Home

Awesome

jAER

Java tools for Address-Event Representation (AER) neuromorphic processing.

Permanent link: http://jaerproject.org

Welcome to the jAER Open Source Project Real time sensory-motor processing for event-based sensors and systems

Founded in 2007 to support event sensors and robot demonstrators developed by the Sensors Group, Inst. of Neuroinformatics, UZH-ETH Zurich.

What jAER feels like to use

jAER demo

Installation

You can find the latest releases at https://github.com/SensorsINI/jaer/releases.

Starting with jAER 2.0, (unsigned) binary installers are now available thanks to the multi-platform installer builder install4j.

Go to install4j jAER installers on dropbox to download installers. Windows: Click More info, Run anyway and Install anyway for unsigned app. MacOS: See opening unsigned dmg on MacOS. Right click, open with Archive Manager, and run the installer. Recommend to install to a user folder. Linux: Run the installer with sh <installer>.sh. Then you can jaer from the installation directory or gnome menu. See video installing and updating jaer on YouTube.

Quick start sample data

Device hardware support

Systems built with Sensors Group chips:

Event cameras from others:

Citation

T. Delbruck, “Frame-free dynamic digital vision,” in International Symposium on Secure-Life Electronics, University of Tokyo, Mar. 2008, pp. 21–26. doi: 10.5167/uzh-17620. Available: http://dx.doi.org/10.5167/uzh-17620

jAER applications

jAER originally targetted characterization of Sensors Group event cameras and silicon cochleas, but has also been used to build many robots: robogoalie (code), audio localization by spike ITD (code), speaker identification from spiking cochlea (code), laser goalie (code), pencil balancer (code), bill (money) catcher (code), slot car racer (code), Dextra roshambo (rock-scissors-poaper) (code), incremental learning of new roshambo hand symbols (code). jAER was also used to develop many event camera algorithms: Feature extraction (code), tracking (code), optical flow methods (code), EDFLOW hardware optical flow (code), and efficient and accurate event denoising (code).

Developing with jAER

To develop with jAER, see the jAER User Guide gdoc.

Support

Please use our GitHub bug tracker to report issues and bugs, or our Google Groups mailing list forum to ask questions.

See also

DVS128 cameras

Hotel bar scene with DAVIS140C