The quality of our life is tied to the quality of our sleep. People with sleep deficits may experience impaired performance, irritability, lack of concentration, and daytime drowsiness. Increased mobility in bed can be a sign of disrupted sleep. Therefore, body movements in bed represent an important behavioral aspect of sleep. In this paper, we propose a method for detection and classification of movement that uses load cells placed at each corner of a bed. The detection of movements is based on short-term analysis of the mean-square differences of the load cell signals. Movement classification is based on features extracted from a wavelet-based multiresolution analysis (MRA) to classify the type of movement into two classes: small and large. A linear classifier is trained on each level of the MRA, and the decisions of the 4 classifiers are combined using a Bayesian combination rule. The method is evaluated on load cell data collected from 6 subjects. Each subject performed 5 trials composed of 20 predefined movements including small shifts of position to large movements of torso and limbs. The performance measure for the detection problem is the equal error rate (EER). We show that the detection method achieves a 2.9% EER and that the classification method has a classification error of 4%.