Axis Ab

Adam Schill Collberg

Xing Danielsson Fan

Fredrik Pihl

Mattias Pettersson

Martin Santesson

Henrik Fasth

Maya Shah

Mikael Starvik

Magnus Mårtensson

Stefan Ekenberg

Andreas Johansson

Magnus Söderdahl

Magnus Martensson

Peter Wilhelmsson

Michael Evehammar

A method of transfer learning an object recognition neural network comprises acquiring a set of image frames; determining, by a first object recognition algorithm implementing an object recognition neural network, a plurality of object recognitions in the set of image frames; determining verified object recognitions by evaluating the plurality of object recognitions by a second, different from the first, object recognition algorithm, wherein an object recognition with a positive outcome in said evaluating forms a verified object recognition; forming a training set of annotated images comprising image frames associated with the verified object recognitions; performing transfer learning of the object recognition neural network based on the training set of annotated images.

Training of an object recognition neural network

Video encoding, and specifically to a method and an encoder which can adapt the probability of intra refresh of image frame subdivisions based on a count of image frames since a previous refresh and modulated through convex or concave shaped distribution functions are set forth herein.

Method for intra refresh encoding of a plurality of image frames using convex and concave distribution functions

A method of determining adjustment of an image pipeline setting comprises determining, by a controller, one or more settings for image data processing in the image pipeline; associating the one or more settings with a tag; transmitting the one or more settings to the image pipeline, wherein the tag is transmitted in association with the one or more settings; transmitting, from the image pipeline to the controller, feedback regarding image data processed with the one or more settings, wherein the tag is transmitted in association with the feedback; and determining, based on the received feedback and the one or more settings associated with the tag, an adjustment of the image pipeline setting.

Method and system for adjusting an image pipeline setting

Growing community of inventors

Lund, Sweden

Adam Schill Collberg