Spatiotemporal volume video event detection for fault monitoring in assembly automation

Abstract

A major goal of many manufacturers is to minimize production downtime caused by machine faults and equipment breakdowns. This goal is typically achieved using sensor-based systems that can quickly detect and diagnose machine faults of various types. This paper proposes the use of a video event detection method based on spatiotemporal volumes (STVs) in a fault monitoring application to complement and improve upon existing systems. To detect faults, a set of image sequences are captured using a single web cam from the part dispensing region of an assembly machine testbed. The motion is segmented in each image creating binary frames which are stacked to build a STV. Normal operation of the machine is modeled by building a STV from several training sequences. New STVs are compared to the model and classified as either normal or faulty behaviour based on a calculated similarity measure. Both full-STV and partial-STV matching methods are tested. Test results show that the system is very effective on the data set collected. Recommendations for further exploration of this concept are made that include alternative video event detection techniques and different testbeds.