Effective Sampling: Fast Segmentation Using Robust Geometric Model Fitting

Tennakoon, Ruwan; Sadri, Alireza; Hoseinnezhad, Reza; Bab–Hadiashar, Alireza

doi:10.1109/tip.2018.2834821

Cited by 21 publications

(14 citation statements)

References 50 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…three points for plane), and grow the initial models by finding all their inlier points. Its later alternatives [40]- [45] modify the sequential fit strategy or the random sampling used by RANSAC. RHA simultaneously finds multi-model instances from the residual distribution per individual data points.…”

Section: Robust Model-based Segmentationmentioning

confidence: 99%

PL-Net3d: Robust 3D Object Class Recognition Using Geometric Models

et al. 2019

Self Cite

View full text Add to dashboard Cite

Three-dimensional point clouds produced by 3D scanners are often noisy and contain outliers. Such data inaccuracies can significantly affect current deep learning-based methods and reduce their ability to classify objects. Most deep neural networks-based object classification methods were targeted to achieve high classification accuracy without considering classification robustness. Thus, despite their great success, they still fail to achieve good classification accuracy with low levels of noise and outliers. This work is carried out to develop a robust network structure that can solidly identify objects. The proposed method uses patches of planar segments, which can robustly capture object appearance. The planar segments information are then fed into a deep neural network for classification. We base our approach on the PointNet deep learning architecture. Our method was tested against several kinds of data inaccuracies such as scattered outliers, clustered outliers, noise and missing points. The proposed method shows excellent performance in the presence of these inaccuracies compared to state-of-the-art techniques. By decomposing objects into planes, the suggested method is simple, fast, provides good classification accuracy and can handle different kinds of point cloud data inaccuracies. The code can be found at https://github.com/AymanMukh/Pl-Net3D INDEX TERMS Object recognition, point cloud classification, primitive fitting, robust classification.

show abstract

Section: Robust Model-based Segmentationmentioning

confidence: 99%

PL-Net3d: Robust 3D Object Class Recognition Using Geometric Models

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Guided sampling can accelerate multi-stuctural data search by utilizing meta-information on the data distribution (Pham et al 2014;Tennakoon et al 2018). The Random Cluster Model Simulated Annealing (RCMSA) (Pham et al 2014) guides promising hypothesis generation by constructing a weighted graph in a simulated annealing framework.…”

Section: Related Workmentioning

confidence: 99%

“…However, the disadvantage of RCMSA is that it assumes spatial smoothness of the inliers, which is computationally expensive and may not apply to particular situations. The guided sampling method that is most closely related to ours, cost-based sampling (CBS) (Tennakoon et al 2018) uses a data sub-sampling strategy to generate the hypotheses. Specifically, CBS employs a K-th order statistical cost function to improve the distribution of hypotheses.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Hypergraph Optimization for Multi-Structural Geometric Model Fitting

Lin

Xiao

Yan

et al. 2019

AAAI

View full text Add to dashboard Cite

Recently, some hypergraph-based methods have been proposed to deal with the problem of model fitting in computer vision, mainly due to the superior capability of hypergraph to represent the complex relationship between data points. However, a hypergraph becomes extremely complicated when the input data include a large number of data points (usually contaminated with noises and outliers), which will significantly increase the computational burden. In order to overcome the above problem, we propose a novel hypergraph optimization based model fitting (HOMF) method to construct a simple but effective hypergraph. Specifically, HOMF includes two main parts: an adaptive inlier estimation algorithm for vertex optimization and an iterative hyperedge optimization algorithm for hyperedge optimization. The proposed method is highly efficient, and it can obtain accurate model fitting results within a few iterations. Moreover, HOMF can then directly apply spectral clustering, to achieve good fitting performance. Extensive experimental results show that HOMF outperforms several state-of-the-art model fitting methods on both synthetic data and real images, especially in sampling efficiency and in handling data with severe outliers.

show abstract

“…Traditionally, VOS (or motion segmentation as it was called) was solved via fitting geometric models to matched key-points in adjacent frames [4]. More recently, deep learning based methods have become prominent.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised video object segmentation: An affinity and edge learning approach.

Muthu¹,

Tennakoon²,

Hoseinnezhad³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

<div>This paper presents a new approach to solve unsupervised video object segmentation~(UVOS) problem (called TMNet). The UVOS is still a challenging problem as prior methods suffer from issues like generalization errors to segment multiple objects in unseen test videos (category agnostic), over reliance on inaccurate optic flow, and problem towards capturing fine details at object boundaries. These issues make the UVOS, particularly in presence of multiple objects, an ill-defined problem. Our focus is to constrain the problem and improve the segmentation results by inclusion of multiple available cues such as appearance, motion, image edge, flow edge and tracking information through neural attention. To solve the challenging category agnostic multiple object UVOS, our model is designed to predict neighbourhood affinities for being part of the same object and cluster those to obtain accurate segmentation. To achieve multi cue based neural attention, we designed a Temporal Motion Attention module, as part of our segmentation framework, to learn the spatio-temporal features. To refine and improve the accuracy of object segmentation boundaries, an edge refinement module (using image and optic flow edges) and a geometry based loss function are incorporated. The overall framework is capable of segmenting and finding accurate objects' boundaries without any heuristic post processing. This enables the method to be used for unseen videos. Experimental results on challenging DAVIS16 and multi object DAVIS17 datasets shows that our proposed TMNet performs favourably compared to the state-of-the-art methods without post processing.</div>

show abstract

Effective Sampling: Fast Segmentation Using Robust Geometric Model Fitting

Cited by 21 publications

References 50 publications

PL-Net3d: Robust 3D Object Class Recognition Using Geometric Models

PL-Net3d: Robust 3D Object Class Recognition Using Geometric Models

Hypergraph Optimization for Multi-Structural Geometric Model Fitting

Unsupervised video object segmentation: An affinity and edge learning approach.

Contact Info

Product

Resources

About