Head-shoulder Detection

Proposal
12 May 2014
Head-shoulder Detection for human detection and tracking
Total votes: 0

Degree:

Head-shoulder Detection for human detection and tracking

Density aware person detection and tracking in crowds

This paper proposes a novel method for rapid and robust human detection and tracking based on the omega-shape features of people’s head-shoulder parts.
There are two modules in this method. In the first module, a Viola-Jones type classifier and a local HOG (Histograms of Oriented Gradients) feature based AdaBoost classifier are combined to detect head-shoulders rapidly and effectively.
Then, in the second module, each detected head-shoulder is tracked by a particle filter tracker using local HOG features to model target’s appearance, which shows great robustness in scenarios of crowding, background distractors and partial occlusions.
References: 

[1] - "Rapid and robust human detection and tracking based on omega-shape features" http://dx.doi.org/10.1109/ICIP.2009.5414008
[2] - "Robust Head-Shoulder Detection by PCA-Based Multilevel HOG-LBP Detector for People Counting" http://dx.doi.org/10.1109/ICPR.2010.509