Title: Scene Understanding
1- Scene Understanding
- perception, multi-sensor fusion, spatio-temporal
reasoning - and activity recognition.
- Francois BREMOND
-
- Orion project-team,
- INRIA Sophia Antipolis, FRANCE
- Francois.Bremond_at_sophia.inria.fr
- http//www-sop.inria.fr/orion/orion-eng.html
- Key words Artificial intelligence,
knowledge-based systems, - cognitive vision, human behavior representation,
scenario recognition
2A scene understanding platform real-time
interpretation of videos from pixels to events
Segmentation
Classification
Scenario Recognition
Tracking
Alarms
access to forbidden area
3D scene model Scenario models
A priori Knowledge
3Video Understanding Applications
metro station monitoring
airport monitoring
train monitoring
building control access
4ETISEO performance evaluation depends on sensors
(position, type) and scenes conditions
strong perspective
shadows
tiny objects
lighting conditions
clutter
close view
5ETISEO selection of 6 sites for ETISEO video
acquisition.
6- Classification into more than 8 classes (e.g.
Person, Groupe, Train) based on 2D and 3D
descriptors (position, 3D ratio height/width, )
7Vandalism in metro station
8Fighting in metro station
9Posture Recognition silhouette comparison
Real world
Virtual world
10Multi sensors information fusion Lateral Shape
Recognition
11Bank agency monitoring
12Parked aircraft monitoring in Toulouse
- Toulouse-Blagnac Airport
- France
Apron
13Parked aircraft monitoring in Toulouse
Unloading Front Operation
14Scenario recognition Disturbing people in a
train
15HealthCare Monitoring
16HealthCare Monitoring
17HealthCare Monitoring Object detection and
tracking
(a) Segmentation
(b) Classification
(c) Tracking
18HealthCare Monitoring Object detection and
tracking
(a) Segmentation
(b) Classification
(c) Tracking
19HealthCare Monitoring Object detection and
tracking
(a) Segmentation
(b) Classification
(c) Tracking
20HealthCare Monitoring Object detection and
tracking
(a) Segmentation
(b) Classification
(c) Tracking
21HealthCare Monitoring Object detection and
tracking
(a) Segmentation
(b) Classification
(c) Tracking
22HealthCare Monitoring Object detection and
tracking
(a) Segmentation
(b) Classification
(c) Tracking
23Trajectory clustering in Torino subway (45min),
2052 trajectories
24- People Classification (based on 3D
parallelepiped) into 3 people classes 1Person,
2Persons, 3Persons, Unknown
25Posture Recognition Set of Specific Postures
Sitting
Bending
Lying
Standing
Hierarchical representation of postures