Object-based Activity Recognition with Heterogeneous Sensors on Wrist
Citations
90 citations
Cites methods from "Object-based Activity Recognition w..."
...[43] utilized wrist-worn cameras to detect what object was currently being used....
[...]
61 citations
Cites background or methods from "Object-based Activity Recognition w..."
...[44] use a wrist-mounted camera and sensors to detect 15 classes of ADL recognition....
[...]
...Activity recognition in visual data is a widely studied problem in computer vision [22, 63, 35, 2], and a number of works have investigated this task in the domain of egocentric video [48, 8, 5, 30] and in combination with other wearable sensors [59, 44]....
[...]
47 citations
Cites background or methods from "Object-based Activity Recognition w..."
...Studies included in our survey mainly used triaxial acceleration signal, while some of them used additional signals to improve recognition accuracy such as [29], [32-34]....
[...]
...[33] KIT(7),DLY(1),HOS(1),SELF(1) MEN, ENG, FETP , FF AdaBoost, DT Precision 58....
[...]
...[33] compared two traditional algorithms, AdaBoost and DT, for examining the efficiency of classifier when collecting the data from heterogeneous sensors....
[...]
...Self-care Activities Applying makeup, Brushing hair, Shaving, Toileting, Flushing the toilet, Getting dressed, Brushing teeth, Washing hands, Washing face, Washing clothes, Drying hair, Taking medication [29] [32-35][53][60]...
[...]
...Daily Activities Ironing, Eating, Drinking, Using phone, Watching TV, Using computer, Reading book/magazine, Listening music/radio, Taking part in conversations, Getup bed, Sleeping, Note-pc, Carrying a box, Getting up [29][32-35][46][53][56][60][64][77]...
[...]
28 citations
Cites methods from "Object-based Activity Recognition w..."
...As with every machine-learning approach, this HMM approach to AR requires training data, which has to be “acquired in each user’s environment because these sensor data are environment dependent” [67]....
[...]
...In [67] hybrid discriminative/generative approach with hidden Markov model (HMM) is used for object-based AR....
[...]
19 citations
Cites background or methods from "Object-based Activity Recognition w..."
...Maekawa et al. (Maekawa et al., 2010) used a wrist-mounted camera and sensors to detect activities in daily living (ADL)....
[...]
...(Maekawa et al., 2010) used a wrist-mounted camera and sensors to detect activities in daily living (ADL)....
[...]
References
4,996 citations
"Object-based Activity Recognition w..." refers methods in this paper
...chieve fast object recognition [2,3] by comparing histograms and object models prepared in advance....
[...]
...Some studies also achieve fast object recognition [2, 3] by comparing histograms and object models prepared in advance....
[...]
286 citations
"Object-based Activity Recognition w..." refers background in this paper
...Many studies try to detect objects from images while taking occlusion, rotation, scale, and blur into account [5, 6]....
[...]
90 citations
61 citations
51 citations
"Object-based Activity Recognition w..." refers background in this paper
...In [4], the Mel-Frequency Cepstral Coefficient (MFCC) is reported to be the best transformation scheme for environmental sound recognition....
[...]