemical analysis:

• Focus on SMD ICs

 Outlook:

• Test OCR

CHIME I CM2651B-KQ KZE4E127A13 0441 T033

FP7

 Type of atomic

emission spectroscopy

 Uses a highly

energetic laser pulse as excitation source to atomize and excite samples

 LIBS can detect all

elements limited by

• the laser power
• sensitivity/wavelength

range of the spectrograph & detector

LIBS signal obtained from a basis plate of LCD

1-12-2014 10

FP7

 Primary characteristics

• Spectroscopic technique with no sample

preparation for gases, solids or liquids

• Real time, semi-quantitative measure of most

chemical species

• Measurements are spatially and temporally resolved
• Detection limits in the order of ppm or better for

most elements

 Pre-processing step to define components

containing the desired materials

FP7

 Development of recognition system and GUI

for database administration

 Recognition performance evaluation

• Data from single sensors
• Combined data from multiple sensors

 Recognition system (GUI)  LIBS as a pre-processing step

1-12-2014 11

FP7

 Setup:

• Going Green 2014

 Sensor Study:

• F. Kleber, C. Pramerdorfer, E. Wetzinger and M. Kampel, „Optical

Sensor Evaluation for Vision Based Recognition of Electronics Waste“, In Proc. of the 6th Int. Conference on Environmental Science and Development (ICESD), 2015, accepted.

 MS Analysis:

• F. Kleber and M. Kampel, „ Pre-Analysis of Printed Circuit Boards

based on Multispectral Imaging for Vision Based Recognition of Electronics Waste“, In Proc. of the 13th Int. Conf. On Environmental and Natural Resources Engineering (ICENRE), 2015, accepted.

 PCB Recognition:

• C. Pramerdorfer and M. Kampel, „Feature-Based PCB Recognition

for Recycling Purposes“, In Proc. of the 10th Int. Conf. On Computer Vision Theory and Applications, 2015, submitted.

FP7 For additional information or possible

cooperation please contact the Coordinator or any of the partners CVL, martin.kampel@tuwien.ac.at Email Coordinator: marc.vankleef@tno

1-12-2014 12

www.re-claim.eu

1-12-2014 13

FP7 FP7

 Asus superior to TOF

• Higher resolution
• Less data noise

 Limited data distinctiveness

• Limited spatial and depth resolution

 Both sensors have problems with

• Specular surfaces
• High density SMDs

 Postprocessing required

1-12-2014 14

FP7