People Tracking and Recognition using the Multi-Object Particle Filter Algorithm and Hierarchical PCA Method

Schleicher, David; Bergasa, Luis M.; Barea, Rafael; López, Elena

doi:10.1109/eurcon.2005.1630116

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After background subtraction, Schleicher et al [17] used a Particle Filter (PF) algorithm to identify and individually track any moving objects. They applied PCA to each object in order to classify it into a person or a nonperson category by using geometrical constraints of several body parts.…”

Section: A Human Classificationmentioning

confidence: 99%

Vision-Based Toddler Tracking at Home

Qin

Wright

2007

EUROCON 2007 - The International Conference on "Computer as a Tool"

View full text Add to dashboard Cite

Abstract-This paper presents a vision-based toddler tracking system for detecting risk factors of a toddler's fall within the home environment. The risk factors have environmental and behavioral aspects and the research in this paper focuses on the behavioral aspects. Apart from common image processing tasks such as background subtraction, the vision-based toddler tracking involves human classification, acquisition of motion and position information, and handling of regional merges and splits. The human classification is based on dynamic motion vectors of the human body. The center of mass of each contour is detected and connected with the closest center of mass in the next frame to obtain position, speed, and directional information. This tracking system is further enhanced by dealing with regional merges and splits due to multiple object occlusions. In order to identify the merges and splits, two directional detections of closest region centers are conducted between every two successive frames. Merges and splits of a single object due to errors in the background subtraction are also handled. The tracking algorithms have been developed, implemented and tested.

show abstract

Section: A Human Classificationmentioning

confidence: 99%

Vision-Based Toddler Tracking at Home

Qin

Wright

2007

EUROCON 2007 - The International Conference on "Computer as a Tool"

View full text Add to dashboard Cite

show abstract

“…After background subtraction, Schleicher et al [17] used environments, only domestic lighting changes are dealt with. a Particle Filter (PF) algorithm to identify and track any As background subtraction detects anything which does moving objects individually.…”

Section: After Background Subtraction Human and Non-humanmentioning

confidence: 99%

A Smart Vision Sensor for Detecting Risk Factors of a Toddler's Fall in a Home Environment

Na¹,

Qin²,

Wright³

2007

2007 IEEE International Conference on Networking, Sensing and Control

View full text Add to dashboard Cite

Abstract-This paper presents a smart vision sensor for environmental hazards (such as slippery surfaces) and detecting risk factors of a toddler's fall in an indoor home perilous activities (such as inattentive walking) [11]. As environment assisting parents' supervision to prevent fall intrinsic factors are associated with health problems, a normal injuries. We identified the risk factors by analyzing real fall toddler's fall would be based on the extrinsic factors which injury stories and referring to a related organization's include their environments and activities. Therefore, this suggestions to prevent falls. In order to detect the risk factors injuries when they fall. As young children are not able to assess risks for 3) ensure that there is no furniture around available for them themselves, the best way to prevent their falls would be to climb on. continuous supervision and instruction from their parents.Based on the above studies, the risk factors to recognize by However, this is not always practical. A smart vision sensor is our sensor were identified as follows: proposed in this paper to assist the parents' supervision for 1) check if clutter has appeared on the floor. preventing fall injuries. 2) check if a toddler moves around when clutter is presentMany applications have been developed to detect on the floor. potentially fatal falls of the elderly [3][4][5][6][7][8][9][10]. Acceleration 3) check if a toddler moves too close to any structure in sensors worn by users and cameras were used in these cases their environment.for detecting falls. Although some of them collected the fall 4) check if a toddler climbs any furniture. data from the sensors to evaluate the user's personal fall risksThe first factor was defined for places such as a corridor for later prevention, there was no prevention against falls where clutter should not be on the floor and could even trip during the data collection and also against irregular falls adults. The second factor was defined for the case that a afterwards. Some wearable devices provided prompt toddler is playing with toys on the floor of a play room. If a protection such as an airbag and an overhead tether when toddler sits still while playing with the toys, the toys do not sensing a fall, but required the user to wear these all the time.

show abstract