Innovations in Visual Systems: Embedded AI Cameras

Today, we will provide a detailed analysis of

the important steps to consider

when selecting an embedded vision camera,

such as: functionality groups, form factors, and physical footprint,

interface options, lens mounts, software support,

thermal management, and electromagnetic compatibility, etc.

When transitioning from a packaged camera to a board-level camera, system designers should carefully consider the imaging and camera performance requirements. Many small board-level cameras only support low-resolution sensors, a limited number of GPIO lines, and have restrictions on the internal functions of the camera. In contrast, many fully functional machine vision cameras in board-level models are merely standard cameras stripped of their housing. While these cameras can achieve the desired imaging performance, their size may not be significantly smaller than standard packaged models. These cameras often use standard GPIO and interface connectors, which are too large for embedded applications. For example, the size of traditional industrial locking connectors is about the same as a Blackfly S board-level camera.

For customers looking to integrate non-standard optical components or place the image sensor as close to the target as possible, board-level cameras are an attractive option. Board-level cameras do not have fixed lens mounts, allowing designers to freely choose optical components, and the machine vision industry typically does not use standard C, CS, or S interface lenses. This design is also very suitable for biotechnology and laser beam analysis applications that usually do not require lenses. Another common application for board-level cameras is to integrate the lens mount into another product component, hence referred to as “embedded vision”. Additionally, integrating the lens mount directly into the product housing using molded techniques can effectively simplify manufacturing and assembly, thereby further reducing costs. To evaluate board-level cameras without lens mounts, installation accessories should also be purchased. If the packaged model has the same sensor and functionality as the board-level model, they can be used as a development platform.

When selecting the correct lens mount options for board-level cameras, one of the most important factors is the size of the sensor being used. Typically, S-type mount lenses are designed for low-resolution sensors (usually below 2MP) of 1/3″ or smaller. CS-type mount lenses are designed for sensors from 1/3″ to 1/2″, and if the sensor size is 1/2″ or larger, it is better to use C-type mount lenses.

Packaged machine vision cameras rely on their housing surface area to dissipate heat generated by the sensor, FPGA, and other components. Without housing, high-performance board-level cameras may have other design requirements to ensure they operate within the recommended temperature range. In this case, providing sufficient heat dissipation is key. Manufacturers typically provide the highest junction temperature for the hottest components. For FLIR Blackfly S cameras, the specified maximum junction temperature for the FPGA is 105 ℃ (221 ℉).

System designers must ensure that their thermal management solutions meet this specification. The size of the heatsink, the surface area of the rack where the camera is mounted, or the type of active heatsink required depends on the sensor, frame rate, operating environment, and the amount of camera image processing being performed. To facilitate the installation of heatsinks on the camera, we recommend using thermal paste on thermal pads to minimize board stress on the camera.

In most cases, board-level cameras are directly integrated into embedded vision systems/products without the need for housing. However, for applications where the camera is not integrated into a product, exposing the internals to components, it may be necessary to use housing to prevent damage. During rapid prototyping, embedded system designers can easily design and print a camera housing using a 3D printer or use a generic plastic housing that accommodates the camera, then use spacers and mounting brackets to secure the camera in place.

USB 3.1 is the ideal interface for embedded systems, whose universal functionality ensures support for various hardware from desktop computers to ARM processor-based single-board computers (SBC). Direct Memory Access (DMA) keeps latency to a minimum without the need for filter drivers. USB 3.1 also uses a single cable for power and provides data throughput of up to 480 MB/s, effectively simplifying mechanical and electrical design.

One important goal for embedded system designers is to miniaturize existing designs. In this case, the maximum length of the cable is far less important than the size of the cable and connectors. Flexible printed circuit (FPC) cables can reach lengths of up to 30 meters and support USB 3.1.FPC cables, as the name implies, are cables that can be bent and twisted to fit tight packaging systems. Additionally, high-quality locking connectors and FPC shielded cables with locking tabs ensure highly secure, reliable connections.

However, USB 3.1 interfaces have a potential drawback, as their high-frequency signals can cause interference to wireless devices up to 5 GHz (such as GPS signals). For applications using such wireless frequencies, we also offer FLIR board-level cameras with GigE interfaces.

MIPI CSI is another universal interface used by many embedded motherboards. However, compared to USB, the complexity of MIPI protocols and drivers may make development more time-consuming. Low Voltage Differential Signaling (LVDS) interfaces are also available and are designed for direct connection to host-side FPGAs; however, each signal transmission channel requires two wires, which can be a minor yet significant drawback in some applications.

When selecting cameras for embedded systems, software support is an important consideration that cannot be overlooked. With SDKs that support both desktop and embedded systems, designers can easily develop vision applications using familiar tools and deploy them to the chosen embedded platform. FLIR’s Spinnaker SDK supports Windows and Linux desktop systems based on x86, x64, and ARM processors.

If there is no shielding effect provided by the housing, the electromagnetic compatibility (EMC) of board-level cameras will differ from packaged models. All packaged FLIR machine vision cameras are EMC certified, but board-level cameras have not undergone this certification. These board-level cameras must be embedded into other products/systems and therefore require separate certification for the finished products. Regardless of the application, we recommend following best practices for managing electromagnetic interference (EMI) just as with other electrical components.

Board-level cameras have revolutionized embedded vision systems, making the design of compact and multifunctional innovative products more flexible and free. In addition to the factors mentioned above, attention should also be paid to using high-quality sensors, optical components, and reliable parts to adapt your embedded system for the future. FLIR’s full range of board-level cameras is designed for these applications and offers an industry-leading 3-year warranty.

If you want to learn more about FLIR machine vision products,

you can click to follow the official WeChat account of “FLIR“

to explore more professional knowledge together~

Click “Read the Original” to discover more secrets~