Content deleted Content added
Reverted 1 edit by Stephenli2000 (talk): Rv linkspam (TW) |
Citation bot (talk | contribs) Add: publisher. | Use this bot. Report bugs. | Suggested by Headbomb | Linked from Wikipedia:WikiProject_Academic_Journals/Journals_cited_by_Wikipedia/Sandbox2 | #UCB_webform_linked 1971/2044 |
||
| (13 intermediate revisions by 10 users not shown) | |||
Line 1:
{{distinguish|Camera tracking}}
'''Video tracking''' is the process of locating a [[Motion (physics)|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 [[video compression|compression]], [[augmented reality]], traffic control, medical imaging<ref>{{cite journal|author1=Peter Mountney, Danail Stoyanov |author2=Guang-Zhong Yang |
==Objective==
[[File:High-speed catching system.webm|thumb|An example of [[visual servoing]] for the robot hand to catch a ball by object tracking with visual feedback that is processed by a high-speed image processing system.<ref>{{cite web|title=High-speed Catching System (exhibited in National Museum of Emerging Science and Innovation since 2005)|url=http://www.k2.t.u-tokyo.ac.jp/fusion/MiraikanCatching/index-e.html|website=Ishikawa Watanabe Laboratory, University of Tokyo|
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.
Line 15:
==Algorithms==
[[File:Samples_of_object_co-segmentation.jpg|thumb|[[Object co-segmentation|Co-segmentation]] of objects in video frames]]
To perform video tracking an algorithm analyzes sequential [[video frame]]s 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.<ref>{{cite journal |author1=S. Kang |author2=J. Paik |author3=A. Koschan |author4=B. Abidi |author5=M. A. Abidi |
* '''Kernel-based tracking''' ([[mean-shift]] tracking<ref>Comaniciu, D.; Ramesh, V.; Meer, P., "[http://imagine.enpc.fr/~de-la-gm/cours/UPEM/projects/Real-Time%20Tracking%20of%20Non-Rigid%20Objects%20using%20Mean%20Shift.pdf 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</ref>): 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. This approach to contour tracking directly evolves the contour by minimizing the contour energy using gradient descent.
''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.<ref>{{cite journal |author=Black, James, Tim Ellis, and Paul Rosin |title=A Novel Method for Video Tracking Performance Evaluation |citeseerx=10.1.1.10.3365|journal=Joint IEEE Int. Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance |year=2003 |pages= 125–132}}</ref> 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.<ref>[
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.<ref>{{cite journal |author1=M. Arulampalam |author2=S. Maskell |author3=N. Gordon |author4=T. Clapp |
* [[Particle filter]]: useful for sampling the underlying state-space distribution of nonlinear and non-Gaussian processes.<ref name="Video Tracking">
{{cite book
Line 30 ⟶ 31:
| volume = 1
| year= 2010
|publisher=Addison-Wesley Professional | url= https://books.google.com/books?id=56LNfE2QGtYC
| quote = Video Tracking provides a comprehensive treatment of the fundamental aspects of algorithm and application development for the task of estimating, over time.
|isbn=9780132702348 }}
Line 39 ⟶ 40:
| volume = 1
| year= 2010
| url= https://books.google.com/books?id=Ws0JThymM-EC
| quote = Background subtraction is the process by which we segment moving regions in image sequences.
| isbn = 9780549524892
Line 59 ⟶ 60:
==External links==
*[https://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.
{{Computer vision}}
[[Category:Motion in computer vision]]
Line 64 ⟶ 67:
[[Category:Tracking]]
[[Category:Articles containing video clips]]
| |||