You don’t need heavy compute that is expensive and consumes a lot of energy. We offer edge based computing with NVIDIA Jetson for a reason! Visionplatform.ai is the only fully end-end solution for AI vision. Get started with a few clicks in the platform and therefore without time-consuming implementation processes.
The NVIDIA Jetson seamlessly integrate with your existing infrastructure. Our platform can be connected to your VMS or production lines in any way you chose.
Flexible, from server room till street cabinet, on fiber or 4G.
A no-effort edge AI solution for complete AI deployment from start to finish
Smooth interaction with ANY existing industrial or IP cameras and controllers
On-premise processing and image management and output analysis
Built on NVIDIA Jetson (a compact, energy-efficient GPU Powerhouse for AI Edge computing)
✓ Secure (on-premise)
✓ Low latency (lightning fast)
✓ Scalable (easily connect multiple cameras)
We selected the NVIDIA Jetson for its remarkable flexibility and energy efficiency. With power consumption ranging between just 30 and 65 watts, it can process up to 20 cameras simultaneously. This equates to an incredibly low power usage of as little as 3.25 watts per camera, making it a highly sustainable and cost-effective solution
Hesitating between a provider offering you a regular PC / computer or server with GPU?
You earn back our PRO license within 1 month if you have >100 cameras
Full support for leading VMS systems like Milestone Systems and Genetec, ensuring compatibility with your existing video management infrastructure.
Seamlessly integrate with custom REST PUSH APIs for tailored data transfer and communication to use for example in your BI environment
Connect through Node-RED to enable communication with Modbus TCP/IP, a widely-used protocol in industrial environments.
Easily connect with PLCs via Node-RED, allowing automation and real-time control across your production systems.
| Dimensions (W x D x H) | 130 x 130 x 46 mm (5.1″ x 5.1″ x 1.8″) | 194.8 x 174.3 x 65.85 mm (7.67″ x 6.86″ x 2.59″) | 194.8 x 174.3 x 65.85 mm (7.67″ x 6.86″ x 2.59″) | 192 x 230 x 87 mm (7.55″ x 9.05″ x 3.43″) | 192 x 230 x 87 mm (7.55″ x 9.05″ x 3.43″) | |
|---|---|---|---|---|---|---|
| Weight | 1.2 kg (2.65 lbs) | 1.2 kg (2.65 lbs) | 1.2 kg (2.65 lbs) | 4.5 kg (9.9 lbs) | 4.5 kg (9.9 lbs) | |
| Installation methods | Desktop / Wall mount | Desktop / Wall mount | Desktop / Wall mount | Desktop / Wall mount | Desktop / Wall mount | |
| Capturing frame rate | up to 8 camera’s | up to 10 camera’s | up to 12 camera’s | up to 16 camera’s | up to 20 camera’s | |
| GigE & USB 3.0 camera compatibility |
Basler Pylon SDK Allied Vision Vimba SDK IDS uEye(+) SDK |
Basler Pylon SDK Allied Vision Vimba SDK IDS uEye(+) SDK |
Basler Pylon SDK Allied Vision Vimba SDK IDS uEye(+) SDK |
Basler Pylon SDK Allied Vision Vimba SDK IDS uEye(+) SDK |
Basler Pylon SDK Allied Vision Vimba SDK IDS uEye(+) SDK |
|
| Inference throughput | Object Detection (YOLOv5m): 131 FPS | Object Detection (YOLOv5m): 193 FPS | Object Detection (YOLOv5m): 193 FPS | Object Detection (YOLOv5m): 342 FPS | Object Detection (YOLOv5m): 342 FPS | |
| Internal storage capability | 256GB or 512GB | 256GB or 512GB | 256GB or 512GB | 256GB, 512GB or 1 TB | 256GB, 512GB or 1 TB | |
| Jetson GPU | 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores | 1024-core NVIDIA Ampere GPU with 32 Tensor Cores | 1024-core NVIDIA Ampere GPU with 32 Tensor Cores |
1792-core NVIDIA Ampere GPU with 56 Tensor Cores, Maximum Operating Frequency: 930 MHz |
2048-core NVIDIA Ampere GPU with 64 Tensor Cores] Maximum Operating Frequency: 1.3GH |
|
| AI performance reference | Up to 40 TOPs | Up to 70 TOPs | Up to 100 TOPs | Up to 200 TOPs | Up to 275 TOPs | |
| CPU |
6-core Arm® Cortex®-A78AE v8.2 64-bit CPU 1.5MB L2 + 4MB L3 |
6-core NVIDIA Arm® Cortex A78AE v8.2 64-bit CPU | 8-core NVIDIA Arm® Cortex A78AE v8.2 64-bit CPU (2MB L2 + 4MB L3) |
8-core NVIDIA Arm® Cortex A78AE v8.2 64-bit CPU, 2MB L2 + 4MB L3 |
12-core NVIDIA Arm® Cortex A78AE v8.2 64-bit CPU, 3MB L2 + 6MB L3 |
|
| I/O |
Ethernet 1 x 10/100/1000 Mbps Display HDMI (Max. resolution 3840×2160 @ 60Hz) USB External: 2 x USB 3.2 Gen 2, 1 x USB 2.0 Internal: 1 x USB 2.0 (by pin header) OTG USB 1 x Micro USB |
Ethernet 1 x 10/100/1000 Mbps Display HDMI (Max. resolution 3840×2160 @ 60Hz) USB External: 6 x USB 3.2 Gen 2 Digital I/O 4-ch DI, 4-ch DO Serial Port (Optional) 2 x RS-232/422/485 (On-board pin header reserved) CANBus 1 OTG USB 1 x Micro USB |
Ethernet 1 x 10/100/1000 Mbps Display HDMI (Max. resolution 3840×2160 @ 60Hz) USB External: 6 x USB 3.2 Gen 2 Digital I/O 4-ch DI, 4-ch DO Serial Port (Optional) 2 x RS-232/422/485 (On-board pin header reserved) CANBus 1 OTG USB 1 x Micro USB |
Ethernet 4 x 10/100/1000 Mbps (Optional PoE support, IEEE 802.3af/at) Display HDMI (Max. resolution 3840×2160 @ 60Hz) USB External: 2 x USB 2.0, 4 x USB 3.2 Gen 2 Internal: 1 x USB 2.0 Digital I/O 4-ch DI, 4-ch DO Power Switch 1 x Power ON/OFF Button Serial Ports 2 x RS-232/422/485 (On-board pin header) OTG USB 1 x Micro USB |
Ethernet 4 x 10/100/1000 Mbps (Optional PoE support, IEEE 802.3af/at) Display HDMI (Max. resolution 3840×2160 @ 60Hz) USB External: 2 x USB 2.0, 4 x USB 3.2 Gen 2 Internal: 1 x USB 2.0 Digital I/O 4-ch DI, 4-ch DO Power Switch 1 x Power ON/OFF Button Serial Ports 2 x RS-232/422/485 (On-board pin header) OTG USB 1 x Micro USB |
I already have my edge computing device:
I want processing locally within my network. That’s why I need a processing unit (edge computing):
I need advise on my hardware and use-case:
I want processing locally within my network. That’s why I need a processing unit (edge computing):
leave your details and we’ll plan a 30 min session.
