cv.ObjectnessBING - mexopencv

The Binarized normed gradients algorithm for Objectness

Implementation of BING for Objectness.

Saliency API

Many computer vision applications may benefit from understanding where humans focus given a scene. Other than cognitively understanding the way human perceive images and scenes, finding salient regions and objects in the images helps various tasks such as speeding up object detection, object recognition, object tracking and content-aware image editing.

About the saliency, there is a rich literature but the development is very fragmented. The principal purpose of this API is to give a unique interface, a unique framework for use and plug sever saliency algorithms, also with very different nature and methodology, but they share the same purpose, organizing algorithms into three main categories:

Static Saliency
Motion Saliency
Objectness

Saliency UML diagram:

To see how API works, try tracker demo: computeSaliency_demo.m.

Objectness Algorithms

Objectness is usually represented as a value which reflects how likely an image window covers an object of any category. Algorithms belonging to this category, avoid making decisions early on, by proposing a small number of category-independent proposals, that are expected to cover all objects in an image. Being able to perceive objects before identifying them is closely related to bottom up visual attention (saliency).

Presently, the Binarized normed gradients algorithm [BING] has been implemented.

References

[BING]:

Cheng, Ming-Ming, et al. "BING: Binarized normed gradients for objectness estimation at 300fps". In IEEE CVPR, 2014.

Superclasses	handle
Sealed	false
Construct on load	false

Base	for window size quantization. default 2
NSS	Size for non-maximal suppress. default 2
W	As described in the paper: feature window size (W, W). default 8
id	Object ID

	addlistener	Add listener for event.
	clear	Clears the algorithm state
	computeSaliency	Compute the saliency
	delete	Destructor
	empty	Checks if detector object is empty
	eq	== (EQ) Test handle equality.
	findobj	Find objects matching specified conditions.
	findprop	Find property of MATLAB handle object.
	ge	>= (GE) Greater than or equal relation for handles.
	getDefaultName	Returns the algorithm string identifier
	getObjectnessValues	Return the list of the rectangles' objectness value
	gt	> (GT) Greater than relation for handles.
Sealed	isvalid	Test handle validity.
	le	<= (LE) Less than or equal relation for handles.
	listener	Add listener for event without binding the listener to the source object.
	load	Loads algorithm from a file or a string
	lt	< (LT) Less than relation for handles.
	ne	~= (NE) Not equal relation for handles.
	notify	Notify listeners of event.
	save	Saves the algorithm parameters to a file
	setBBResDir	This is a utility function that allows to set an arbitrary path in which the algorithm will save the optional results
	setTrainingPath	This is a utility function that allows to set the correct path from which the algorithm will load the trained model