Salient Region Detection Using Weighted Feature Maps Based on the Human Visual Attention Model

Hu, Yiqun; Xie, Xing; Ma, Wei‐Ying; Chia, Liang-Tien; Rajan, Dinesh

doi:10.1007/978-3-540-30542-2_122

Cited by 95 publications

(86 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a ranking measure for each individual saliency maps, we can tell how much "information" there is in attending that particular map. We use an energy measure (E-measure) similar to the Composite Saliency Indicator (CSI) of Hu et al 79 Accordingly, the top-down and bottom-up energies, E T D and E BU , are defined as the saliency density divided by the area of the convex hull of all salient points. 80 Thus, for a map with many salient points concentrated in a small area, the E-value is higher than for a map with the same number of salient points spread over a larger area.…”

Section: Attention Systemmentioning

confidence: 99%

Towards Grasp-Oriented Visual Perception for Humanoid Robots

Bohg

Barck-Holst

Huebner

et al. 2009

Int. J. Human. Robot.

View full text Add to dashboard Cite

A distinct property of robot vision systems is that they are embodied. Visual information is extracted for the purpose of moving in and interacting with the environment. Thus, different types of perception-action cycles need to be implemented and evaluated.In this paper, we study the problem of designing a vision system for the purpose of object grasping in everyday environments. This vision system is firstly targeted at the interaction with the world through recognition and grasping of objects and secondly at being an interface for the reasoning and planning module to the real world. The latter provides the vision system with a certain task that drives it and defines a specific context, i.e. search for or identify a certain object and analyze it for potential later manipulation. We deal with cases of: (i) known objects, (ii) objects similar to already known objects, and (iii) unknown objects. The perception-action cycle is connected to the reasoning system based on the idea of affordances. All three cases are also related to the state of the art and the terminology in the neuroscientific area.

show abstract

Section: Attention Systemmentioning

confidence: 99%

Towards Grasp-Oriented Visual Perception for Humanoid Robots

Bohg

Barck-Holst

Huebner

et al. 2009

Int. J. Human. Robot.

View full text Add to dashboard Cite

show abstract

“…To do this we define an energy measure (E-measure) following Hu et al, who introduced the Composite Saliency Indicator (CSI) for similar purposes [9]. In their case, however, they applied the measure on each individual feature map.…”

Section: The E-measurementioning

confidence: 99%

“…Each NN had the same structure, based on 13 hidden neurons, and was trained using the same number of iterations. Since all weights (11) can be affected by all context-components (9) and since each weight can be increased, decreased or neither, a minimum number of 12 hidden units is necessary for good learning.…”

Section: Nn-trainingmentioning

confidence: 99%

An Attentional System Combining Top-Down and Bottom-Up Influences

Rasolzadeh¹,

Targhi²,

Eklundh³

2007

Attention in Cognitive Systems. Theories and Systems From an Interdisciplinary Viewpoint

View full text Add to dashboard Cite

show abstract

“…Some methods represented in [7], [8], [9], [10] are purely computational. Zhang, Ma [7] and Achanta et al [8] estimate saliency using center-surround feature distances.…”

Section: Introductionmentioning

confidence: 99%

“…Zhang, Ma [7] and Achanta et al [8] estimate saliency using center-surround feature distances. Hu et al [9] estimate saliency by a frequency-tuned method. A remarkable computational method using motion features was given by Chen [10] , by which motion features can be extracted from some dynamic images.…”

Section: Introductionmentioning

confidence: 99%

A New Hybrid Model for Video Shot Saliency Extraction

Fang¹

2014

Proceedings of the 3rd International Conference on Computer Science and Service System

View full text Add to dashboard Cite

Abstrac--Video screen shots of images are special, and they are motive compare to other images. To extract saliency maps from video images quickly and accurately is a hard task. This paper is inspired by some excellent works, employing the combination of several ideas to propose a hybrid model for extracting saliency. The hybrid model to extract salient region is based on visual attention theory, dynamic feature saliency maps extraction technique, and motionprior idea integrate spatial with time. We perform experiments to make extraction with itti model, and results prove the fact that the proposed model can get an ideal effect when extract salient region dynamically considering the combination of speed and direction is closing to biological visual mechanisms.

show abstract

Salient Region Detection Using Weighted Feature Maps Based on the Human Visual Attention Model

Cited by 95 publications

References 8 publications

Towards Grasp-Oriented Visual Perception for Humanoid Robots

Towards Grasp-Oriented Visual Perception for Humanoid Robots

An Attentional System Combining Top-Down and Bottom-Up Influences

A New Hybrid Model for Video Shot Saliency Extraction

Contact Info

Product

Resources

About