Optical Tracking - CNNLok

At a glance

© iStock

CNNLok offers camera-based, infrastructure-free positioning of mobile objects.

In the CNNLok system, mobile computers equipped with a camera use a special deep learning architecture to localize themselves within a learned environment. These capabilities can be implemented using everything from simple Android smartphones to embedded computers with multiple cameras. Reliable positions are calculated by continuously re-exploring the environment and with the help of an application-specific motion model.

The technology

CNNLok can even be used in environments that are subject to change, such as the varying loading status of high-bay storage in the logistics sector. The system can also learn positioning in areas where infrastructure cannot be deployed. Unlike traditional radio-based or optical technologies, it is capable of self-positioning without sensor infrastructure or the installation of any optical markers in the environment, as is often required by other self-positioning systems. The ability to calculate positions based solely on the static elements in the existing environment means that CNNLok is suitable for autonomous use and offers a high degree of versatility in many different areas of application.

Now that the technical feasibility of this idea has been confirmed, a team at Fraunhofer IIS is working on a practical solution. Although there are still a number of obstacles to overcome, the development of self-learning technology is proceeding at a rapid pace.

© Fotolia

How it works

The mobile processing unit uses a convolutional neural network (CNN) to calculate the current position based on a camera image. First, data is automatically acquired from thousands of camera images and the corresponding positions. The data is then used to further train an existing network in order to adapt it to the target environment, so that the finished network can determine the position of new images when deployed on the target platforms. To prevent the system from degenerating over time, updated information is continuously collected on a central processing unit for further training of the network and distribution to the mobile processors.

System components of CNNLok

The mobile processing unit is typically either a simple smartphone or an ARM- or Intel-based single-board computer with a standard camera. With its high level of versatility, the platform allows multiple application scenarios that cannot be covered using traditional, infrastructure-based solutions. Adapted motion models and special preprocessing of the collected data allow new data to populate an existing positioning system. Due to the intensive processing involved in continuously learning more about its environment, the system needs to be connected to other hardware via a network or docking station or by similar means. Depending on the dynamics of the area, there may also be a need for a central server with powerful standard deep learning hardware, such as graphics cards or special vector processors. This central processor would take over the duties of the mobile processing units at appropriate times – for example, when they need to be charged.

Applications and what we offer

Added value for industry

With its autonomous self-positioning capabilities, CNNLok offers vast potential for the optimization of workflows in logistics, even in dynamic environments. Downstream analytical applications could use these positioning capabilities to achieve efficiencies such as increased throughput of goods.


Added value for indoor positioning

For various indoor applications that need to get by without infrastructure and operate in a dynamic environment, indoor positioning could pave the way for the development of specific positioning solutions. In the retail sector, for example, it allows the creation of navigation services that can be implemented on a purely local basis on a smartphone.

Your partner in research

There are numerous other potential applications of CNNLok. The system opens up new possibilities by ensuring the positioning device’s autonomy, lack of reliance on positioning infrastructure, and tolerance of dynamic changes.

We would be delighted to work with you on the further development of CNNLok and to adapt the technology to meet your exact wishes and requirements.