FitOptiVis

ITI is creating an industrial inspection prototype for FitOptiVis. The device is being assembled and will include 16 Nvidia Jetson Nano to perform Edge Computing calculations. Currently ITI is designing the panel that will hold the boards and installing the hardware which controls the cameras.

The goal is to provide a solution that will be easily integrated in production processes allowing real-time capture, 3D reconstruction and inspection of factory produced parts.

Using Edge Computing, it will be possible to increase performance of data acquisition by improvements in the object detection algorithms, executed close to the cameras using low power consumption boards. These boards will be a key point to achieve code palatalization and network usage optimization.

As a part of traffic surveillance use case, we integrate advanced HDR image capturing and object detection in FPGA, targeting Zynq platform in a smart camera. The camera will capture multi-exposure Full-HD video at 90 FPS and merge the image stream to 30 FPS tone-mapped HDR video using novel motion-aware merging algorithm.

Smart Camera with Embedded Object Detection - FitOptiVis FitOptiVis As a part of traffic surveillance use case, we integrate advanced HDR image capturing and object detection in FPGA, targeting Zynq platform in a smart camera. The camera will capture multi-exposure Full-HD video at 90 FPS and merge the image stream to 30 FPS tone-mapped HDR video using novel motion-...