Section: New Results

Introduction

This year Stars has proposed new algorithms related to its three main research axes : perception for activity recognition, semantic activity recognition and software engineering for activity recognition.

Perception for Activity Recognition

Participants : Julien Badie, Slawomir Bak, Piotr Bilinski, François Brémond, Bernard Boulay, Guillaume Charpiat, Duc Phu Chau, Etienne Corvée, Carolina Garate, Michal Koperski, Ratnesh Kumar, Filipe Martins, Malik Souded, Anh Tuan Nghiem, Sofia Zaidenberg, Monique Thonnat.

For perception, the main achievements are:

• Our new covariance descriptor has led to many publications and applications already. The work on this topic is now more about the precise use of the descriptor in varied applications than the design of new descriptors.

• The new action descriptors have led to finer gesture classification. As our target application is the detection of the Alzheimer syndrome from gesture analysis, which requires still finer descriptors, we will continue the work on this topic.

• The different shape priors developed (for shape growth enforcement, shape matching, articulated motion) have been formulated and designed so that efficient optimization tools could be used, leading to global optimality guarantees. These particular problems can thus be considered as solved, but there is still much work to be done on shape and related optimization, in particular to obtain shape statistics for human action recognition.

• The success obtained in the control of trackers is a proof of concept, but this work still needs to be pursued to get more practical and to be applied on more real world videos.

More precisely, the new results for perception for activity recognition are:

• People Detection for Crowded Scenes ( 6.3 ),

• Walking Speed Detection on a Treadmill using an RGB-D camera : experimentations and results ( 6.4 ),

• Head detection using RGB-D camera ( 6.5 ),

• Video Segmentation and Multiple Object Tracking ( 6.6 ),

• Enforcing Monotonous Shape Growth or Shrinkage in Video Segmentation ( 6.7 ),

• Multi-label Image Segmentation with Partition Trees and Shape Prior ( 6.8 ),

• Automatic Tracker Selection and Parameter Tuning for Multi-object Tracking ( 6.9 ),

• An Approach to Improve Multi-object Tracker Quality using Discriminative Appearances and Motion Model Descriptor ( 6.10 ),

• Person re-identification by pose priors( 6.11 ),

• Global tracker : an online evaluation framework to improve tracking quality ( 6.12 ),

• Human action recognition in videos ( 6.13 ),

• Action Recognition using 3D Trajectories with Hierarchical Classifier ( 6.14 ),

• Action Recognition using Video Brownian Covariance Descriptor for Human ( 6.15 ),

• Towards Unsupervised Sudden Group Movement Discovery for Video Surveillance ( 6.16 ).

Semantic Activity Recognition

Participants : Vania Bogorny, Luis Campos Alvares, Vasanth Bathrinarayanan, Guillaume Charpiat, Duc Phu Chau, Serhan Cosar, Carlos F. Crispim Junior, Giuseppe Donatielo, Baptiste Fosty, Carolina Garate, Alvaro Gomez Uria Covella, Alexandra Konig, Farhood Negin, Anh-Tuan Nghiem, Philippe Robert, Carola Strumia.

For activity recognition, the main advances on challenging topics are:

• The utilization by clinicians for their everyday work of a first monitoring system able to recognize complex activities, to evaluate in real-time older people performance in an ecological room at Nice Hospital.

• The successful processing of over 80 older people videos and matching their performance for autonomy at home (e.g. walking efficiency) and cognitive disorders (e.g. realisations of executive tasks) with gold standard scales (e.g. NPI, MMSE). This research work contributes to the early detection of deteriorated health status and the early diagnosis of illness.

• The fusion of events coming from camera networks and heterogeneous sensors (e.g. RGB videos, Depth maps, audio, accelerometers).

• The management of the uncertainty of primitive events.

• The generation of event models in an unsupervised manner.

For this research axis, the contributions are :

• Autonomous Monitoring for Securing European Ports ( 6.17 ),

• Video Understanding for Group Behavior Analysis ( 6.18 ),

• Evaluation of an event detection framework for older people monitoring: from minute to hour-scale monitoring and Patients autonomy and dementia assessment ( 6.19 ),

• Uncertainty Modeling Framework for Constraint-based Event Detection in Vision Systems ( 6.20 ),

• Assisted Serious Game for older people ( 6.21 ),

• Enhancing Pre-defined Event Models using Unsupervised Learning ( 6.22 ),

• Using Dense Trajectories to Enhance Unsupervised Action Discovery ( 6.23 ),

• Abnormal Event Detection in Videos and Group Behavior Analysis ( 6.24 ).

Software Engineering for Activity Recognition

Participants : François Brémond, Daniel Gaffé, Sabine Moisan, Annie Ressouche, Jean-Paul Rigault, Omar Abdalla, Mohamed Bouatira, Ines Sarray, Luis-Emiliano Sanchez.

For the software engineering part, the main achievements are the Software Engineering methods and tools applied to video analysis. We have demonstrated that these approaches are appropriate and useful for video analysis systems:

• Run time adaptation using MDE is a promising approach. Our current prototype resorts to tools and technologies which were readily available. This made possible a proof of concepts.

• Introducing metrics in feature models was valuable to reduce the huge set of valid configurations after a dynamic context change and to provide a real time selection of an appropriate running configuration.

• The synchronous approach is well suited to describe reactive systems in a generic way, it has a well-established formal foundation allowing for automatic proofs, and it interfaces nicely with most model-checkers.

The contributions for this research axis are:

• Model-Driven Engineering for Activity Recognition Systems( 6.25 ),

• Scenario Analysis Module ( 6.26 ),

• The Clem Workflow ( 6.27 ),

• Multiple Services for Device Adaptive Platform for Scenario Recognition ( 6.28 ).