Embedded vision components are ever popular and being incorporated into a plethora of applications. What all these applications have in common is the need to pack more functionality into tight spaces. Often, it is advantageous for these systems to make decisions on the edge. To enable such systems, including the ability to prototype quickly, Teledyne FLIR has introduced the Quartet Embedded Solution for TX2. This customized carrier board enables easy integration of up to 4 x USB3 machine vision cameras at full bandwidth.
To highlight what the Quartet can enable, steps taken in developing an ITS (traffic systems)-inspired prototype running four simultaneous applications are described. Three of these cases use deep learning:
- Application 1: License plate recognition using deep learning
- Application 2: Vehicle type categorization using deep learning
- Application 3: Vehicle color classification using deep learning
- Application 4: See-through windshield (past reflection and glare)
Source: Teledyne FLIR
Keep reading to see a list of hardware and software components, learn about the development time for each application and the number of training images required, and actions to optimize overall system performance.
