Wahtari nCam Solution - UP Bridge the Gap

　Partner Solution

Wahtari nCam

AI at the edge, powered by Intel® – it delivers power-efficient performance and specialized capabilities for new cases at the edge. The highly versatile Wahtari nCam is a powerful machine vision camera with deep learning capabilities, powered by Intel® Movidius™ Myriad™ X and Intel® Distribution of OpenVINO™ toolkit.

Utilizing Wahtari’s proprietary AI platform, you can develop a range of computer vision tasks from license plate recognition to quality control, analysis of medical images, or even facial recognition in the public security sector.

The neural camera configuration is flexible, with a modularized design allowing users to easily swap sensors with different resolutions and capture speeds or frame rates.

Overview

Wahtari nCam

An all in one solution – embedded system by UP and AI training software by Wahtari. This sophisticated solution includes UP Core Board, UP AI Core X – an AI accelerator powered by Intel® Movidius™ Myriad™ X, and Wahtari image-based AI systems, which enables users to develop various computer vision tasks such as Quality Control, Automatic Number-Plate Recognition, Facial Recognition.

With Wahtari end-to-end AI platform, the Wahtari nCam can detect objects efficiently with the support of 60 to 120 FPS. Additionally, this modular designed Wahtari nCam offers the possibility of swapping components to facilitate higher resolution or processing higher FPS.

Wahtari in-house nLab AI Platform

Key AI training processes in Wahtari nLab AI Platform:

Initial Capturing
Labeling
Training
Deploy

Wahtari nLab AI platform is built to readily adapt to unfamiliar plate styles, languages, and character types. The process begins by capturing fewer than 100 of the novel plates, which human operators manually label. These data entry enables nLab to retrain the deep-learning model at a Wahtari or customer data center.

Leverage this solution to train your own AI model is possible, the SKU will be available soon!

Wahtrai Consulting Services

Wahtari enables companies to unlock the potential of AI technologies in order to successfully compete internationally.

A toolchain optimized and continuously developed for this purpose enables us to respond individually to the problems of our customers and to train customized artificial intelligence in a short time.

Wahtari generates customer-specific AI models and delivers them on tailor-made hardware with integrated AI accelerators, and , you should expect 2 weeks to have your first custom AI model ready.

Wahtari nCam Details

Hardware overview

UP Core Board with Intel Atom® x5-Z8350 SoC, up to 1.92 GHz
UP AI Core X – Mini-PCIe card with Intel® Movidius™ Myriad™ X
UP Core high speed carrier board
Wahtari custom PCB
Wahtari nCam
DC power adapter (12V@2A)

Preinstalled Software

Linux: Custom Wahtari OS
Intel® Distribution of OpenVINO™ toolkit 2020.1 release
Intel® Distribution of OpenVINO™ toolkit Model Optimizer
OpenCV 4.x (Master channel)
Abandoned VULKAN AI Runtime
Wahtari nCam AI and Image processing Software stack
ONNX/Darknet/Tensorflow/Caffe model support

An AI-based inspection system can reliably detect complex situations and geometries at an image capturing rate of 60 to 160 fps. Regardless of the number, size, shape, material and position of the components – even under difficult viewing angles & lighting situations.

Wahtari AI Software Use Cases

Wahtari Vision

For productive use in operations

Wahtari nLab

The All-in-One solution for development & training of AI systems

Administration and generation of data sets
Autocompletion for acceleration during data input based on pretrained models
Labelling & Training
Single or multi-user application
On premise or cloud-based
End-to-end encryption
Any number of users

Deep LPR access control

Organise your entrances and exits using the latest technology. Wahtari LPR/ANPR nCam with numerous features is the heart of the system.

Persons & PPE detection

Ensure the integrity of your workers. Equip your facilities and machinery with Wahtari nCam to protect your workers. (Personal Protective Equipment Detection)

Quality control

Avoid unnecessary rejects by locating quality defects even more precisely and automatically rejecting only the affected products from your process. Reduce your production costs as well as your energy and material consumption. Make quality your competitive advantage.

