Accurate assessment of mobility in bed presents challenges to clinicians and researchers alike. It is traditionally performed by either overnight polysomnograph recording or wrist-actigraphy. A different approach is instrumenting the bed itself rather than the sleeping subject. This paper describes an alternative system for unobtrusive monitoring of mobility in bed that uses load sensors installed at the corners of a bed. This work is focused on the detection and classification of the type of movements based on the forces sensed by load cells. The accuracy of the system is evaluated using data collected in a laboratory. The system is capable of detecting voluntary movement with an average equal error rate of 3.22% (± 0.54). The approach for movement classification is based on Gaussian Mixture Models using a time-domain feature representation that correctly classified 84.6% of movements. Because the system allows both quantification and specification of movement, it has great potential for clinical use.