Kinect Shadow Detection and Classification

Deng, Teng; Li, Hui; Cai, Jianfei; Cham, Tat‐Jen; Fuchs, Henry

doi:10.1109/iccvw.2013.97

Cited by 11 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But even in this case, RA-JBF still has generally smaller dilation of depth discontinuities. To improve the hole-filling performance, one possible solution is to take into account the Kinect shadow prior [Berdnikov and Vatolin 2011;Deng et al 2013] because the large holes that RA-JBF cannot well handle are usually shadows.…”

Section: Quantitative Evaluation Of Hole-filling Performancementioning

confidence: 99%

Kinect Depth Recovery Using a Color-Guided, Region-Adaptive, and Depth-Selective Framework

Chen

Cai

Zheng

et al. 2015

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

Considering that the existing depth recovery approaches have different limitations when applied to Kinect depth data, in this article, we propose to integrate their effective features including adaptive support region selection, reliable depth selection, and color guidance together under an optimization framework for Kinect depth recovery. In particular, we formulate our depth recovery as an energy minimization problem, which solves the depth hole filling and denoising simultaneously. The energy function consists of a fidelity term and a regularization term, which are designed according to the Kinect characteristics. Our framework inherits and improves the idea of guided filtering by incorporating structure information and prior knowledge of the Kinect noise model. Through analyzing the solution to the optimization framework, we also derive a local filtering version that provides an efficient and effective way of improving the existing filtering techniques. Quantitative evaluations on our developed synthesized dataset and experiments on real Kinect data show that the proposed method achieves superior performance in terms of recovery accuracy and visual quality. . 2015. Kinect depth recovery using a color-guided, region-adaptive, and depth-selective framework.

show abstract

Section: Quantitative Evaluation Of Hole-filling Performancementioning

confidence: 99%

Kinect Depth Recovery Using a Color-Guided, Region-Adaptive, and Depth-Selective Framework

Chen

Cai

Zheng

et al. 2015

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Reference [11] shows that the hardware sensor is applicable to the medical field through its use in a virtual rehabilitation system to help stroke victims regain balance. The Kinect's inherit issues, as described in [12], can be transformed into useful information for use in creating automatic foreground segmentation. Lastly, [13] shows a unique example of utilizing the Kinect in the music field.…”

Section: Related Workmentioning

confidence: 99%

Frame Filtering and Skipping for Point Cloud Data Video Transmission

Moreno¹,

Li²

2017

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

“…For the automatic RGB-D image segmentation work, we make use of our previous work [22] to realize automatic foreground segmentation and automatic multi-object segmentation, where the extracted shadow detection results are used to generate accurate foreground and background seeds, and to generate accurate fixation points, respectively. The proposed shadow-assisted segmentation methods can achieve fully automatic cutout with superior segmentation performance.…”

Section: Resultsmentioning

confidence: 99%

“…As mentioned earlier, we utilize our previous Kinect shadow detection work [22]. In this section, we will give a brief description of the Kinect shadow detection work.…”

Section: Prior Information Pre-processingmentioning

confidence: 99%

See 1 more Smart Citation

Semantic image segmentation and evaluation

Li¹

Self Cite

View full text Add to dashboard Cite

Though quite a few image segmentation benchmark datasets have been constructed, there is no suitable benchmark for semantic image segmentation. In this thesis, we first construct a benchmark for such a purpose, where the groundtruths are generated by leveraging the existing fine granular groundtruths in the Berkeley Segmentation Dataset (BSD) as well as using an interactive segmentation tool for new images. We also propose a percept-tree-based region merging strategy for dynamically adapting the groundtruth for evaluating test segmentation. Moreover, we propose a new evaluation metric that is easy to understand and compute, and does not require boundary matching. Experimental results show that, compared with the BSD, the generated groundtruth dataset is more suitable for evaluating semantic image segmentation, and the conducted user study demonstrates that the proposed evaluation metric matches user ranking very well. In the second part of this thesis, we focus on segmentation application by utilizing prior information (i.e., depth in this thesis) to improve segmentation quality. To the best of our knowledge, little work has been attempted so far to achieve automatic image segmentation on RGB-D image. Users are usually asked to input scribbles to indicate the foreground and background or the framework needs to be trained on a database to obtain the bounding box for a specified target. All these methods require external information. We propose to utilize Kinect shadow information into state-of-the-art algorithms for automatic foreground segmentation and multiple object segmentation. Experimental results demonstrate that the proposed shadowassisted segmentation methods can achieve fully automatic cutout with superior segmentation performance.

show abstract

Kinect Shadow Detection and Classification

Cited by 11 publications

References 11 publications

Kinect Depth Recovery Using a Color-Guided, Region-Adaptive, and Depth-Selective Framework

Kinect Depth Recovery Using a Color-Guided, Region-Adaptive, and Depth-Selective Framework

Frame Filtering and Skipping for Point Cloud Data Video Transmission

Semantic image segmentation and evaluation

Contact Info

Product

Resources

About