Commercial solutions for people monitoring make extensive use of pervasive technology in order to recognize abnormal behaviours, requiring considerable efforts for sensors installation, tuning and environment mapping as well as the employment of specialized staff. In order to provide a self-contained technology solution not requiring neither the environment rearrangement/redesign, nor the presence of specialized staff, nor a-priori information about elderly characteristics/habitude, the emphasis is placed on the detection of adverse events, such falls. People movements are acquired and tracked by a wall-mounded MESA SR3000 camera, overcoming the limitations of the wearable approaches for human monitoring (the devices are prone to be incorrectly worn or forgotten by users). The used active sensor allows to implement more efficient self-adapted vision algorithms since they are not affected by well-known issues of the passive vision systems such as time-varying light conditions, shadows and occlusions presence and dynamic background changes. The discussed monitoring system is quite innovative since the particular technology hasn't been investigated in AAL applications.
TOF cameras in ambient assisted living applications
Leone Alessandro;Diraco Giovanni
2013
Abstract
Commercial solutions for people monitoring make extensive use of pervasive technology in order to recognize abnormal behaviours, requiring considerable efforts for sensors installation, tuning and environment mapping as well as the employment of specialized staff. In order to provide a self-contained technology solution not requiring neither the environment rearrangement/redesign, nor the presence of specialized staff, nor a-priori information about elderly characteristics/habitude, the emphasis is placed on the detection of adverse events, such falls. People movements are acquired and tracked by a wall-mounded MESA SR3000 camera, overcoming the limitations of the wearable approaches for human monitoring (the devices are prone to be incorrectly worn or forgotten by users). The used active sensor allows to implement more efficient self-adapted vision algorithms since they are not affected by well-known issues of the passive vision systems such as time-varying light conditions, shadows and occlusions presence and dynamic background changes. The discussed monitoring system is quite innovative since the particular technology hasn't been investigated in AAL applications.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
