The world's first Intelligent Vision Sensor with edge processing
Compared with just a few years ago, we are living in a different era. Consumers demand rights to personal privacy, and this is enforced with new data protection regulations around the world, including the EU General Data Protection Regulation (GDPR) from 2018, and the California Consumer Privacy Act (CCPA) from 2020, which aim to protect how personal data related to an identified or identifiable individual is collected and handled.
This global change in how privacy is understood and enforced has a huge impact on vision systems deployed in public or semipublic places, but also in private places following widely publicized data breaches from online security cameras. Customers now expect that their personally identifying data is handled securely and protected from data breaches.

Solutions using IMX500 can address these risks. The image data never leaves the chip, if you don't want it to. Use the IMX500 Intelligent Vision Sensor to process the image stream in real time, up to 30 FPS, and output the metadata results only for sensitive applications.
Aside from protecting personal privacy, many industrial vision system solutions need only output the results (the actual images are less important), which uses much less bandwidth than sending a video stream over the network.
IMX500 is the world's first Intelligent Vision Sensor with edge processing functionality, enabling high-speed edge AI processing without needing a round trip to a server.
IMX500 Key Benefits

One-chip solution
IMX500 has a stacked sensor structure combining an image sensor with a powerful DSP and dedicated on-chip SRAM to enable high-speed edge AI processing without needing a round trip to a server.
Optimized processing
IMX500 eliminates the need for high-performance processors or external memory, so your devices will be more reliable and cheaper to produce.


Low latency
Deploy, evaluate, and iterate any type of neural network. AI inference at the edge means image data does not need to be uploaded for processing, in turn meaning your solutions will benefit from lower latency and need less bandwidth and less power than traditional vision system solutions.
Low power & cost friendly
IMX500 eliminates the need for high-performance processors or external memory, so your devices will need less bandwidth and less power.
IMX500 uses industry-standard M12 (S-mount) lenses.
Deploy a new AI model and reuse the same hardware for different tasks.


Address Privacy Concerns
Protect your customer's personal privacy, and manage compliance with privacy regulations, by outputting the processed image metadata only. The image data never leaves the chip, if you don't want it to.
Intelligent Vision Sensor Solutions
Deploy any type of deep learning model to empower AI-enabled video analytics

Classify an object in an image

Localize and classify one or multiple objects in an image

Single person or multi-person keypoint detection

Take your image classification to the pixel level and understand the shapes of objects in an image
Industry Applications
Intelligent Vision Sensor IMX500 enables possibilities across almost any kind of industry

Create useful data about customer behaviors in real time

Image classification to understand shapes of objects

Check for safety equipment, mask detection, congestion detection

Line abnormality detection, worker monitoring, safety zone monitoring
IMX500 Developer Tools
The IMX500 developer tools provide opportunities to develop AI-equipped cameras, enabling a diverse range of applications in retail and industrial equipment industries and contributing to building optimal systems that link with the cloud
Development kit hardware

The IMX500 development kit includes Intelligent Vision Sensor hardware. There are a number of different hardware kits and components depending on your individual requirements.
User registration is required to access the developer tools. Let's get started >