Technologies for Ambient Assisted Living (AAL) combine new Information and Communication Technologies (ICT) to improve and increase the quality of life of the elderly. The SenseCam visual lifelogging device is now used not only to support memory recall, but also by research groups in other fields in order to investigate human lifestyle. Recent and continuing work in Dublin City University’s SCI-SYM centre has been an application and evaluation of a novel approach, namely use of the cross correlation matrix and Maximum Overlap Discrete Wavelet Transform (MODWT) to analyse SenseCam lifelog data streams. By examination of the eigenspectrum, we show that these approaches enable detection of key sources or major events in the time SenseCam recording, with MODWT also providing useful insight on details of major events. In this paper, we analyse the data collected from the EvAAL (Evaluating AAL System Through Competitive Benchmarking) competition. The results confirmed our previous findings [1, 2]. We believe that highlighting key episodes to identify event boundaries can be used to develop automatic classifiers for visual lifelogs, helping to infer different lifestyle characteristics.