University Laval Infrared Thermography Databases for Deep Learning Multiple Types of Defect Detections Training

Nowadays, automatic defect detection research by deep learning algorithms plays a crucial role, especially for non-destructive evaluation with infrared thermography. In deep learning research, the databases are the Achilles’ heel during the training in order to preserve optimized performance. In this work, we will present the infrared thermography sequences databases from the Universite Laval Multipolar Infrared Vision Infrarouge Multipolaire (MIVIM) research group for regular and irregular defect analysis in order to provide the best data collection resources for the pretraining of convolutional neural network and feature extraction analysis with future researchers and engineers. The databases will include infrared thermography sequences from regular and irregular defects of carbon fiber-reinforced polymer (CFRP), glass fiber-reinforced polymer (GFRP), plexiglass, aluminum, and steel, which could be available online for public use and research purposes.

Indoor Positioning Method Based on Infrared Vision and UWB Fusion

Ultra-wideband (UWB) has broad application prospects in the field of indoor localization. In order to make up for the shortcomings of ultra-wideband that is easily affected by the environment, a positioning method based on the fusion of infrared vision and ultra-wideband is proposed. Infrared vision assists locating by identifying artificial landmarks attached to the ceiling. UWB uses an adaptive weight positioning algorithm to improve the positioning accuracy of the edge of the UWB positioning coverage area. Extended Kalman filter (EKF) is used to fuse the real-time location information of the two. Finally, the intelligent mobile vehicle-mounted platform is used to collect infrared images and UWB ranging information in the indoor environment to verify the fusion method. Experimental results show that the fusion positioning method is better than any positioning method, has the advantages of low cost, real-time performance, and robustness, and can achieve centimeter-level positioning accuracy.

Using through-transmission mid-wave infrared vision and air-coupled ultrasound for artwork inspection: a case study on mock-ups of Portrait of the Painter's Mother

The conservation of artworks is playing an increasingly important role in society today. Non-destructive investigation can provide the potential to identify deterioration as early as possible. In this research, transmission mid-wave infrared (MWIR) vision and air-coupled ultrasound (ACU) were used to investigate two paintings on canvas made from different textile support materials. An X-ray technique was used in the work for validation. It was found that the transmission mode can probe deeper and the differences in absorption due to the different textile support materials can be distinguished. This paper summarises advantages of the transmission inspection mode and compares and analyses images from the two techniques from a physical point of view.

Reduction of residual stress in polymorphous silicon germanium films and their evaluation in microbolometers

Hydrogenated polymorphous silicon germanium (pm-SixGe1–x:H) thin films were deposited by the PECVD technique at 200 °C. Three compositions were investigated by changing the silane/germane gas mixture. It was found that the temperature coefficient of resistance (TCR) varies from 2.25% K−1 to 4.26% K−1 while the electrical conductivity ranges from 9.1 × 10−6 S cm−1 to 3.7 × 10−3 S cm−1. On the other hand, the residual stress of as-deposited films was highly compressive reaching values of nearly 700 MPa. After a thermal annealing of 3 hours, it was observed an acceptable reduction and a slight change towards tensile stress. A thin film with low residual stress and high TCR was chosen to manufacture test microbolometers in order to assess if the thermosensing properties of pm-SixGe1–x:H were not affected. After fabricating the microbolometers, their structural conditions were evaluated by scanning electron microscopy and it was found that the reduction of stress significantly improved their mechanical stability and reduced the warping of the membranes. Finally, test structures were characterized at a chopper frequency of 30 Hz, with a DC current of 2.5 μA in a vacuum environment of 20 mTorr. Voltage responsivity of 1.9 × 106 V/W, detectivity of 4.4 × 108 cm ∙ Hz1/2/W, NEP of 1 × 10−11 W/Hz1/2, NETD of 18 mK and 2 ms of thermal response time were measured. In summary, we have studied different process conditions to obtain better pm-SixGe1–x:H films in terms of their electrical and mechanical properties. In this sense, the results obtained with microbolometers show that pm-SixGe1–x:H is a very attractive material to develop infrared vision systems with high sensitivity.

Optical Mouse Sensor for Eye Blink Detection and Pupil Tracking: Application in a Low-Cost Eye-Controlled Pointing Device

In this paper, a new application of the optical mouse sensor is presented. The optical mouse is used as a main low-cost infrared vision system of a new proposal of a head-mounted human-computer interaction (HCI) device controlled by eye movements. The default optical mouse sensor lens and illumination source are replaced in order to improve its field of view and capture entire eye images. A complementary 8-bit microcontroller is used to acquire and process these images with two optimized algorithms to detect forced eye blinks and pupil displacements which are translated to computer pointer actions. This proposal introduces an inexpensive and approachable plug and play (PnP) device for people with severe disability in the upper extremities, neck, and head. The presented pointing device performs standard computer mouse actions with no extra software required. It uses the human interface device (HID) standard class of the universal serial bus (USB) increasing its compatibility for most computer platforms. This new device approach is aimed at improving comfortability and portability of the current commercial devices with simple installation and calibration. Several performance tests were done with different volunteer users obtaining an average pupil detection error of 0.34 pixels with a successful detection in 82.6% of all mouse events requested by means of pupil tracking.