Channel Coding for Joint Colour and Depth Segmentation

Wallenberg, Marcus; Felsberg, Michael; Forssén, Per-Erik; Dellen, Babette

doi:10.1007/978-3-642-23123-0_31

Cited by 11 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…if exists if does not exist (18) Image represents the right image warped to the viewpoint of the left one except for the points of the left image not visible in the right one. For these points the corresponding value in the left image is simply copied onto .…”

Section: Segmentation Of Stereo Image Pairsmentioning

confidence: 99%

“…In [19], we proposed a segmentation scheme for stereoscopic data that exploits different stereo vision algorithms in order to extract depth information which is then used to assist image segmentation based on clustering techniques. The approach of [19] was limited to stereo vision setups and required a supervised adjustment of a parameter weighting the relevance of geometry against color, an issue common also to other joint depth and color segmentation schemes such as [17] and [18].…”

Section: Introductionmentioning

confidence: 99%

“…Bleiweiss and Werman [17] follow this approach and apply mean shift clustering to vectors containing both the color and depth information. In [18], superparamagnetic clustering and channel representations are instead exploited to segment plant scenes from the color and depth data acquired by a Microsoft Kinect camera. In [19], we proposed a segmentation scheme for stereoscopic data that exploits different stereo vision algorithms in order to extract depth information which is then used to assist image segmentation based on clustering techniques.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fusion of Geometry and Color Information for Scene Segmentation

Mutto

Zanuttigh

Cortelazzo

2012

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Scene segmentation is a well-known problem in computer vision traditionally tackled by exploiting only the color information from a single scene view. Recent hardware and software developments allow to estimate in real-time scene geometry and open the way for new scene segmentation approaches based on the fusion of both color and depth data. This paper follows this rationale and proposes a novel segmentation scheme where multidimensional vectors are used to jointly represent color and depth data and normalized cuts spectral clustering is applied to them in order to segment the scene. The critical issue of how to balance the two sources of information is solved by an automatic procedure based on an unsupervised metric for the segmentation quality. An extension of the proposed approach based on the exploitation of both images in stereo vision systems is also proposed. Different acquisition setups, like time-of-flight cameras, the Microsoft Kinect device and stereo vision systems have been used for the experimental validation. A comparison of the effectiveness of the different depth imaging systems for segmentation purposes is also presented. Experimental results show how the proposed algorithm outperforms scene segmentation algorithms based on geometry or color data alone and also other approaches that exploit both clues

show abstract

Section: Segmentation Of Stereo Image Pairsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fusion of Geometry and Color Information for Scene Segmentation

Mutto

Zanuttigh

Cortelazzo

2012

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…An important advantage of this is that distances calculated on these vectors behave as sigmoid functions on the original feature spaces, and thus provide a robust error measure. This can be used to obtain better generalisation in segmentation compared to other techniques, and is the subject of (Wallenberg et al, 2011a) (see part II, paper C).…”

Section: Segmentation and Image Representationmentioning

confidence: 99%

“…The final consensus score is the composed of a normalised average of such terms. For further details, see (Wallenberg et al, 2011a) (part II, paper C).…”

Section: Performance Measuresmentioning

confidence: 99%

Embodied Visual Object Recognition

Wallenberg¹

Self Cite

View full text Add to dashboard Cite

Object recognition is a skill we as humans often take for granted. Due to our formidable object learning, recognition and generalisation skills, it is sometimes hard to see the multitude of obstacles that need to be overcome in order to replicate this skill in an artificial system. Object recognition is also one of the classical areas of computer vision, and many ways of approaching the problem have been proposed.Recently, visually capable robots and autonomous vehicles have increased the focus on embodied recognition systems and active visual search. These applications demand that systems can learn and adapt to their surroundings and arrive at decisions in a reasonable amount of time. Ideally, this should be done while maintaining high object recognition performance. This is especially challenging due to the high dimensionality of image data and in cases where end-to-end learning from pixels to output is needed. Therefore, mechanisms designed to make inputs tractable are often necessary for less computationally capable embodied systems.Active visual search also means that mechanisms for attention and gaze control are integral to the object recognition procedure. Therefore, the way in which attention mechanisms should be introduced into feature extraction and estimation algorithms must be carefully considered when constructing a recognition system. This thesis describes work done on the components necessary for creating an embodied recognition system, specifically in the areas of decision uncertainty estimation, object segmentation from multiple cues, adaptation of stereo vision to a specific platform and setting, problem-specific feature selection, efficient estimator training and attentional modulation in convolutional neural networks. Contributions include the evaluation of methods and measures for predicting the potential uncertainty reduction that can be obtained from additional views of an object, allowing for adaptive target observations. Also, in order to separate a specific object from other parts of a scene, it is often necessary to combine multiple cues such as colour and depth in order to obtain satisfactory results. Therefore, a method for combining these using channel coding has been evaluated. In order to make use of three-dimensional spatial structure in recognition, a novel stereo vision algorithm extension along with a framework for automatic stereo tuning have also been investigated. Feature selection and efficient discriminant sampling for decision tree-based estimators have also been implemented. Finally, attentional multi-layer modulation of convolutional neural networks for recognition in cluttered scenes has been investigated. Several of these components have been tested and evaluated on a purpose-built embodied recognition platform known as Eddie the Embodied.v Populärvetenskaplig sammanfattningFörmågan att tolka och lära av synintryck är både viktig och självklar för oss män-niskor. Detta gör att vi sällan ägnar en tanke åt den enorma komplexitet och de många utmaningar vi med l...

show abstract