ISRA MONO3D system automates body-shop operations through vision-guided robot autoracking
SEPTEMBER 6--Automation specialist Comau Pico (Southfield, MI) has purchased 20 MONO3D machine-vision systems to automate body-shop operations at two North American automotive manufacturing locations. Each ISRA VISION (Lansing, MI) system includes cameras, cabling, LED lights, and MONO3D software running on an ISRA VISION controller. ISRA's national sales manager for North America, Kevin Taylor, says "These systems will be used to remove sheet-metal parts from racks for placement into fixtures for the assembly of the car body eliminating manual load. MONO3D's small footprint enables the cameras and lights to be mounted on the robot end effector to improve the overall accuracy of robot guidance solution. MONO3D will locate the part in six degrees of freedom using predefined part features such as holes or edges and guide the robot to the part in 3-D space.
ISRA VISION released MONO3D in early 2004 in response to customer requests for a more cost-effective 3-D automated machine-vision system with a smaller footprint for robot guidance, 3-D inspection, and similar applications. MONO3D only requires one camera to measure multiple points in the camera's 3-D field of view with accuracy and speed comparable to more expensive laser-based and multi-camera based 3-D machine-vision systems. With large parts multiple cameras can be utilized to determine the objects 3-D location providing considerable speed and cost savings compared to traditional stereovision systems, which would require multiple cameras for each field of view.
MONO3D extracts 3-D data by locating three or more features in an image, determining the spatial relationships between those features, and comparing that to stored 3-D models based on CAD data. ISRA VISION's MONO3D system can precisely establish all six degrees of freedom (position and orientation) of any point within the camera's field of view.
This approach not only drastically reduces the outlay for equipment, but also the cost of installation, calibration, and operation. MONO3D's single-camera approach and flexibility enables more efficient image processing, reducing hardware costs on both the acquisition and processing ends of the machine-vision system, while allowing customers to improve throughput based on the specific needs of the application. MONO3D's easy configurability gives the user maximum flexibility to determine spatial resolution, speed and throughput by accommodating a virtually unlimited number of additional features into its calculations or by limiting the 3-D vision to 2-D or 2.5 D (x, y, rotation, and a scaling of z), depending on the needs of the application.