A new feature called "3D scene flow" in MVTec’s HALCON 12 machine vision software will enable users to detect and track the 3D motion of objects.
A new emerging technology in the automotive industry is the collision avoidance system, which detects an imminent front crash using optical sensors, radar, or a combination of the two, and provides warning, braking, and/or steering systems in response, according to MVTec. In addition, autonomous robot manufacturers are using 3D imaging to guide the motion of robots or autonomous vehicles. HALCON 12, which officially launched at the end of 2014, addresses the need for 3D motion tracking with its 3D scene flow feature.
3D scene flow works by using two consecutive stereo image pairs to determine uncalibrated (relative) and calibrated (real-world coordinate) 3D motion data. In the uncalibratred mode, 3D scene flow provides relative motion information in the form of optical flow (the 2D shift of features between consecutive images) plus the change in disparity of features between two consecutive stereo image pairs. Calibrated 3D scene flow provides 3D motion data by detecting and tracking the 3D position changes of surface points on a 3D object model found in consecutive point cloud scenes. In this case, the point clouds are reconstructed from the stereo image pairs.
Additional new features in HALCON 12 include an "automatic text reader," OCR function, which can handle variations in character features and can both detect and recognize characters in a single operation. Another feature is a set of improvements for MLP classifier, as well as an enhanced interface programming environment, HDevelop, including support for event-based processing.
In addition, MVTec’s new software will feature faster speeds, as it will utilize multi-core processors SSE2 and AVX, as well as GPU acceleration and AVX2, which will enable faster running times on state-of-the-art processors.
View more information on HALCON.
Share your vision-related news by contacting James Carroll, Senior Web Editor, Vision Systems Design
To receive news like this in your inbox, click here.
Join our LinkedIn group | Like us on Facebook | Follow us on Twitter | Check us out on Google +
