Mean shift is a non-parametric feature-space

Feature space

In pattern recognition a feature space is an abstract space where each pattern sample is represented as a point in n-dimensional space. Its dimension is determined by the number of features used to describe the patterns...

 analysis technique, a so-called mode seeking algorithm. Application domains include clustering in computer vision

Computer vision

Computer vision is a field that includes methods for acquiring, processing, analysing, and understanding images and, in general, high-dimensional data from the real world in order to produce numerical or symbolic information, e.g., in the forms of decisions...

 and image processing

Image processing

In electrical engineering and computer science, image processing is any form of signal processing for which the input is an image, such as a photograph or video frame; the output of image processing may be either an image or, a set of characteristics or parameters related to the image...

.

Overview

Mean shift is a procedure for locating the maxima of a density function given discrete data sampled from that function. It is useful for detecting the mode

Mode (statistics)

In statistics, the mode is the value that occurs most frequently in a data set or a probability distribution. In some fields, notably education, sample data are often called scores, and the sample mode is known as the modal score....

s of this density. This is an iterative method, and we start with an initial estimate . Let a kernel function be given. This function determines the weight of nearby points for re-estimation of the mean. Typically we use the Gaussian kernel on the distance to the current estimate, . The weighted mean of the density in the window determined by is



where is the neighborhood of , a set of points for which .

The mean-shift algorithm now sets , and repeats the estimation until converges.

Mean shift for visual tracking

The mean shift algorithm can be used for visual tracking. The simplest such algorithm would create a confidence map in the new image based on the color histogram of the object in the previous image, and use mean shift to find the peak of a confidence map near the object's old position. A few algorithms, such as Ensemble Tracking, expand on this idea.

Code implementations

• Scikit-learn library Numpy/Python implementation uses ball tree for efficient neighboring points lookup
• EDISON library. C++ implementation of mean-shift-based image segmentation
• OpenCV contains mean-shift implementation via cvMeanShift Method
• Aiphial. Java-based mean-shift implementation for numeric data clustering and image segmentation
• Apache Mahout. An map-reduce based implementation of MeanShift clustering written on Apache Hadoop.