3D Target Detection on Real Time

target detection

This post is also available in: עברית (Hebrew)

A new method allows for target detection and imaging through cluttered scenes, enabling robust, real-time target reconstruction of complex moving scenes, and a fore-runner for the eventual sensing technologies needed for long-range automotive sensing, a key capability for next generation driverless cars. 

According to phys.org, the reconstruction of 3-D scenes has many important applications that are shaping our present and future, including autonomous cars, environmental monitoring and defense.

Researchers at Heriot-Watt University, in collaboration with researchers from the University of Toulouse, France, have proposed a novel framework that combines statistical models with highly scalable computational tools from the computer graphics community to accurately extract the 3-D information in real-time (50 frames per second).

The multidisciplinary research combines photonics, statistical image processing and computer graphics tools.

Prof. Stephen McLaughlin, head of the School of Engineering and Physical Sciences and one of the researchers said: “The ability to deliver real time 3-D video reconstruction enables the deployment of new sensing technologies for long-range automotive sensing, a key capability for next generation driverless cars.”

Prof. Gerald S. Buller from the Institute of Photonics and Quantum Sciences said: “This work represents the most advanced real-time 3-D image reconstruction of a complex real-world scene yet demonstrated.”

While primitive laser-based radar — or lidar — techniques are currently being used cars to assess distance to neighboring vehicles or other potential obstacles, the new method uses the advanced time-correlated single-photon counting lidar approach, allowing the use of eye-safe laser sources and enabling excellent resolution at long range (hundreds of meters to kilometers).

Recently, this technique was used to successfully reconstruct high resolution 3-D images in extreme environments such as through fog, with cluttered targets, in highly scattering underwater media, and in free-space at ranges greater than 10 km.

The findings were published in the scientific journal, Nature Communications.