Rim Romdhane

Evaluation of a monitoring system for event recognition of older people

Population aging has been motivating academic research and industry to develop technologies for the improvement of older peoples quality of life, medical diagnosis, and support on frailty cases. Most of available research prototypes for older people monitoring focus on fall detection or gait analysis and rely on wearable, environmental, or video sensors. We present an evaluation of a research prototype of a video monitoring system for event recognition of older people. The prototype accuracy is evaluated for the recognition of physical tasks (e.g., Up and Go test) and instrumental activities of daily living (e.g., watching TV, writing a check) of participants of a clinical protocol for Alzheimers disease study (29 participants). The prototype uses as input a 2D RGB camera, and its performance is compared to the use of a RGB-D camera. The experimentation results show the proposed approach has a competitive performance to the use of a RGB-D camera, even outperforming it on event recognition precision. The use of a 2D-camera is advantageous, as the camera field of view can be much larger and cover an entire room where at least a couple of RGB-D cameras would be necessary.

Activity recognition and uncertain knowledge in video scenes

Activity recognition has been a growing research topic in the last years and its application varies from automatic recognition of social interaction such as shaking hands, parking lot surveillance, traffic monitoring and the detection of abandoned luggage. This paper describes a probabilistic framework for uncertainty handling in a description-based event recognition approach. The proposed approach allows the flexible modeling of composite events with complex temporal constraints. It uses probability theory to provide a consistent framework for dealing with uncertain knowledge for the recognition of complex events. We validate the event recognition accuracy of the proposed algorithm on real-world videos. The experimental results show that our system can successfully recognize activities with a high recognition rate. We conclude by comparing our algorithm with the state of the art and showing how the definition of event models and the probabilistic reasoning can influence the results of real-time event recognition.

A Framework Dealing with Uncertainty for Complex Event Recognition

This paper presents a constraint-based approach forvideo event recognition with probabilistic reasoning forhandling uncertainty. The main advantage of constraintbasedapproaches is the possibility for human expert tomodel composite events with complex temporal constraints.But the approaches are usually deterministic and do notenable the convenient mechanism of probability reasoningto handle the uncertainty. The first advantage of the proposedapproach is the ability to model and recognize compositeevents with complex temporal constraints. The secondadvantage is that probability theory provides a consistentframework for dealing with uncertain knowledge for arobust and reliable recognition of complex event. This approachis evaluated with 4 real healthcare videos and a publicvideo ETISEO’06. The results are compared with stateof the art method. The comparison shows that the proposedapproach improves significantly the process of recognitionand characterizes the likelihood of the recognized events.

Probabilistic recognition of complex event

This paper describes a complex event recognition approach with probabilistic reasoning for handling uncertainty. The first advantage of the proposed approach is the flexibility of the modeling of composite events with complex temporal constraints. The second advantage is the use of probability theory providing a consistent framework for dealing with uncertain knowledge for the recognition of complex events. The experimental results show that our system can successfully improve the event recognition rate. We conclude by comparing our algorithm with the state of the art and showing how the definition of event models and the probabilistic reasoning can influence the results of the real-time event recognition.

Combining multiple sensors for event recognition of older people

We herein present a hierarchical model-based framework for event recognition using multiple sensors. Event models combine a priori knowledge of the scene (3D geometric and semantic information, such as contextual zones and equipment) with moving objects (e.g., a Person) detected by a monitoring system. The event models follow a generic ontology based on natural language, which allows domain experts to easily adapt them. The framework novelty relies on combining multiple sensors at decision (event) level, and handling their conflict using a probabilistic approach. The proposed approach for event conflict handling computes the event reliability for each sensor, and then combines them using Dempster-Shafer Theory with an alternative combination rule. The proposed framework is evaluated using multi-sensor recording of instrumental daily living activities (e.g., watching TV, writing a check, preparing tea, organizing week intake of prescribed medication) of participants of a clinical trial for Alzheimers disease. Two evaluation cases are presented: the combination of events (or activities) from heterogeneous sensors (RGB ambient camera and a wearable inertial sensor) by a deterministic fashion, and the combination of conflicting events recognized by video cameras with partially overlapped field of view (a RGB- and a RGB-D-camera, Kinect®). The results show the framework improves the event recognition rate in both cases.

Automatic video monitoring system to detect apathy in Alzheimer's disease

Background: Apathy is one of the main neuropsychiatric symptoms in Alzheimer’s diseasewhich increases cognitive impairment and involves earlier institutionalization. Currently, evaluation of apathy is based on subjective scales as Apathy Inventory (AI) and domain Apathy of the Neuropsychiatric Inventory (NPI), or on more subjective tools as actigraphy. However, actigraphy only measures motor activity. We hypothesized that using postural and gait recognition with automatised video would bring objective data to recognize goal-directed activities and to measure apathy. Methods: AD patients with and without apathy are recruited in the memory center in Nice and performed a scenario in a smartroom with 2 camera and 3 worn-actigraph. The scenario is divided in 3 steps covering basic to more complex activities: 1) directed activities, 2) semi-directed activities, patients have a list of daily living activities to follow, 3) free activities. Patients are evaluatedwithMMSE, IADL,AI, NPI and diagnostic criteria for apathy. Results: Preliminary results confirm the feasibility this protocol. 20 AD patients were evaluated with this scenario. Only, two of them did not perform completely different activities because of anxiety. The results show that apathy correlate with lower goal-directed activities especially during all the step of the scenario. Besides, apathetic patients walked slowly (p < .05) and scores of apathy evaluated by AI clinician versio and item apathy of the NPI correlated significantly (p1⁄4 .02) negatively with shorter Step length (R 1⁄4 .79). Two clinical vignettes will be presented to compare some gait and postural parameters according to presence or not of apathy. Conclusions: The procedure seems to be acceptable for patients and elderly controls. Video processing is able to capture gait differences. Differences for more complex activities need to be demonstrated after inclusion of additional patients. These preliminary results probably premised to define judgment criteria for the different steps of the scenario and must be completed by a comparative study with two larger subgroups of AD patients according to the presence of apathy or not. This would bring more objective data to evaluate apathy.