A newborn is preterm if birth occurred before a gestational age (GA) of 37 weeks. He has several immature functions, which implies a specific monitoring and, among others, the analysis of its sleep. Indeed, temporal organization of sleep stages is directly linked with maturation of its brain. By newborn, sleep stages are said “behavioral” and their annotation, performed by observing the baby, is subjective and time-consuming. Here we make a focus on Quiet Sleep (QS), whose increasing is primordial with increasing age, and characterized by an absence of motion and a regular cardio-respiratory rhythm. A method to automatically detect the QS is proposed, on the basis on a video analysis (detection of motion), supplemented with the processing of ECG and respiration signals (detection of “quality”). Both steps rely on a machine learning classification algorithm. The approach was first validated on a set of 15 newborns: 10 preterm (two dates: birth and discharge) and 5 full-term (one date: birth). For this purpose, a set of 25 eight-hours recordings were manually annotated and two features were extracted: (i) average duration of intervals (ADI) of QS and (ii) percentage of time in QS (%tQS). We considered each modality (motion, ECG, respiration) either one by one, two by two, and all three together. The best configuration was obtained by combining non-motion intervals and ECG quality, but showing also an overestimation of the QS (Se=88%, Sp=49%). However, regarding features, we observed similar trends between manual and automated QS, with an increasing of ADI and %tQS with increasing dates, also approaching values of the full-term newborns. Then, the computation of QS on a larger set of 45 recordings (23 newborns, five groups of GA, up to three dates) confirmed the interest of the approach for maturation evaluation purposes.