Table 1 - uploaded by Hakan Erdogan
Content may be subject to copyright.
Source publication
We introduce a novel tracking technique which uses dynamic confidence-based
fusion of two different information sources for robust and efficient tracking
of visual objects. Mean-shift tracking is a popular and well known method used
in object tracking problems. Originally, the algorithm uses a similarity
measure which is optimized by shifting a sea...
Contexts in source publication
Context 1
... Table 1 we present tracking success ratios of trackers for different objects, where we also show situations that tracker has failed to track the ob- ject until the end with a * mark. The trackers are initialized using ground truth rectangles of the objects after they are fully visible in the frame. ...
Context 2
... Table 1 it can be seen that in all of the situ- ations where individual classifiers fail to track the object until the end, the tracker obtained with our fusion approach can track the object successfully. In addition, even in the cases where both classifiers can succeed individually, the measure presented in Equation (14) has always higher values with the tracker obtained with our fusion approach. ...
Similar publications
We present a face detection algorithm based on Deformable Part Models and
deep pyramidal features. The proposed method called DP2MFD is able to detect
faces of various sizes and poses in unconstrained conditions. It reduces the
gap in training and testing of DPM on deep features by adding a normalization
layer to the deep convolutional neural netwo...
We present a generative model which can automatically summarize the stroke
composition of free-hand sketches of a given category. When our model is fit to
a collection of sketches with similar poses, it discovers and learns the
structure and appearance of a set of coherent parts, with each part represented
by a group of strokes. It represents both...