"Due to our modular AI-Training Platform, we are using many different AI frameworks (provided by AAEON Technology), where ONNX simplifies the deployment processed of trained models, since they adhere to one shared standard. Intel® Distribution of OpenVINO™ toolkit is backed by a strong open-source community, great documentation, a deep integration into OpenCV and an easier to use API compared to competitors like TensorRT, CuDNN, etc. It also makes it possible to switch between different hardware for execution, like CPU, GPU, FPGAs and Movidius Chips, on-the-fly."

Sebastian Borchers

Co-founder of Wahtari

Wahtari ANPR nCam

Wahtari ANPR nCam deploys in UAE area, recognizing mixed Arabic languages & more than 70 different plate types.
Read the Application Story here to discover how Wahtari nCam tackled ANPR solution under an extreme circumstance where 52°C heatwave with intense dust, motion blur and complex lighting condition!

Smart cameras and deep learning for computer vision on the edge

#Webinar

The flexible and modular design of the Wahtari nCam, allows users to easily swap sensors with different resolutions and frame rates or inference speed. Utilizing Wahtari’s proprietary AI platform, you can develop a range of computer vision tasks from license plate recognition to quality control, analysis of medical images, or even facial recognition in the public security sector.

How UP can enhance Wahtari nCam

AI at the edge, powered by Intel® – it delivers power-efficient performance and specialized capabilities for new cases at the edge. The highly versatile Wahtari nCam is a powerful machine vision camera with deep learning capabilities, powered by Intel® Movidius™ Myriad™ X and Intel® Distribution of OpenVINO™ toolkit.

Vertical Markets

AI powering the smart, connected, data-centric world

Tech Specifications

Wahtari nCam
Hardware Components	- UP Core - Main computing board - UP High Speed Carrier Board - Ethernet connectivity - UP AI Core X - AI Accelerator - Wahtari Custom board - Wahtari nCam™ Lens Module
Wahtari nCam Imaging
Resolution (H × V pixels)	1280 × 720 1920 x 1200 (optional)
Sensor	Color, Progressive scan CMOS 1/3”
Max Frame Rate (at all resolution)	60 fps
Output Format	JPEG, MJPEG stream, VP8, H.264
Exposure Control	Global shutter
JPEG Quality	Adjustable between 40 % – 90 %
Day/Night Mode	Configurable day/night mode switching
Wahtari nCam Lens
Lens Type	6 - 22 mm with high precision motorized positioning 5 - 50 mm with high precision motorized positioning (optional)
Iris	Fixed Switchable (optional)
Focus & Zoom	Automatic motorized, programmable
Optical Filter	Fixed IR cut above 850 nm
Recommended ANPR Range	3 m – 20 m (10 feet – 65 feet)
Wahtari nCam Electrical
Input Voltage	12V DC (110/230V power supply available)
Basic Power Consumption	18W
Power Consumption With Heating	50 W (optional)
Conformity	CE, FCC, RoHS
Wahtari nCam Mechanical
Operating Temperature	Operating Temperature 0 °C – 55 °C (-40 °F – 131 °F)* * heated housing option available (-40°C - +55 °C)
Housing (optional)	IP67-rating
Dimensions (L × W × H)	147.00 mm × 87.10 mm × 61.50 mm (5.79" × 3.43" × 2.42")
Weight	325g (the whole solution)

The highly versatile Wahtari nCam is a powerful machine vision camera with deep learning capabilities.

Utilizing Wahtari’s proprietary AI platform, you can develop a range of computer vision tasks from license plate recognition, quality inspection analysis to medical images or even facial recognition in the public security sector.

The camera configuration is flexible. With a modularized design, the sensor can be swapped easily to different resolution and frame rates.

Wahtari nCam