The Imaging Source blog

In order to efficiently access the performance features of the NVIDIA and Raspberry Pi 4 platforms for embedded vision applications, The Imaging Source offers a portfolio of MIPI CSI-2 board cameras. Many embedded machine vision applications (especially multi-camera applications) require cable lengths longer than the maximum 20 cm reached with MIPI CSI-2 cameras. Using the FPD-Link III bridge, cable lengths of up to 15m can be achieved. Image data is transmitted via a thin (Ø 2.8 mm) coaxial cable at up to 4.16 Gbps, with image data, control commands and power supply being transmitted simultaneously. The bandwidth is sufficient, for example, for the transfer of image data from a 5-MP camera at 30 frames/s. Developers can choose between MIPI-CSI-2 and FPD-Link-III board cameras as well as FPD-Link-III cameras with IP67-rated housing. The compact cameras are available as monochrome and color versions with the latest CMOS image sensors from Sony and On Semiconductor (global shutter and rolling shutter with resolutions from 0.3 MP [VGA] - 8.3 MP).

Why Choose MIPI CSI-2 or FPD-Link-III Camera Interfaces?

The Imaging Source provides MIPI CSI-2 and FPD-Link-III camera carrier boards with up to 6 camera inputs (platform dependent) for connecting the board cameras to the NVIDIA™ Jetson Nano®, Xavier NX, AGX Xavier and Raspberry Pi 4. Some users might be left wondering what the reasons are for using MIPI CSI-2 or FPD-Link-III cameras instead of USB-3 or GigE cameras. The answer lies in the hardware features of the embedded platforms themselves, namely the hardware-accelerated image signal processor (ISP). The embedded platforms' MIPI-CSI-2 interfaces are directly connected to the ISP to avoid latencies and data conversions. The Imaging Source's MIPI-CSI-2 cameras have been specifically designed to pass the raw image data directly to the interface. Since these embedded board cameras include only essential functionality, they are particularly cost effective. The ISP handles hardware-accelerated operations such as de-bayering, color correction, color space conversion, white balance, lens correction and image data compression (e.g. H.264/H.256).

Platforms Bring the Power of AI to Embedded Vision

In addition to their ISPs, the aforementioned embedded computers from NVIDIA (e.g. NVIDIA Jetson Nano, Xavier NX* and AGX Xavier*) offer a GPU with CUDA cores and several MIPI-CSI-2 camera interfaces which make them predestined for AI and demanding machine vision applications. The NVIDIA platforms are capable of running several neural networks in parallel to implement image segmentation, image classification and object recognition. The NVIDIA SDK "JetPack" supports all NVIDIA Jetson-based embedded platforms.

NVIDIA offers extensive software libraries for deep learning and for image and video processing. The Imaging Source provides the corresponding camera drivers, which are seamlessly integrated into the NVIDIA software framework. This allows image data to be transferred directly to a pre-trained deep learning module.

For less demanding image processing tasks, the Raspberry Pi 4 with a MIPI-CSI-2 camera interface and an ISP is also an excellent choice. Here too, the MIPI-CSI-2 interface is directly connected to the ISP. The Raspberry Pi 4, for example, is capable of compressing high-resolution H.264 images and sending them via Ethernet or WLAN.

The NVIDIA and Raspberry Pi embedded platforms are supported by a large open source and maker communities. Support questions can be posted in appropriate forums, where developers can exchange information with each other. NVIDIA also offers free online training courses on the subject of deep learning.

*The Imaging Source's latest embedded products for NVIDIA's Xavier NX and AGX Xavier platforms will be available in Q4 2020. Please contact us if you would like to be informed as the products become available.

The above article was published in the September 2020 edition of the German-language industry journal Markt&Technik under the title, FPD-Link III ergänzt MIPI CSI-2.

In addition to its comprehensive array of rule-based methods, MVTec HALCON offers a wide range of the latest deep learning technologies including object detection, classification and anomaly detection. As a certified distributor for HALCON*, The Imaging Source has tested HALCON's powerful deep learning functionality extensively in order to help you get started as quickly as possible with your deep learning projects.

