Evaluation of a monitoring system for event recognition of older people

Over the last few years, the use of new technologies for the support of elderly people and in particular dementia patients received increasing interest. We investigated the use of a video monitoring system for automatic event recognition for the assessment of instrumental activities of daily living (IADL) in dementia patients. Participants (19 healthy subjects (HC) and 19 mild cognitive impairment (MCI) patients) had to carry out a standardized scenario consisting of several IADLs such as making a phone call while they were recorded by 2D video cameras. After the recording session, data was processed by a platform of video signal analysis in order to extract kinematic parameters detecting activities undertaken by the participant. We compared our automated activity quality prediction as well as cognitive health prediction with direct observation annotation and neuropsychological assessment scores. With a sensitivity of 85.31% and a precision of 75.90%, the overall activities were correctly automatically detected. Activity frequency differed significantly between MCI and HC participants (p < 0.05). In all activities, differences in the execution time could be identified in the manually and automatically extracted data. We obtained statistically significant correlations between manually as automatically extracted parameters and neuropsychological test scores (p < 0.05). However, no significant differences were found between the groups according to the IADL scale. The results suggest that it is possible to assess IADL functioning with the help of an automatic video monitoring system and that even based on the extracted data, significant group differences can be obtained.

show abstract

“…The study's results were consistent with those pre-432 viously presented in [32], where a recall of 88.…”

supporting

confidence: 88%

Validation of an Automatic Video Monitoring System for the Detection of Instrumental Activities of Daily Living in Dementia Patients

König

Crispim

Derreumaux

et al. 2015

JAD

View full text Add to dashboard Cite

show abstract

“…Constraints provide a generic basis to combine different sources of knowledge [ 8 , 9 ]. They can be handcrafted by domain experts [ 3 , 4 , 8 ], learned from data or obtained by a combination of both forms [ 9 ]. Knowledge-driven methods are generally associated to an ontological formalism to define domain concepts and their interrelations [ 8 , 10 ].…”

Section: Related Workmentioning

confidence: 99%

“…Prior work on knowledge-driven methods and color-depth sensing (e.g., Asus Xtion PRO Live) have demonstrated the benefits of this sensing approach (3D information about the scene and invariance to illumination changes) to track the position of hands and facial features during psychomotor exercises (cognitive rehabilitation) [ 6 ], to recognize fall events in hospital rooms [ 13 ], and to recognize complex daily living activities of senior people (e.g., making the bed). Finally, Crispim-Junior et al [ 3 ] compared the performance of event recognition between two different vision pipelines: a standard, color video camera and a color-depth sensor (Kinect ® with PrimeSense library). They have demonstrated that a pipeline with a standard color camera demanded a finer parameter tuning to handle low-level noise and achieve a performance comparable to the color-depth one.…”

Section: Related Workmentioning

confidence: 99%

“…However, this task is a challenging problem, far from being solved due to the unconstrained nature of real-life scenes, and the large intra-class variance of human activities (e.g., each person may have their own way of preparing coffee). The recognition of human activities has been explored from different sensor perspectives over the years, e.g., from ambient- [ 1 , 2 ] to visual-sensing [ 3 , 4 ], up to their combination [ 5 ]. Ambient sensing tends to equip the scene with several low-level sensors (e.g., microphones, presence and door contact sensors) and to monitor people activities by their interaction with (or disturbances in) the sensor network [ 1 , 2 ].…”

Section: Introductionmentioning

confidence: 99%

“…Although ambient sensing by low-level sensors has its advantages, like preserving people privacy, it may undermine the recognition and detailed description of complex activities by modeling them as a function of relatively simpler sensor states (e.g., kettle turned on, moved cup). As an alternative for low-level sensors, visual sensing focuses on the direct observation of people during the realization of activities [ 3 , 4 , 6 ], which fosters more detailed representations of activities. However, noise due to scene illumination changes and the estimation of 3D information from 2D data may degenerate the quality of vision systems using 2D video cameras and consequently degrade their performance.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Online Recognition of Daily Activities by Color-Depth Sensing and Knowledge Models

Crispim-Junior

Uría

Strumia

et al. 2017

Sensors

Self Cite

View full text Add to dashboard Cite

Visual activity recognition plays a fundamental role in several research fields as a way to extract semantic meaning of images and videos. Prior work has mostly focused on classification tasks, where a label is given for a video clip. However, real life scenarios require a method to browse a continuous video flow, automatically identify relevant temporal segments and classify them accordingly to target activities. This paper proposes a knowledge-driven event recognition framework to address this problem. The novelty of the method lies in the combination of a constraint-based ontology language for event modeling with robust algorithms to detect, track and re-identify people using color-depth sensing (Kinect® sensor). This combination enables to model and recognize longer and more complex events and to incorporate domain knowledge and 3D information into the same models. Moreover, the ontology-driven approach enables human understanding of system decisions and facilitates knowledge transfer across different scenes. The proposed framework is evaluated with real-world recordings of seniors carrying out unscripted, daily activities at hospital observation rooms and nursing homes. Results demonstrated that the proposed framework outperforms state-of-the-art methods in a variety of activities and datasets, and it is robust to variable and low-frame rate recordings. Further work will investigate how to extend the proposed framework with uncertainty management techniques to handle strong occlusion and ambiguous semantics, and how to exploit it to further support medicine on the timely diagnosis of cognitive disorders, such as Alzheimer’s disease.

show abstract

Uncertainty Modeling Framework for Constraint-Based Elementary Scenario Detection in Vision Systems

Crispim-Junior

Brémond

2015

Computer Vision - ECCV 2014 Workshops

View full text Add to dashboard Cite

Evaluation of a monitoring system for event recognition of older people

Abstract: Abstract

Cited by 20 publications

References 9 publications

Validation of an Automatic Video Monitoring System for the Detection of Instrumental Activities of Daily Living in Dementia Patients

Validation of an Automatic Video Monitoring System for the Detection of Instrumental Activities of Daily Living in Dementia Patients

Online Recognition of Daily Activities by Color-Depth Sensing and Knowledge Models

Uncertainty Modeling Framework for Constraint-Based Elementary Scenario Detection in Vision Systems

Contact Info

Product

Resources

About