A method of abnormal habits recognition in intelligent space

• Proposed the concept of ISUS (intelligent space for understanding and service).
• Object location is achieved using a multi-camera positioning algorithm which combines head location with posture recognition.
• Obtain the key points' duration histogram according to the object's position.
• Get the data used to recognize abnormal habits by combining key points' duration histogram with the information of ISUS.
• Achieve abnormal habits recognition using SVM.

To provide intelligent care and accompaniment for solitary seniors, it is the premise to recognize and understand their habits correctly, and at the same time the abnormal habit recognition is the important part of the habit understanding. At present, most of the researches are concentrated on behavior or abnormal behavior recognition, whereas the studies about the habit recognition are relatively scarce. In this paper, a method is proposed to recognize abnormal habits using key points' duration histogram combining with information provided by intelligent space. The contribution of this paper is as follows: 1. proposing a multi-camera positioning algorithm which improves the positioning accuracy by combining head location with posture recognition. 2. Proposing a new recognition algorithm which realizes the abnormal habits recognition effectively by clustering the data obtained from combining key points' duration histogram with the information of ISUS (intelligent space for understanding and service). Experiments show that the abnormal habit of seniors can be recognized properly using the methods proposed above.

Figure optionsDownload as PowerPoint slide