An ambulatory fall monitor for the elderly

Tamura, Taku; Yoshimura, Takumi; Horiuchi, F.; Higashi, Yuji; Fujimoto, Toshiro

doi:10.1109/iembs.2000.901393

Cited by 27 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed object clustering algorithm comprises two iteration loops: the outer-loop iteratively handles individual object groups of the labeled macroblocks; whereas the inner-loop recursively clusters the object group labeled with a same label. The inner-loop first estimates the object motion using the sixparameter affine model of a classified object group as follows: The local object motion is then used to determine which macroblocks are outliers (i.e., those with MVs that are significantly different from the object motion model) as shown in (6). If the number of outlier macroblocks is greater than the threshold TH obj , implying that the object group has more than one object, the object macroblocks with MVs which conforms to the object motion model is labeled with a new object label.…”

Section: Object Clustering and Labelingmentioning

confidence: 99%

“…The main reasons elderly people become bedridden are apoplectic ictus, decrepitude, falls, and fractures [6]. Fall-related injuries have also been among the five most common causes of death amongst the elderly population [7].…”

mentioning

confidence: 99%

“…Most of the existing fall detection schemes described in [6]- [9] propose to use specially designed sensors and circuitry, which may not be convenient for the elderly to wear or bring all the time. Recently, several computer vision based techniques, such as object tracking, behavior understanding and description, personal identification, and event detection, have been developed for visual surveillance and homecare applications due to the wide deployment of low-cost video cameras [4][10] [11].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Compressed-domain Fall Incident Detection for Intelligent Homecare

Lin¹,

Ling²,

Chang³

et al. 2007

J VLSI Sign Process Syst Sign Im

View full text Add to dashboard Cite

--This paper presents a compressed-domain fall incident detection scheme for intelligent homecare applications. For object extraction, global motion parameters are estimated to distinguish local object motions from camera motions so as to obtain a rough object mask. We then perform change detection and/or background subtraction on the DC+2AC images extracted from the incoming coded bitstream to refine the object mask.Subsequently, an object clustering algorithm is used to automatically separate the individual video objects iteratively. After detecting the moving objects, compresseddomain features of each object are then extracted for identifying and locating fall incidents. Our experiments show that the proposed method can correctly detect fall incidents in real time.

show abstract

Section: Object Clustering and Labelingmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Compressed-domain Fall Incident Detection for Intelligent Homecare

Lin¹,

Ling²,

Chang³

et al. 2007

J VLSI Sign Process Syst Sign Im

View full text Add to dashboard Cite

show abstract

“…The main reasons elderly people become bedridden are apoplectic ictus, decrepitude, falls, and fractures [4]. Fall-related injuries have also been among the five most common causes of death amongst the elderly population [5].…”

mentioning

confidence: 99%

“…Most of the existing fall detection schemes described in [4]- [6] propose to use specially designed sensors and circuitry, which may not be convenient for the elderly to wear or bring all the time. Recently several computer vision based techniques, such as object tracking, behavior understanding and description, personal identification, and event detection, have been developed for visual surveillance and homecare applications due to the wide deployment of low-cost video cameras.…”

mentioning

confidence: 99%

Automatic Fall Incident Detection in Compressed Video for Intelligent Homecare

Lin

Ling

2007

2007 16th International Conference on Computer Communications and Networks

View full text Add to dashboard Cite

Abstract-This paper presents a compressed-domain fall incident detection scheme for intelligent homecare applications. First, a compressed-domain object segmentation scheme is performed to extract moving objects based on global motion estimation and local motion clustering. After detecting the moving objects, three compressed-domain features of each object are then extracted for identifying and locating fall incidents. The proposed system can differentiate fall-down from squatting by taking into account the event duration. Our experiments show that the proposed method can correctly detect fall incidents in real time.

show abstract