Depth Matters: Influence of Depth Cues on Visual Saliency

Lang, Congyan; Nguyên, Tam; Katti, Harish; Yadati, Karthik; Kankanhalli, Mohan; Yan, Shuicheng

doi:10.1007/978-3-642-33709-3_8

Cited by 204 publications

(156 citation statements)

References 26 publications

Supporting

Mentioning

147

Contrasting

Order By: Relevance

“…Our work contrasts with [14] through the additional observations on depth saliency reported from our experiments, through the formulations of our 3D saliency model and the model for fusing 3D and visual saliency. It is well known that in images of large depth of field scenes taken using conventional cameras, the farther regions are out-of-focus, but images from the Kinect camera does not contain this phenomenon.…”

Section: Introduction and Related Workmentioning

confidence: 90%

“…With the advent of the Kinect sensor, depth information has been used in addition to color images for object recognition [13], human action recognition [22] and saliency detection [14,16,18]. In [18] and [16] , authors incorporate depth information from stereopsis making use of disparity maps of saliency detection.…”

Section: Introduction and Related Workmentioning

confidence: 99%

“…Their work is limited to well framed images using stereoscopic cameras and does not cater to the needs of indoor environment. In [14], the authors use the Kinect sensor to obtain the depth and integrate it with a 2D saliency model. They develop a large 3D dataset along with fixations using a 3D eye-tracking system which is first of its kind.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Depth really Matters: Improving Visual Salient Region Detection with Depth

Desingh

K²,

Rajan

et al. 2013

Procedings of the British Machine Vision Conference 2013

156

View full text Add to dashboard Cite

Depth information has been shown to affect identification of visually salient regions in images. In this paper, we investigate the role of depth in saliency detection in the presence of (i) competing saliencies due to appearance, (ii) depth-induced blur and (iii) centre-bias. Having established through experiments that depth continues to be a significant contributor to saliency in the presence of these cues, we propose a 3D-saliency formulation that takes into account structural features of objects in an indoor setting to identify regions at salient depth levels. Computed 3D saliency is used in conjunction with 2D saliency models through non-linear regression using SVM to improve saliency maps. Experiments on benchmark datasets containing depth information show that the proposed fusion of 3D saliency with 2D saliency models results in an average improvement in ROC scores of about 9% over state-of-the-art 2D saliency models.

show abstract

Section: Introduction and Related Workmentioning

confidence: 90%

Section: Introduction and Related Workmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Depth really Matters: Improving Visual Salient Region Detection with Depth

Desingh

K²,

Rajan

et al. 2013

Procedings of the British Machine Vision Conference 2013

156

View full text Add to dashboard Cite

show abstract

“…Lang et al present a depth prior for saliency learned from human gaze information [16]. This saliency prior produces a saliency map that is then either directly added or multiplied by the saliency results of other methods.…”

Section: Saliency Computation With Depthmentioning

confidence: 99%

“…We propose a novel method which incorporates depth measurements into the computation of visual saliency. Human subject studies have shown that depth is an important cue in determining salient regions in human visual processing [16,23]. Depth measurements make it possible to separate objects which may be similar in appearance.…”

Section: Introductionmentioning

confidence: 99%

An In Depth View of Saliency

Ciptadi¹,

Hermans²,

Rehg³

2013

Procedings of the British Machine Vision Conference 2013

115

View full text Add to dashboard Cite

Visual saliency is a computational process that identifies important locations and structure in the visual field. Most current methods for saliency rely on cues such as color and texture while ignoring depth information, which is known to be an important saliency cue in the human cognitive system. We propose a novel computational model of visual saliency which incorporates depth information. We compare our approach to several state of the art visual saliency methods and we introduce a method for saliency based segmentation of generic objects. We demonstrate that by explicitly constructing 3D layout and shape features from depth measurements, we can obtain better performance than methods which treat the depth map as just another image channel. Our method requires no learning and can operate on scenes for which the system has no previous knowledge. We conduct object segmentation experiments on a new dataset of registered RGB-D images captured on a mobile-manipulator robot.

show abstract

RGB-D Salient Object Detection: A Review

Ren

Zhang

2019

RGB-D Image Analysis and Processing

View full text Add to dashboard Cite

Rearrangement planning for object retrieval tasks from confined spaces is a challenging problem, primarily due to the lack of open space for robot motion and limited perception. Several traditional methods exist to solve object retrieval tasks, but they require overhead cameras for perception and a time-consuming exhaustive search to find a solution and often make unrealistic assumptions, such as having identical, simple geometry objects in the environment. This paper presents a neural object retrieval framework that efficiently performs rearrangement planning of unknown, arbitrary objects in confined spaces to retrieve the desired object using a given robot grasp. Our method actively senses the environment with the robot's in-hand camera. It then selects and relocates the non-target objects such that they do not block the robot path homotopy to the target object, thus also aiding an underlying path planner in quickly finding robot motion sequences. Furthermore, we demonstrate our framework in challenging scenarios, including real-world cabinet-like environments with arbitrary household objects. The results show that our framework achieves the best performance among all presented methods and is, on average, two orders of magnitude computationally faster than the best-performing baselines.

show abstract

Depth Matters: Influence of Depth Cues on Visual Saliency

Cited by 204 publications

References 26 publications

Depth really Matters: Improving Visual Salient Region Detection with Depth

Depth really Matters: Improving Visual Salient Region Detection with Depth

An In Depth View of Saliency

RGB-D Salient Object Detection: A Review

Contact Info

Product

Resources

About