Tracking and Recognition in Camera Networks

Scallop

Figure 1: Our Scallop framework for distributed sensor networks.



SCALLOP: An Open Peer-to-Peer Framework for Distributed Sensor Networks

Scallop

Figure 2: Sensors nodes and their locations.

Description:

Related Publication:



Object Tracking and Recognition in Camera Networks

tracking3.png

Description:

An object tracker produces a sequence of images of the tracked object. This temporal information can be exploited in object re-identification across camera views. We have developed a classification algorithm for learning and matching such image sequences. Adaptive boosting (AdaBoost) and classification trees are used for learning while a wide collection of features (shape, pose, color, texture, etc.) form an object model.

Related Publication:



Template Matching

tracking4.png

Description:

We propose a method of person re-identification based on color self-similarity. The spatial distributions of self-similarities w.r.t. color words are combined to characterize the appearance of pedestrians. Promising results are obtained in the public ETHZ database compared with state-of-art performances.

Related Publication:



Group Matching

tracking5.png

Description:

We present a new solution to the problem of matching groups of people across multiple non-overlapping cameras. Similar to the problem of matching individuals across cameras, matching groups of people also faces challenges such as variations of illumination conditions, poses and camera parameters. Moreover, people often swap their positions while walking in a group.

Related Publication:



Tracking Multiple Objects Using Color, Texture and Motion

tracking6.png

Figure 6: Multi-object tracking.

Description:

Related Publication:



Camera Topology

tracking7.png

Description:

Related Publication:

CMV/Research/TrackingAndRecognitionInCameraNetworks (last edited 2012-11-02 15:06:27 by HannuRautio)