All News | Boards | Chips | Devices | Software | Archive | About | Contact | Subscribe
Follow LinuxGizmos:
Twitter Facebook Pinterest RSS feed
*   get email updates   *

LTE-equipped machine vision computer runs Linux on a Jetson TX2

May 30, 2019 — by Eric Brown 2,297 views

[Updated: Jun. 3] — Imago’s “VisionBox Daytona” machine vision platform runs Linux on a Jetson TX2 and offers 4G LTE plus dual GbE camera ports with PoE and triggers. Other recent, Linux-based Imago systems include an octa-core VisionBox Le Mans and an EdgeBox cloud server.

Imago Technologies has released a variety of Linux-ready VisionBox machine vision platforms in recent years running on both Arm and x86 processors (see farther below). Now, it has introduced an Arm-based VisionBox Daytona computer that answers the question: What do you do when your remote machine-vision computer needs a little help? Unlike many vision computers, the VisionBox adds LTE so that “questionable decisions” can be remotely “validated by the expert through image analysis,” says Imago.

Yes, it appears there’s still room for a human in the loop after all.

VisionBox Daytona (left) and Jetson TX2
(click images to enlarge)

The LTE radio, along with the 802.11ac WiFi built into the Nvidia Jetson TX2 module that powers the system, serve another purpose, as well. According to Friedberg, Germany-based Imago, the vision industry is abandoning monolithic, all-inclusive vision software for an a la carte approach based on a variety of third-party apps. That means “image and program transfer are necessary,” says the company.


Other applications could also make use of the 4G connection. “Installed in a forklift truck, the VisionBox can immediately contact the logistics infrastructure,” says Imago.

VisionBox Daytona dimensions
(click image to enlarge)

The VisionBox Daytona is Imago’s first Jetson-based computer. The hexa-core Jetson TX2 module provides the Daytona with the AI smarts within the CUDA acceleration libraries running on its 256-core Pascal GPU for applications such as deep learning, hyperspectral imaging, and computing 3D images.

You choose the original 8GB LPDDR4/32GB eMMC 5.1 Jetson TX2 model or the newer 4GB/16GB version. Only the 8GB version has onboard WiFi. (The 8GB TX2 has Bluetooth, too although Imago makes no mention of it and it might be disabled).

Like all the VisionBox models, the Daytona provides an unnamed FPGA with real-time I/O controller capabilities. The FPGA is supported with Imago’s RTCC SDK.

VisionBox Daytona with antennas
(click image to enlarge)

The VisionBox Daytona build on the Jetson TX2 with an external SD slot and an internal M.2 slot for solid state drives (SSDs). The centerpiece of the device is a pair of GbE-based GigE Vision camera ports with Power-over-Ethernet and 2x Trigger-over-Ethernet camera triggers to match. Antenna mounts are available for both WiFi and LTE.

The system is further equipped with a standard GbE port, a DisplayPort, 2x USB 3.0 ports, and an encoder based on RS-422. You also get 8x inputs and 8x outputs with opto-isolation for 24V. Like the GigE camera triggers, the serial and DIO connections are controlled by Imago’s real-time FPGA.

The 163 x 163 x 48mm footprint expands to 210mm in one dimension with the addition of a mounting plate. The 1.3 Kg computer has a 20-28VDC input and runs at 7W (idle) or 24W (typical). Power can be supplied to PoE-powered devices such as cameras. The fanless system has a heatsink and can tolerate a 0 to 50°C range. Long-term availability runs through 2028.

VisionBox Le Mans, Age-X Tiger+, EdgeBox, and more

Most of the other VisionBox systems also run Linux. There’s a recent VisionBox Le Mans system that runs Linux on NXP’s 2GHz, octa-core, Cortex-A72 QorIQ Layerscape LS2084 SoC.

VisionBox Le Mans (left) and VisionBox Octa
(click images to enlarge)

The 24V-powered Le Mans is further equipped with 8GB RAM, 2x 10GbE ports, 4x GbE ports, 2x USB 3.0 ports, 8/8 opto-decoupled DIO, and an SD slot. Four PCIe slots support optional VisionBoards, including a board with additional DIO, an LED strobe controller board, a framegrabber, or a model with 4x triggered GigE Vision ports with PoE (see image below).

VisionBoard options for VisionBox Le Mans
(click image to enlarge)

Imago also offers a VisionBox Age-X family that runs Linux or Windows on an unnamed dual- or quad-core x86 processor. There’s a new AGE-X Tiger+ variant that features 4x GigE Vision ports with trigger-over-Ethernet and 16/16 I/O.

The VisionBox Octa runs a real-time OS on an octa-core Texas Instruments Keystone SoC with FPU. The Octa has a GbE port and a 4x camera link ports.

VisionBox AGE-X

Image also sells a family of VisionCam smart cameras with both a camera sensor and image processor that run Linux on a dual-core, Cortex-A15 SoC. The VisionCam cameras support the Halcon Embedded MVTec image processing library. The VisionCam XM smart area scan camera can power an additional GigE camera via a switch. There’s also a VisionCam LM line-scan model, as well as a basic, embedded VisionSensor PV camera. The VisionCam EB model offers event-based contrast detection CMOS sensors from Prophesee for high-speed tracking, object counting, vibration measurement, or kinematic monitoring.

Finally, Imago sells a security-enhanced EdgeBox “cloud server” for industrial environments. It runs Linux on the same octa-core -A72 LS2084 SoC that drives the VisionBox Le Mans.

The EdgeBox is equipped with 2x 10GbE ports, 4x GbE ports, 2x USB ports, a COM port, and digital I/O controlled by Imago’s real-time FPGA. The system is available in both a compact desktop model and a larger version with several PCIe slots and a fan designed for 19-inch racks.

VisionCam XM (Left) and EdgeBox
(click images to enlarge)

Imago posts only minimal specs on its products, but we asked for a Daytona datasheet and they sent us one. Maybe they will do the same for you.

Further information

No pricing or availability information was provided for the VisionBox Daytona. Limited information on all the VisionBox systems may be found on Imago Technologies’ VisionBox product page. More on the VisionCam systems may be found on Imago’s VisionCam product page and more on the EdgeBox may be found on the EdgeBox page.


(advertise here)

Print Friendly, PDF & Email

Please comment here...