Combining Detectors for Robust Head Detection
نویسندگان
چکیده
This paper, addresses the problem of detecting heads in crowded real world scenes, by combining a human head, an upper-body and a body detector to create a robust head detector. The idea is not to rely on a single detector. Instead, a head, an upper-body and a body detector, are used for decision making by combining their individual opinions to derive a consensus decision. The combined classifier is tested on the town centre dataset, and results show an 18% reduction in log-average miss rate of our combined classifier and illustrate that combining classifiers may perform better than a single head detector.
منابع مشابه
Toward robust foveated wide field of view people detection
We present a foveated vision system for robust person detection in wide field of view. The system consists of an omidirectional camera for people detection in a wide field of view and a pan-tilt camera that can focus on a particular location. Combining the information from both cameras leads to improved people detection. The people detection is based on human body part detectors and a probabili...
متن کاملطراحی و ساخت آشکارسازRETGEM سه گانه
The aim of this paper is to design, manufacture and test the first triple RETGEM detector. Using resistive electrode in RETGEM detectors made them more robust against the electrical discharge with respect to THGEM detectors. However, even these robust detectors are not protected against electrical discharge at gains higher than 105. Studying the role of dimensions of the triple RETGEMS detector...
متن کاملX Less is More: Building Selective Anomaly Ensembles
Ensemble learning for anomaly detection has been barely studied, due to difficulty in acquiring ground truth and the lack of inherent objective functions. In contrast, ensemble approaches for classification and clustering have been studied and effectively used for long. Our work taps into this gap and builds a new ensemble approach for anomaly detection, with application to event detection in t...
متن کاملCollaborative spectrum sensing by combining energy and cyclostationarity-based detection schemes
In this paper, the problem of spectrum sensing in cognitive radio communication networks is considered. This paper proposes a robust decision fusion scheme that can perform well when interference caused by other sources is present. Specifically, the proposed detection scheme is based on fusing the local decisions from energy detectors and cyclostationarity-based detectors. The proposed fusion s...
متن کاملCombining Detectors for Human Hand Detection
In this paper we present a hand detector system used for the Person Layout competition at PASCAL VOC Challenge 2010, in conjunction with an external head detector module. HOG features are extracted from the training set, and a clustering is performed in order to categorize the different poses that hands can have. A cascade of classifiers is trained for each one of the discovered hand subclasses...
متن کامل