In order to enhance the quality of life of people with mobility problems like Parkinson's disease or stroke patients, it is crucial to monitor and assess their daily life activities by characterizing basic movements like postural transitions, which is the main goal of this work. This paper presents a novel postural transition detection algorithm which is able to detect and identify Sit to Stand and Stand to Sit transitions with a Sensitivity of 88.2% and specificity of 98.6% by using a single sensor located at the user's waist. The algorithm has been tested with 31 healthy volunteers and an overall amount of 545 transitions. The proposed algorithm can be easily implemented in real-time system for on-line monitoring applications.