 | TrackerGOTURN Class |
GOTURN (@cite GOTURN) is kind of trackers based on Convolutional Neural Networks (CNN).
Inheritance HierarchySystemObject
OpenCvSharpDisposableObject
OpenCvSharpDisposableCvObject
OpenCvSharpAlgorithm
OpenCvSharp.TrackingTracker
OpenCvSharp.TrackingTrackerGOTURN
OpenCvSharpDisposableObject
OpenCvSharpDisposableCvObject
OpenCvSharpAlgorithm
OpenCvSharp.TrackingTracker
OpenCvSharp.TrackingTrackerGOTURN
Namespace: OpenCvSharp.Tracking
Assembly: OpenCvSharp (in OpenCvSharp.dll) Version: 1.0.0
SyntaxThe TrackerGOTURN type exposes the following members.
Constructors| Name | Description | |
|---|---|---|
 | TrackerGOTURN | Initializes a new instance of the TrackerGOTURN class |
Properties| Name | Description | |
|---|---|---|
 | AllocatedMemory |
Gets or sets a memory address allocated by AllocMemory.
(Inherited from DisposableObject.) |
| AllocatedMemorySize |
Gets or sets the byte length of the allocated memory
(Inherited from DisposableObject.) |
 | CvPtr |
Native pointer of OpenCV structure
(Inherited from DisposableCvObject.) |
| DataHandle |
Gets or sets a handle which allocates using cvSetData.
(Inherited from DisposableObject.) |
| Empty |
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read
(Inherited from Algorithm.) |
| IsDisposed |
Gets a value indicating whether this instance has been disposed.
(Inherited from DisposableObject.) |
| IsEnabledDispose |
Gets or sets a value indicating whether you permit disposing this instance.
(Inherited from DisposableObject.) |
Methods| Name | Description | |
|---|---|---|
| AllocGCHandle |
Pins the object to be allocated by cvSetData.
(Inherited from DisposableObject.) |
| AllocMemory |
Allocates the specified size of memory.
(Inherited from DisposableObject.) |
  | Create |
Constructor
|
| Create(TrackerGOTURNParams) |
Constructor
|
| Dispose |
Releases the resources
(Inherited from DisposableObject.) |
| Dispose(Boolean) |
Releases the resources
(Inherited from DisposableObject.) |
| DisposeManaged |
Releases managed resources
(Inherited from Tracker.) |
| DisposeUnmanaged |
releases unmanaged resources
(Inherited from DisposableCvObject.) |
| Equals | Determines whether the specified object is equal to the current object. (Inherited from Object.) |
| Finalize |
Destructor
(Inherited from DisposableObject.) |
| GetDefaultName |
Returns the algorithm string identifier.
This string is used as top level xml/yml node tag when the object
is saved to a file or string.
(Inherited from Algorithm.) |
| GetHashCode | Serves as the default hash function. (Inherited from Object.) |
| GetType | Gets the Type of the current instance. (Inherited from Object.) |
| Init |
Initialize the tracker with a know bounding box that surrounding the target
(Inherited from Tracker.) |
| MemberwiseClone | Creates a shallow copy of the current Object. (Inherited from Object.) |
| NotifyMemoryPressure |
Notifies the allocated size of memory.
(Inherited from DisposableObject.) |
| Read |
Reads algorithm parameters from a file storage
(Inherited from Algorithm.) |
| Save |
Saves the algorithm to a file.
In order to make this method work, the derived class must
implement Algorithm::write(FileStorage fs).
(Inherited from Algorithm.) |
| ThrowIfDisposed |
If this object is disposed, then ObjectDisposedException is thrown.
(Inherited from DisposableObject.) |
| ToString | Returns a string that represents the current object. (Inherited from Object.) |
| Update |
Update the tracker, find the new most likely bounding box for the target
(Inherited from Tracker.) |
| Write |
Stores algorithm parameters in a file storage
(Inherited from Algorithm.) |
Fields| Name | Description | |
|---|---|---|
 | ptr |
Data pointer
(Inherited from DisposableCvObject.) |
Remarks
* While taking all advantages of CNN trackers, GOTURN is much faster due to offline training without online fine-tuning nature.
* GOTURN tracker addresses the problem of single target tracking: given a bounding box label of an object in the first frame of the video,
* we track that object through the rest of the video.NOTE: Current method of GOTURN does not handle occlusions; however, it is fairly
* robust to viewpoint changes, lighting changes, and deformations.
* Inputs of GOTURN are two RGB patches representing Target and Search patches resized to 227x227.
* Outputs of GOTURN are predicted bounding box coordinates, relative to Search patch coordinate system, in format X1, Y1, X2, Y2.
* Original paper is here: [http://davheld.github.io/GOTURN/GOTURN.pdf]
* As long as original authors implementation: [https://github.com/davheld/GOTURN#train-the-tracker]
* Implementation of training algorithm is placed in separately here due to 3d-party dependencies:
* [https://github.com/Auron-X/GOTURN_Training_Toolkit]
* GOTURN architecture goturn.prototxt and trained model goturn.caffemodel are accessible on opencv_extra GitHub repository.
See Also