Structured Learning of Tree Potentials in CRF for Image Segmentation

Liu, Fayao; Lin, Guosheng; Qiao, Ruizhi; Shen, Chunhua

doi:10.1109/tnnls.2017.2690453

Cited by 21 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to further analyze the effect of different projection methods on the semantic segmentation of RGB-DI images, the two-order CRF method, which takes into account the pixel position relationship [18], is applied to the semantic segmentation of RGB-DI images generated by PCA, LDA, MDS, and our method. In experiments, the RGB-DI images It is clear the results of our method are substantially better than those of PCA, LDA, and MDS.…”

Section: B Results Of Rgb-di Image Generatingmentioning

confidence: 99%

See 1 more Smart Citation

RGB-DI Images and Full Convolution Neural Network-Based Outdoor Scene Understanding for Mobile Robots

Qiu

Zhuang

Yan

et al. 2019

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

This paper presents a multisensor-based approach to outdoor scene understanding of mobile robots. Since laser scanning points in 3-D space are distributed irregularly and unbalanced, a projection algorithm is proposed to generate RGB, depth, and intensity (RGB-DI) images so that the outdoor environments can be optimally measured with a variable resolution. The 3-D semantic segmentation in RGB-DI cloud points is, therefore, transformed to the semantic segmentation in RGB-DI images. A full convolution neural network (FCN) model with deep layers is designed to perform semantic segmentation of RGB-DI images. According to the exact correspondence between each 3-D point and each pixel in a RGB-DI image, the semantic segmentation results of the RGB-DI images are mapped back to the original point clouds to realize the 3-D scene understanding. The proposed algorithms are tested on different data sets, and the results show that our RGB-DI image and FCN modelbased approach can provide a superior performance for outdoor scene understanding. Moreover, real-world experiments were conducted on our mobile robot platform to show the validity and practicability of the proposed approach.

show abstract

Section: B Results Of Rgb-di Image Generatingmentioning

confidence: 99%

“…12. The random forest classifier [21] and the CRF classifier [18] are selected. For the second idea, the RGB-DI image is generated by the proposed method and color histogram features are extracted from the neighborhood of a pixel in RGB-DI images.…”

Section: Semantic Segmentation Results With Different Algorithmsmentioning

confidence: 99%

RGB-DI Images and Full Convolution Neural Network-Based Outdoor Scene Understanding for Mobile Robots

Qiu

Zhuang

Yan

et al. 2019

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…Although each methods are different and have diverse property, they all work with the same purpose: reserving the useful information like texture and edges, and eliminate the noise. The image denoising algorithms can be classify into following categories: Nonlocal Methods [12], [13], Transform Based Methods [14], Bilateral Filtering [16]- [18], Anisotropic Diffusion [19]- [21], Statistical Model [22], Conditional Random Fields [23] and Deep Learning Methods [24], [25]. Transform Based Methods mainly includes wavelet transform, curvelet transform, contourlet transform, and shearlet transform.…”

Section: Related Work a Image Denoising Methodsmentioning

confidence: 99%

Denoising of Uncertain Type Noise Images by Spatial Feature Classification in Nonsubsampled Shearlet Transform

Lyu

Han

2020

IEEE Access

View full text Add to dashboard Cite

Most denoising methods are designed to deal standard images with specific type noise, which do not perform well when denoising real noisy images contain uncertain types of noise. However, underwater image is a typical uncertain type noise image. To solve this problem, this paper presents a method using spatial feature classification jointing nonsubsampled shearlet transform (NSST) for denoising uncertain type noise images. Justifiable granule is employed to solve the problem of parameter selection. The raw image was decomposed by using the NSST to get one low frequency subband and several high frequency subbands. Then, the preliminary binary map is built, the binary map is employed to decide whether a coefficient contains spatial feature or not. And we employ justifiable granule to solve the difficulty of parameter selection. The high subbands coefficients are classified into two classes by fuzzy support vector machine classification: the texture class and the noise class. At last, the adaptive Bayesian threshold is used to shrink the coefficients. Simulation results show the proposed method is effective in uncertain type noise images(also have good performance in specific type noise). The method we proposed has been compared with other popular denoising methods and get excellent subjective performance and PSNR improvement. INDEX TERMS Uncertain type noise image, denoising, nonsubsampled shearlet transform (NSST), spatial feature, justifiable granularity.

show abstract

“…Jenis klasifikasi seperti ini merupakan klasifikasi pada proses stokastik. Segmentasi citra yang menggunakan jenis klasifikasi citra ini membutuhkan sebuah model stokastik, diantaranya Markov Random Field (MRF) [4] dan Conditional Random Field (CRF) [5] [6]. Performa yang baik ditunjukan oleh kedua model tersebut dalam melakukan segmentasi citra.…”

Section: Pendahuluanunclassified

Untitled

Rachmadi¹,

Alamsyah²

2017

RESTI

View full text Add to dashboard Cite

Autonomous UAV is typically require a system which is capable of mapping (segmenting) region of a color image, where the segmentation is a depth image. The depth image can be done by estimate the color image. Estimating color images into depth images is an open challenge in the field of computer vision. The problem of depth image estimation is stochastic based problem. Conditional Random Field (CRF) is a model which is capable of mapping stochastic problems. This study uses CRF as a model of structured classification that is Structured Support Vector Machine (SSVM). In the pre-process, the color image process is converted into superpixel form and using Principal Component Analysis (PCA) as its feature extraction. The results of this study show a good accuracy in the segmentation of the region that is 71.25%.

show abstract

Structured Learning of Tree Potentials in CRF for Image Segmentation

Cited by 21 publications

References 34 publications

RGB-DI Images and Full Convolution Neural Network-Based Outdoor Scene Understanding for Mobile Robots

RGB-DI Images and Full Convolution Neural Network-Based Outdoor Scene Understanding for Mobile Robots

Denoising of Uncertain Type Noise Images by Spatial Feature Classification in Nonsubsampled Shearlet Transform

Untitled

Contact Info

Product

Resources

About