The goal of SCIBA (Smart Cameras for Intelligent Behavior Analysis) is to develop robust techniques for the recognition of unexpected behavior of crowds and individuals in complex situations.
The goal encloses the following aims:
- a. Combine statistical features with tracking of individuals. Statistical features are more robust for a global decision of unexpected behavior with the drawback that no information of individuals is used. Global and local approaches can benefit from a combination of both.
- b. Improve computational performance of people detectors such as the detection using the histogram of oriented gradients (HOG) by learning spatial relationships in the scene in order to execute in real-time on smart cameras.
- c. Improve trajectory assignments for tracking using discriminative distance functions.
- d. Extend the two dimensional HOG model or another model to a three dimensional representation using a multi-camera setup.
The solution of the behavior recognition problem is important in many visual surveillance scenarios. Examples are:
- Bank robbery: Individuals who behave unexpected can be tracked and recorded. A possibility would be that the system locks all doors and calls the police when unexpected behavior is detected.
- Crowd analysis: General crowd analysis includes events such as evacuation, mass panic and gathering. Behavior recognition can be applied to detect unwanted events.
This project will be performed in cooperation with:
|A. Zweng and M. Kampel – “Introducing a Inter-frame Relational Feature Model for Pedestrian Detection”, Scandinavian Conferences on Image Analysis (SCIA 2013), pp.225-235, Espoo, Finnland, June 2013.|
|A. Zweng, T. Rittler and M. Kampel – “A Flexible Relational Feature Model for Fall Detection”, 10th International Conference on Signal Processing, Pattern Recognition and Applications (SPPRA 2013), pp.535-542, Innsbruck, Austria, Feb. 2013.|
|A. Zweng, M. Kampel – “Performance Evaluation of an Improved Relational Feature Model for Pedestrian Detection”, 15th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS 2013), Clearwater Beach, Florida, Jan. 2013.|
|A. Zweng, M. Kampel – “Using Depth Cameras and a Relational Feature Model for People Detection”, 25th International Conference on Intelligent Robots and Systems (IROS’12, CDCFR), Vila Moura, Algarve, Oct. 2012.|
|A. Zweng, M. Kampel – “Improved Relational Feature Model for People Detection using Histogram Similarity Functions”, 9th International Conference on Advanced Video and Signal-Based Surveillance (AVSS 2012), pp.422-427, Beijing, China, Sep. 2012.|
|A. Zweng, T. Rittler and M. Kampel – “Evaluation of Histogram-Based Similarity Functions for Different Color Spaces”, 14th International Conference on Computer Analysis of Images and Patterns (CAIP 2011), pp.455-462, Sevilla, Spain, Aug. 2011.|
|A. Zweng, M. Kampel – “Introducing Confidence Maps to Increase the Performance of Person Detectors”, 7th International Symposium on Visual Computing (ISVC’11), pp.446-455, Las Vegas, Nevada, Sep. 2011.|