Fast Global Kernel Density Mode Seeking: Applications to Localization and Tracking

• Published in: IEEE transactions on image processing Vol. 16; no. 5; pp. 1457 - 1469
• Main Authors: Chunhua Shen, Brooks, M.J., van den Hengel, A.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.05.2007; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Annealing; Applied sciences; Artificial Intelligence; Bandwidth; Computational complexity; Density; Density functional theory; Design methodology; Exact sciences and technology; fast mean shift (MS); global density mode; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; Information, signal and communications theory; Kernel; Mathematical analysis; Mathematical models; Monte Carlo methods; Motion; Optimization methods; Pattern Recognition, Automated - methods; Position (location); Reproducibility of Results; Sensitivity and Specificity; Signal processing; Studies; Target tracking; Telecommunications and information theory; Temperature; Tracking; Video Recording - methods; visual localization; visual tracking; Target tracking; Annealing; Similarity; visual tracking; Iterative method; Algorithm; Computational complexity; Video signal processing; global density mode; Global local method; Kernel method; Density function; Gradient method; Importance sampling; Object location; fast mean shift (MS); visual localization
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2007.894233

Tracking objects in video using the mean shift (MS) technique has been the subject of considerable attention. In this work, we aim to remedy one of its shortcomings. MS, like other gradient ascent optimization methods, is designed to find local modes. In many situations, however, we seek the global mode of a density function. The standard MS tracker assumes that the initialization point falls within the basin of attraction of the desired mode. When tracking objects in video this assumption may not hold, particularly when the target's displacement between successive frames is large. In this case, the local and global modes do not correspond and the tracker is likely to fail. A novel multibandwidth MS procedure is proposed which converges to the global mode of the density function, regardless of the initialization point. We term the procedure annealed MS, as it shares similarities with the annealed importance sampling procedure. The bandwidth of the procedure plays the same role as the temperature in conventional annealing. We observe that an over-smoothed density function with a sufficiently large bandwidth is unimodal. Using a continuation principle, the influence of the global peak in the density function is introduced gradually. In this way, the global maximum is more reliably located. Since it is imperative that the computational complexity is minimal for real-time applications, such as visual tracking, we also propose an accelerated version of the algorithm. This significantly decreases the number of iterations required to achieve convergence. We show on various data sets that the proposed algorithm offers considerable promise in reliably and rapidly finding the true object location when initialized from a distant point