Title: IBM Smart Surveillance System S3 Sales and Technical Training
1Emerging Topics in Video Surveillance
Rogerio Feris IBM TJ Watson Research
Center rsferis_at_us.ibm.com http//rogerioferis.com
2Outline
- Video Surveillance in Crowded Scenarios
- Online Learning Self-adaptation in
Surveillance - Other Recent Topics
3Simple Scenarios
- Few Objects Background Subtraction Tracking
High-level Event/Alert Detection
- Current systems work well
4Crowded Scenarios
- Many objects, occlusions, shadows, etc.
Object Segmentation, Tracking and Event Analysis
in crowded scenarios Open Problem!
5Parts-based Detectors
Pedro et al, A discriminatively trained,
multiscale, deformable part model, CVPR08
- Root filter (low-res) Parts filters (high-res)
6Parts-based Detectors
- Score of a window score of root score of
parts - Score of Parts Appearance Geometry
- Efficient localization of parts through Dynamic
Programming - SVM Classification (Structured prediction)
7Detecting Pedestrians in Crowds
Leibe et al, Pedestrian Detection in Crowded
Scenes, CVPR05
- Combination of different models bag of
features, segmentation, and chamfer matching
8Tracking in Crowds
Andriluka et al, People-tracking-by-detection
and people-detection-by-tracking, CVPR08
- Extends Leibe et al, CVPR05 to
temporal-domain and person articulation (parts)
estimation
9Crowd Segmentation
Dong et al, Fast Crowd Segmentation Using Shape
Indexing, ICCV07
10Crowd Analysis
Ali Shah, A Lagrangian Particle Dynamics
Approach for Crowd Flow Segmentation and
Stability Analysis, CVPR07
11Online Learning
12Offline Adaboost Learning
- Adaboost ensembles many weak classifiers into
one single strong classifier
- Initialize sample weights
- For each cycle
- Find a classifier/rectangle feature that performs
well on the weighted samples - Increase weights of misclassified examples
- Return a weighted combination of classifiers
13Offline Adaboost Learning
Major Problems
- Large number of examples required to train a
robust classifier - time consuming to label data
- slow training (may take several days)
- No Adaptation to particular surveillance
scenarios
14Learning from Small Sets
- Choice of Features (Levi Weiss, CVPR04)
- Co-Training (Levin Viola, ICCV2003)
- Online Adaptation
- Online Boosting (Oza01, Javed05, Bischof06,
Pham07)
15Online Boosting Oza,2001
- Train a generic strong classifier (set of weak
classifiers, of weak classifiers fixed) on a
small training set. - Online Process
- Given one single example with known label
- Slide the example over each weak classifier
- When the weak classifier receives the example
- update the weak classifier online
- update the weight of the example and pass to the
next weak classifier
16Online Boosting Oza,2001
17Online Boosting Oza,2001
18Online Boosting Car and People Detection Omar
Javed, CVPR05
- Train a generic strong classifier (set of weak
classifiers, of weak classifiers fixed) on a
small training set. - While running the classifier on unlabeled data,
if an example is confidently predicted by a
subset of weak classifiers ? use it for online
learning - Co-training framework
- BGS used for efficiency, for using more
expensive features, and for balancing the number
of positive and negative examples
19Online Boosting Car and People Detection Omar
Javed, CVPR05
20More Recent Work
- Helmut Hurst, Online Boosting and Vision,
CVPR06
- Bo Wu Nevatia, Improving Part-based Object
Detection by Unsupervised, Online Boosting,
CVPR07
- Pham Cham, Online Learning Asymmetric Boosted
Classifiers for Object Detection, CVPR07
- Huang et al.,Incremental Learning of Boosted
Face Detector, ICCV07 Boosting Adaptation
- IEEE Online Learning for Classification Workshop
(CVPR08)
21Other Recent Topics
22High-Resolution Imagery Kopf et al, Capturing
and Viewing Gigapixel Images, SIGGRAPH07
- How can we make use of high-resolution in video
analytics?
- Much more info e.g., in face reco skin
texture, iris, etc.
23Next Generation Neural Networks Hinton, Reducing
the dimensionality of data with neural networks,
Science 2006
- New algorithm for learning deep belief nets
- State-of-the art results in MNIST digit dataset
(better than SVMs) - Youtube talk at Google http//www.youtube.com/w
atch?vAyzOUbkUf3M - Matlab Code http//www.cs.toronto.edu/hinton/
24Learning with lots of data
- How can we recognize thousands of products in a
retail store for loss prevention? - 80 Million Tiny Images (http//www.cs.nyu.edu/f
ergus/)
Surveillance with Moving Cameras
- Cameras in vehicles, or even wearable cameras.
New challenges object detection, etc. - Leibe et al, Dynamic 3D Scene Analysis from a
Moving Vehicle, CVPR 2007
25Many more recent topics
- Check for papers in recent computer vision
conferences (like CVPR, ICCV, and ECCV) and also
specialized workshops/conferences such as AVSS
and PETS