Because required third-party libraries are directly integrated into the HALCON installer, the system is ready immediately after installation. HALCON's deep learning functionality enables users to take on inspection tasks that were previously impossible or required considerable programming hours.

MVTec HALCON also offers a data labeling tool (at no additional cost) whose labeled data can be seamlessly integrated into the HALCON development environment, HDevelop, enabling particularly rapid set up of robust AI modeling for successful deep-learning-based OCR, object detection, semantic segmentation and anomaly detection.

HALCON provides sample workflows featuring several convenience functions that simplify working with its deep learning technologies. Many of these sample workflows can be easily adapted to your own tasks, thereby eliminating the need to code complicated workflows for training and evaluation of your neural network. HALCON also performs automatic memory management, leaving you with one less thing to worry about.

Direct monitoring of training and current progress rounds out this collection of versatile, user-friendly software products that will enable you to get started using deep learning technologies in your own applications right away.

Contact us* for a free HALCON evaluation license and get started today. See for yourself how easy deep learning can be.

*Please Note: The Imaging Source is a certified MVTec distributor for Germany, Austria, Switzerland and number of other countries around the world. Please click here to find the authorized MVTec distributor for your country.

MVTec's newest version of their HALCON Progress Edition, HALCON 20.05, will be released on May 20, 2020. To mark the event, MVTec will host a free webinar to acquaint users with the latest improvements.

Included among the many improvements is the bar code reader's advanced decoding algorithm which can now read codes with an element size smaller than 1 pixel.

The performance of surface-based 3D matching for almost symmetric objects has been further enhanced by making use of small features within the objects.

In the field of deep learning technologies, HALCON 20.05 also comes with some major improvements: training for deep learning technologies can now be performed on the CPU. A dedicated GPU is no longer necessary and gives customers greater flexibility in implementing their deep learning algorithms on standard industrial PCs.

In support of the HALCON 20.05 release, MVTec is offering a webinar on May 26, 2020. Mario Bohnacker (Technical Product Manager) will introduce the latest additions and improvements and will answer your questions directly after the webinar in a short Q&A session.

Webinar

• Topic: MVTec HALCON 20.05
• Date and Time: May 26, 2020 at 9 a.m. (CEST)
• Speaker: Mario Bohnacker, Technical Product Manager HALCON
• Register for the webinar here.

Even if you are unable to attend the live webinar, a recording will be available shortly after the live session for those registered.

Since February, all of us find ourselves in a dynamic situation with regards to the SARS-CoV-2 (COVID-19) pandemic. The Imaging Source continues to closely monitor the latest developments in order to anticipate and plan for any potential disruptions to our supply chain which might impact our delivery capabilities.

In accordance with state and federal guidelines, the majority of our employees are working from home, allowing The Imaging Source to remain fully operational while ensuring that the remaining on-site employees are able to maintain appropriate social distancing measures. Our sales, order processing and support personnel are available as usual to assist you with all of your new and existing projects and orders.

The Imaging Source holds high levels of production-critical inventory and we will remain in constant contact with our suppliers in order to ensure supply chain integrity. In addition to our supply chain management, our two production facilities in Germany and Taiwan afford us the flexibility and capacity to maintain regular production activities.

As this remains a fluid situation, we will inform customers of any significant changes impacting our ability to maintain our stated delivery times.

Since 1990, The Imaging Source has been delivering high-performance industrial cameras for automation, quality control, logistics and medical/pharmaceutical applications. The Imaging Source's 2020 catalog features a wide variety of industrial and board-level cameras based on the latest Sony and ONSemi sensors. New product offerings include:

1. NVIDIA development kits
2. MIPI board cameras
3. FPD-Link III board cameras
4. FPD-Link III IP67 housed cameras
5. Polarization cameras
6. 20x optical zoom cameras

In addition to our comprehensive camera portfolio, The Imaging Source also provides an extensive range of lenses and accessories.

You can immediately download the catalog
(no registration required):

Download Catalog