Video tracking is the process of locating a moving object (or multiple objects) over time using a camera. It has a variety of uses, some of which are: human-computer interaction, security and surveillance, video communication and compression, augmented reality, traffic control, medical imaging and video editing. Video tracking can be a time consuming process due to the amount of data that is contained in video. Adding further to the complexity is the possible need to use object recognition techniques for tracking, a challenging problem in its own right.
The objective of video tracking is to associate target objects in consecutive video frames. The association can be especially difficult when the objects are moving fast relative to the frame rate. Another situation that increases the complexity of the problem is when the tracked object changes orientation over time. For these situations video tracking systems usually employ a motion model which describes how the image of the target might change for different possible motions of the object.
Examples of simple motion models are:
- When tracking planar objects, the motion model is a 2D transformation (affine transformation or homography) of an image of the object (e.g. the initial frame).
- When the target is a rigid 3D object, the motion model defines its aspect depending on its 3D position and orientation.
- For video compression, key frames are divided into macroblocks. The motion model is a disruption of a key frame, where each macroblock is translated by a motion vector given by the motion parameters.
- The image of deformable objects can be covered with a mesh, the motion of the object is defined by the position of the nodes of the mesh.
To perform video tracking an algorithm analyzes sequential video frames and outputs the movement of targets between the frames. There are a variety of algorithms, each having strengths and weaknesses. Considering the intended use is important when choosing which algorithm to use. There are two major components of a visual tracking system: target representation and localization, as well as filtering and data association.
Target representation and localization is mostly a bottom-up process. These methods give a variety of tools for identifying the moving object. Locating and tracking the target object successfully is dependent on the algorithm. For example, using blob tracking is useful for identifying human movement because a person's profile changes dynamically. Typically the computational complexity for these algorithms is low. The following are some common target representation and localization algorithms:
- Blob tracking: segmentation of object interior (for example blob detection, block-based correlation or optical flow). Blob detection refers to mathematical methods that are aimed at detecting regions in a digital image that differ in properties, such as brightness, hue or color, compared to the areas that are surrounding those regions.
- Kernel-based tracking (mean-shift tracking): an iterative localization procedure based on the maximization of a similarity measure (Bhattacharyya coefficient).
- Contour tracking: detection of object boundary (e.g. active contours or Condensation algorithm). Contour tracking methods iteratively evolve an initial contour initialized from the previous frame to its new position in the current frame. Our approach to contour tracking directly evolves the contour by minimizing the contour energy using gradient descent.
- Visual feature matching: registration
- Particle filter tracking: a hypothetical tracker, that approximates the filtered posterior distribution by a set of weighted particles. It weighs particles based on a likelihood score and then propagates these particles according to a motion model. Various parameters such as color histogram is used to determine the position of particles.
Filtering and data association is mostly a top-down process, which involves incorporating prior information about the scene or object, dealing with object dynamics, and evaluation of different hypotheses. These methods allow the tracking of complex objects along with more complex object interaction like tracking objects moving behind obstructions. Additionally the complexity is increased if the video tracker (also named TV tracker or target tracker) is not mounted on rigid foundation (on-shore) but on a moving ship (off-shore), where typically an inertial measurement system is used to pre-stabilize the video tracker to reduce the required dynamics and bandwidth of the camera system. The computational complexity for these algorithms is usually much higher. The following are some common filtering algorithms:
- Kalman filter: an optimal recursive Bayesian filter for linear functions subjected to Gaussian noise.It is an algorithm that uses a series of measurements observed over time, containing noise (random variations) and other inaccuracies, and produces estimates of unknown variables that tend to be more precise than those based on a single measurement alone.
- Particle filter: useful for sampling the underlying state-space distribution of nonlinear and non-Gaussian processes.
- http://www.youtube.com/watch?v=2y5oVHNfbf8&list=FL8KomHNN46yntJPaerp06uA&feature=mh_lolz - Interesting historical example (1980) of Cromemco Cyclops Camera used to track a ball going through a maze.
- Peter Mountney, Danail Stoyanov and Guang-Zhong Yang (2010). "Three-Dimensional Tissue Deformation Recovery and Tracking: Introducing techniques based on laparoscopic or endoscopic images." IEEE Signal Processing Magazine. 2010 July. Volume: 27". IEEE Signal Processing Magazine 27 (4): 14–24. doi:10.1109/MSP.2010.936728.
- Lyudmila Mihaylova, Paul Brasnett, Nishan Canagarajan and David Bull (2007). Object Tracking by Particle Filtering Techniques in Video Sequences; In: Advances and Challenges in Multisensor Data and Information. NATO Security Through Science Series, 8. Netherlands: IOS Press. pp. 260–268. ISBN 978-1-58603-727-7. CiteSeerX: 10
.1 .1 .60 .8510.
- Kato, Hirokazu, and Mark Billinghurst (1999). "Marker Tracking and HMD Calibration for a Video-based Augmented Reality Conferencing System". IWAR '99 Proceedings of the 2nd IEEE and ACM International Workshop on Augmented Reality (IEEE Computer Society, Washington, DC, USA).
- S. Kang, J. Paik, A. Koschan, B. Abidi, and M. A. Abidi (2003). "Real-time video tracking using PTZ cameras". Proc. Of SPIE 5132: 103–111. doi:10.1117/12.514945. CiteSeerX: 10
.1 .1 .101 .4242.
- Comaniciu, D.; Ramesh, V.; Meer, P., "Real-time tracking of non-rigid objects using mean shift," Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on , vol.2, no., pp.142,149 vol.2, 2000
- Black, James, Tim Ellis, and Paul Rosin (2003). "A Novel Method for Video Tracking Performance Evaluation". Joint IEEE Int. Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance: 125–132. CiteSeerX: 10
.1 .1 .10 .3365.
- Gyro Stabilized Target Tracker for Off-shore Installation
- M. Arulampalam, S. Maskell, N. Gordon, and T. Clapp (2002). "A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking". IEEE Trans. on Signal Processing 50 (2): 174. doi:10.1109/78.978374. CiteSeerX: 10
.1 .1 .117 .1144.
- Emilio Maggio, Andrea Cavallaro (2010). Video Tracking: Theory and Practice 1.
Video Tracking provides a comprehensive treatment of the fundamental aspects of algorithm and application development for the task of estimating, over time.
- Karthik Chandrasekaran (2010). Parametric & Non-parametric Background Subtraction Model with Object Tracking for VENUS 1.
Background subtraction is the process by which we segment moving regions in image sequences.
- J. Martinez-del-Rincon, D. Makris, C. Orrite-Urunuela and J.-C. Nebel (2010). "Tracking Human Position and Lower Body Parts Using Kalman and Particle Filters Constrained by Human Biomechanics". IEEE Transactions on Systems Man and Cybernetics - Part B', 40(4).