Search Results

Many technical projects, most vehicle and component testing, and all accident reconstructions, product failure analyses, and other forensic investigations, require photographic documentation. Roadway evidence disappears, tested or wrecked vehicles are repaired, disassembled, or scrapped, and components can be tested for failure. Photographs are frequently the only evidence that remains of a wreck, or the only records of subjects before or during tests. Making consistently good images during any inspection is a critical part of the evaluation process. 

Photographs and video recordings of vehicle crashes and accident sites are more prevalent than ever, with dash mounted cameras, surveillance footage, and personal cell phones now ubiquitous. The information contained in these pictures and videos provide critical information to understanding how crashes occurred, and  analyze physical evidence. This course teaches the theory and techniques for getting the most out of digital media, including correctly processing raw video and photographs, correcting for lens distortion, and using photogrammetric techniques to convert the information in digital media to usable scaled three-dimensional data.

This two-day course will begin with a discussion of commercial off the shelf (COTS) test requirements.  The instructor will then guide participants through the various cabin interior emergency provisions and their requirements such as supplemental passenger oxygen, emergency equipment, seats, flammability, emergency exits, emergency lighting and escape path markings, and various other cabin interior systems.  

Convolutional neural networks are the de facto method of processing camera, radar, and lidar data for use in perception in ADAS and L4 vehicles, yet their operation is a black box to many engineers. Unlike traditional rules-based approaches to coding intelligent systems, networks are trained and the internal structure created during the training process is too complex to be understood by humans, yet in operation networks are able to classify objects of interest at error rates better than rates achieved by humans viewing the same input data.