Sony unveils SDK for polarised camera modules

Sony Europe’s Image Sensing Solutions has launched a software development kit (SDK) for polarised camera modules which it says cuts machine vision application design time and costs. Stephane Clauss, senior business development manager Europe at Sony, says the company has worked with customers to identify key functions for the XPL-SDKW and develop optimised algorithms. “Depending on the dev team and application, a standard polarised-camera application would typically take between 6 to 24 months,” he
May 15, 2019 Read time: 2 mins

4551 Sony Europe’s 5853 Image Sensing Solutions has launched a software development kit (SDK) for polarised camera modules which it says cuts machine vision application design time and costs.

Stephane Clauss, senior business development manager Europe at 576 Sony, says the company has worked with customers to identify key functions for the XPL-SDKW and develop optimised algorithms.

“Depending on the dev team and application, a standard polarised-camera application would typically take between 6 to 24 months,” he continues.

Using the SDK, and its image processing library, this can be cut to 6-12 weeks, Clauss says.

Created to run on its XCG-CP510 polarised module, the XPL-SDKW comes with a set of functions which have been developed to run on a standard PC.

A ‘Cosine fit’ function allows developers to define a virtual polariser angle for the whole image while the ‘Average’ function creates a non-polarised image from raw data to simultaneously export what a standard machine camera would see for comparison, the company adds.

According to Sony, pre-processing functions calculate various polarisation specific information like the ‘degree of polarisation’ and the ‘surface normal vector’.

Detection, Monitoring & Machine Vision

For more information on companies in this article

Related Content

  • Luna unveils ‘cm-level’ positioning for e-scooters
    October 30, 2019
    Dublin-based start-up Luna has released a telematic device which it says uses 10cm-level positioning accuracy to help scooter companies ensure their scooters are ridden and parked correctly. The device uses GNSS/GPS positioning with an integrated correction service to achieve this accuracy. It also uses machine vision and artificial intelligence (AI) to recognise parking spaces in GPS blackspots via 2D images (QR codes) located in and around the site, the company adds. According to Luna, the device aug
    Read More
  • SafeRide: it’s time to act on cyberattacks
    May 10, 2019
    Cyber threats are increasing rapidly and conventional security measures are unable to keep up. Ben Spencer talks to SafeRide’s Gil Reiter about what OEMs can do now As more vehicles become connected, so the potential threats to their security increase. Gil Reiter, vice president of product management for security firm SafeRide, says the biggest ‘attack surface’ for connected cars is their internet connectivity - and the in-vehicle applications that use the internet connection. “The most vulnerable co
    Read More
  • Machine vision makes red light enforcement easier
    December 1, 2015
    Teledyne Dalsa’s Manny Romero looks at how the combination of camera manufacturer and software provider can make enforcement easier. Californian video analytics solution provider Eutecus develops real-time images capture and high speeds processing technology for applications including intelligent lighting and advanced driver assistance systems.
    Read More
  • The long road to Spanish enlightenment
    October 22, 2018
    Julián Núñez, immediate past president of ASECAP, gets his teeth into the vision of a European strategy for toll roads. David Arminas reports from Madrid. Getting European politicians to agree to a long-term cross-border highway infrastructure programme for toll roads is extremely difficult. It’s a bit like pulling teeth: people want to avoid the pain. But pain is something that Spanish operators, including Abertis, OHL, ACS, FCC and Acciona, have been going through for the past decade. The country has
    Read More

Highlighted Content