HD‑SDI Frame Grabber with 325 GFLOPS Tegra-K1 CUDA Processing
- NVIDIA® Tegra-K1 APU for image processing
- WOLF Frame Grabber eXtreme (FGX) embedded FPGA capture engine
- 325 GFLOPS processing
- APU accelerated H.264 encoding
- Advanced power management (tunable as low as 10 watts)
WOLF’s VNX‑TK1-FGX is an image capture and processing module for aerospace and defense. It includes both an NVIDIA Tegra K1 APU and WOLF’s Frame Grabber eXtreme (FGX). The FGX can capture two HD-SDI inputs. The video data can be routed to the Tegra K1 for processing and the processed data can be output as HD‑SDI, HDMI or an encoded H.264 transport stream.
The FMC‑FGX‑TK1 is designed to operate reliably in harsh environments while performing precision-intensive operations, such as image processing, video stabilization, filtering, terrain analytics, 3D visualization of geospatial data, object recognition, and tracking.
The rugged VNX-FGX-TK1 modules uses the compact VITA 74 specification which defines an extremely small form factor. This form factor is roughly 50 percent of the weight and 30 percent of the volume compared to a typical 3U VPX.
WOLF VNX Module
This product is currently under consideration by the WOLF engineering team.
Contact WOLF to discuss the features and schedule if this product is of interest to you.
- NVIDIA Tegra-K1 Embedded APU:
- 5 ARM processor cores
- Kepler 192 CUDA core GPGPU
- 4 GB DDR3L memory
- 64 GB Embedded Flash
- 2× HD‑SDI input (SMPTE‑292M)
- 1× HD‑SDI output (SMPTE‑292M); Optionally can be mirrored to a second output
- 1× HDMI output
- 1× USB 2.0 interface
- 2× UART interfaces
- 1× 10/100/1000 Ethernet up to USB 2.0 speeds (480Mbps)
- Embedded Linux environment
- Dimensions: 75mm x 89mm x 19.5mm
- High level of ruggedization:
- Rugged conduction-cooled
- Operating temperature: -40° to +85°C
- Vibration (sine wave): 10G peak, 5 - 2000Hz
- Shock: 40G peak for conduction-cooled
- High-speed 400-pin connector derived from VITA 57 FMC spec
- Uses VPX signal mapping and bus structure
Login to access WOLF datasheets.