Development and integration of feature detection algorithms for metal-based direct deposition processes

Metal-based direct energy deposition processes, such as robotic welding and laser powder fed additive manufacturing, ideally require feedback sensing of the deposition quality using vision detectors. Image processing algorithms are challenging to develop due to changing process operating conditions. Despite challenges, implementing in-process image processing algorithms is beneficial for traceability and quality assurance, for calibrating process models, and for developing closed loop control algorithms which are able to maintain deposition quality within acceptable quality margins.

Thermal and Electroluminescence Imaging and Application to the Location and Classification of Defects in Crystalline and Multi-Crystalline Solar Cells

When a solar cell is illuminated by light from the sun, a current is generated that can be used to provide electrical power. Conversely, if we apply a current to a solar cell, light is generated and this process is called electroluminescence (EL). In Silicon solar cells the EL is very weak and in a perfect cell is extremely uniform. Defects inherent in the material, such as dislocations which degrade its performance or those created during the cell fabrication process, such as microcracks which affect its long term reliability can be clearly observed in EL imaging.

Robust Face Detection and Tracking for Video Surveillance

Intelligent visual surveillance refers to the use of context rich visual sensors, i.e. video cameras, for the purpose of surveillance. Surveillance systems can be deployed in diverse environments, such as airports, department stores, office buildings, home buildings, conference rooms, parking lots, and hotels for diverse purposes, such as ambient and personal security, information recording, and personal identification.

FPGA-accelerated Laser Line Profile Extraction

The research project with Xiris Automation Inc, a developer of high-end machine vision components, is to devise a laser vision system to inspect pipe welds at very high speeds. This will be accomplished by designing custom hardware on a field programmable gate array (FPGA). This process must detect reliably the quality of the welds in a noisy industrial environment and must account for specular reflection on the pipe’s surface. The desired image acquisition and processing speed will be in the range of 200-500 frames per second.