Skip to main content

More on WiFiSLAM standalone sensor fusion

A few weeks ago we wrote (here) about WiFiSLAM's demonstration of standalone sensor fusion (motion sensing) technology, running without any other methods assisting it. At the time we explained a few questions we had regarding their technology, particularly how they achieved their strong performance, while most others have needed to integrate sensor fusion with other technologies.

Since then, WiFiSLAM has answered some of our questions on their blog (here) - here is an excerpt from their article:


  • The demo video includes no maps constraints. It is purely accelerometer, gyroscope, and compass.
  • We are able to get better-than-typical accuracy because we are taking non-traditional pattern-matching approaches to sensor fusion rather than the conventional “double-integration + Kalman filter” techniques used traditionally.
  • We held the phone in front of us, trying to mimic a typical smartphone user who is following a map and walking while looking at their phone. Nothing super-specific.


See their blog article for more details of their sensor fusion technology and how it's deployed.

As we've written for over a year, we believe that sensor fusion has a huge potential that is only starting to be tapped.  Our reports on indoor location positioning technology have detailed research in the area, both by mobile software companies and by chip makers. The chip makers are particularly exciting, since hardware support could allow sensor fusion to run pervasively without loading down the smartphone CPU.

Some say that 2012 was the year that indoor location technology bloomed, but from what we report about research still in progress, we think that the best is yet to come.....

Comments

Popular posts from this blog

Intel demos indoor location technology in new Wi-Fi chips at MWC 2015

Intel made several announcements at MWC 2015, including a new chipset for wireless connectivity (Wi-Fi) in mobile devices. This new chipset, the 8270, include in-chip support for indoor location positioning. Below we explain their technology and show a video of it in action. With this announcement, Intel joins Broadcom, Qualcomm and other chip makers in moving broad indoor location positioning into mobile device hardware.

The transition of indoor location positioning into chips is a trend identified in the newest Grizzly Analytics report on Indoor Location Positioning Technologies, released the week before MWC 2015. By moving indoor location positioning from software into hardware, chips such as Intel's enable location positioning to run continuously and universally, without using device CPU, and with less power consumption.

Intel's technology delivers 1-3 meter accuracy, using a technique called multilateration, generating a new location estimate every second. While 1-3 meter …

Seeing Quuppa's indoor location technology at MWC 2015

I first met Fabio and Kimmo from Quuppa in 2012, before Quuppa existed, when they had spent years researching indoor location positioning technologies at Nokia Research Center. Less than a year after that they formed Quuppa, independent of Nokia, to bring their technology to market. At the time I called Quuppa "the newest and oldest in indoor location positioning."

Fast forward two and a half years. Their technology has reached market, it can now track both smartphones and BLE devices, and it's accurate to within 20-50cm. Before reading more about their technology, take a look at a video of their demo in action:



Grizzly Analytics has analyzed indoor location technologies by over 150 companies, and virtually all of the radio-based technologies operate by measuring the distance between the device being tracked and other radio devices, and using these distance measurements for either multilateration or fingerprinting. For example, the well known BLE beacons measure a device…

Robot Camera Foreshadows an Era of Location-Aware Electronics

A French company called Move 'N See produces a line of camera robots. Their devices act as a smart tripod, holding a video camera and automatically moving and zooming the camera as people of interest move around a site.

The idea is simple but amazingly innovative. Photo selfies are easy to take, but video selfies are next to impossible. How can I video myself playing football or doing gymnastics, without setting the camera so far back as to be useless? Do spectators want to spend an entire sporting event carefully videoing their friend or relative moving around the field?
Enter Move 'N See's "personal robot cameramen." Their devices aim, pan and zoom a video camera as one or more people move around an area. The people of interest wear armbands whose locations are tracked, enabling the camera controller to know where to aim the camera. The camera controller also includes enough smarts to adjust the camera smoothly and to capture multiple people evenly. The armband…