On-device computer vision
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 16 |
| Companies | 84 |
| Map changed | 2026-08-29 |
| Map | open the map |
On-device computer vision is a territory of the AI industry on map of ai. In short: on-device computer vision processes images and video locally on edge devices without sending data to cloud servers. The map lists 84 products and companies in 16 categories.
The map of on-device computer vision has 16 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
edge ai chips & npus8 products and companies · its own article →
model optimization & deployment runtimes8 products and companies
on-device object detection & tracking11 products and companies
on-device face & biometric recognition5 products and companies
Products and companies
industrial machine vision & quality inspection5 products and companies
Products and companies
on-device camera ai for smartphones4 products and companies
On-device camera AI performs computer vision tasks directly on smartphones without cloud processing, enabling real-time photo/video analysis, object detection, and augmentation. Used by consumers for photography, AR, accessibility, and privacy-conscious applications.
Open ground
Most devices still lack unified, developer-friendly APIs for custom on-device vision models, forcing app makers to choose between limited pre-built features or sending data to servers.
on-device pose & gesture estimation5 products and companies
Products and companies
on-device autonomous vehicle perception4 products and companies
On-device autonomous vehicle perception uses computer vision models running locally on vehicle hardware to detect objects, lane markings, and obstacles in real-time without cloud connectivity. Used by autonomous vehicle manufacturers, self-driving car platforms, and advanced driver assistance system (ADAS) developers.
Products and companies
on-device retail & checkout vision4 products and companies
Products and companies: amazon just walk out, standard ai, trigo, grabango.
on-device medical imaging & diagnostics3 products and companies
Products and companies: butterfly network, oxehealth, sight diagnostics.
on-device ar/xr spatial vision4 products and companies
Products and companies: apple vision pro ml, meta quest slam, magic leap 2, microsoft hololens 2.
smart cameras and edge vision hardware5 products and companies
Smart cameras and edge vision hardware are dedicated imaging devices that run computer vision models directly on the camera hardware without sending video to external servers. They are used by enterprises, security integrators, and developers building surveillance, monitoring, and inspection systems.
Products and companies: luxonis, hailo, axis communications, google coral, sony aitrios.
mobile camera and photo ai5 products and companies
Mobile camera and photo AI processes images and video on smartphones using on-device computer vision models to enhance photos, apply effects, and analyze visual content without cloud processing. Phone manufacturers, camera app developers, and social media platforms integrate these systems for users who take and edit photos on mobile devices.
Products and companies: google pixel camera, apple visual intelligence, samsung galaxy ai, google lens, snap.
on-device ar and tracking5 products and companies
On-device AR and tracking encompasses real-time spatial mapping, plane detection, and object tracking that runs locally on mobile devices and AR glasses without server calls. Developers of AR apps, enterprise logistics systems, and consumer AR platforms use this to anchor digital content to physical spaces.
Products and companies: niantic spatial, google mediapipe, apple arkit, 8th wall, vuforia.
automotive and driver monitoring vision4 products and companies
On-device computer vision systems that monitor driver behavior, attention, and cabin conditions in vehicles in real time. Automakers, fleet operators, and insurance companies deploy these systems to reduce accidents and liability.
on-device vision language models4 products and companies · its own article →
Software and runtime systems that enable large language and vision models to run locally on consumer devices without cloud connectivity. Developers, device manufacturers, and end users deploy these to process images and text with multimodal understanding on phones, tablets, and embedded systems.
Products and companies: moondream, smolvlm, gemma, liquid ai.
Papers, last 30 days:See also
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong.