Rotational Projection Statistics for 3D Local Surface Description and Object Recognition

Guo, Yulan; Sohel, Ferdous; Bennamoun, Mohammed; Lü, Min; Wan, Jianwei

doi:10.1007/s11263-013-0627-y

Cited by 595 publications

(534 citation statements)

References 61 publications

(151 reference statements)

Supporting

Mentioning

506

Contrasting

Unclassified

Order By: Relevance

“…Other than the descriptors used so far, RoPS [5] require a triangle mesh to work with. This mesh is generated following the approach for fast triangulation of unordered point clouds described in [17].…”

Section: Rotational Projection Statistics (Rops)mentioning

confidence: 99%

“…For object recognition, the Rotational Projection Statistics (RoPS) descriptor was reported as the best choice in [5], but in other studies, the Point-Feature Histograms (PFH) delivered good results as well [6] [7]. Regarding the matching of point clouds, recent publications rank the RoPS descriptor on top [8] [9], with [10] and [11] additionally reporting good results for the SHOT and Fast-Point-Feature Histogram (FPFH) descriptor, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Experimental Evaluation of the Performance of Local Shape Descriptors for the Classification of 3D Data in Precision Farming

Mack¹,

Trakowski²,

Rist³

et al. 2017

JCC

View full text Add to dashboard Cite

Object classification in high-density 3D point clouds with applications in precision farming is a very challenging area due to high intra-class variances and high degrees of occlusions and overlaps due to self-similarities and densely packed plant organs, especially in ripe growing stages. Due to these application specific challenges, this contribution gives an experimental evaluation of the performance of local shape descriptors (namely Point-Feature Histogram (PFH), Fast-Point-Feature Histogram (FPFH), Signature of Histograms of Orientations (SHOT), Rotational Projection Statistics (RoPS) and Spin Images) in the classification of 3D points into different types of plant organs. We achieve very good results on four representative scans of a leave, a grape bunch, a grape branch and a flower of between 94 and 99% accuracy in the case of supervised classification with an SVM and between 88 and 96% accuracy using a k-means clustering approach. Additionally, different distance measures and the influence of the number of cluster centres are examined.

show abstract

Section: Rotational Projection Statistics (Rops)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Experimental Evaluation of the Performance of Local Shape Descriptors for the Classification of 3D Data in Precision Farming

Mack¹,

Trakowski²,

Rist³

et al. 2017

JCC

View full text Add to dashboard Cite

show abstract

“…Each scene was synthetically built by randomly rotating and translating three to five models to create clutter and pose variances. In consequence, the ground truth rotations and translations between each model and its instances in the scene were known as a priori during the process of construction 7 .…”

Section: Dataset and Parameter Settingmentioning

confidence: 99%

“…The global feature based algorithms achieved a good performance in shape retrieval applications. However, these algorithms need complete 3D models so that they cannot work well to deal with occlusion and clutter 7 . In contrast, the local feature based methods generate a set of features by encoding the properties of the local patch of key points which make them more robust to occlusion and clutter.…”

Section: Introductionmentioning

confidence: 99%

Signature of position angles histograms for 3D object recognition

Hao

Cai

et al. 2017

SPIE Proceedings

View full text Add to dashboard Cite

This paper presents a robust and rotation invariant local surface descriptor by encoding the position angles of neighboring points with a stable and unique local reference frame (LRF) into a 1D histogram. The whole procedure includes two stages: the first stage is to construct a unique LRF by performing eigenvalue decomposition on the covariance matrix formed using all the neighboring points on the local surface. On the second stage, the sphere support field of a key point was divided along the radius into several sphere shells which is similar with the Signature of Histograms OrienTations (SHOT). In each sphere shell, we calculate the cosine of the angles between the neighboring points and the x-axis, z-axis respectively to form two 1D histograms. Finally, all the 1D histograms were stitched together followed by a normalization to generate the local surface descriptor. Experiment results show that our proposed local feature descriptor is robust to noise and varying mesh-resolutions. Moreover, our local feature descriptor based 3D object recognition algorithm achieved a high average recognition rate of 98.9% on the whole UWA dataset.

show abstract

“…1,2 This technique has been used in numerous applications including automation, manipulation and grasping, robot localization and navigation, surgery and education. [3][4][5] Given a database of 3-D models and a range image, the aim of object recognition is to identify the set of visible models and find the 3-D rigid transformations (i.e., rotations and translations) that can transform the visible models into the scene to superimpose the relative areas well. 6 However, to correctly recognize all the visible models in scenes with different levels of noise, varying mesh resolution, occlusion, and clutter is still a challenging work.…”

Section: Introductionmentioning

confidence: 99%

Simple and efficient improvement of spin image for three-dimensional object recognition

Hao

2016

Opt. Eng

View full text Add to dashboard Cite

Abstract. This paper presents a highly distinctive and robust local three-dimensional (3-D) feature descriptor named longitude and latitude spin image (LLSI). The whole procedure has two modules: local reference frame (LRF) definition and LLSI feature description. We employ the same technique as Tombari to define the LRF. The LLSI feature descriptor is obtained by stitching the longitude and latitude (LL) image to the original spin image vertically, where the LL image was generated similarly with the spin image by mapping a two-tuple ðθ; ϕÞ into a discrete two-dimensional histogram. The performance of the proposed LLSI descriptor was rigorously tested on a number of popular and publicly available datasets. The results showed that our method is more robust with respect to noise and varying mesh resolution than existing techniques. Finally, we tested our LLSI-based algorithm for 3-D object recognition on two popular datasets. Our LLSI-based algorithm achieved recognition rates of 100%, 98.2%, and 96.2%, respectively, when tested on the Bologna, University of Western Australia (UWA) (up to 84% occlusion), UWA datasets (all). Moreover, our LLSI-based algorithm achieved 100% recognition rate on the whole UWA dataset when generating the LLSI descriptor with the LRF proposed by Guo.

show abstract

Rotational Projection Statistics for 3D Local Surface Description and Object Recognition

Cited by 595 publications

References 61 publications

Experimental Evaluation of the Performance of Local Shape Descriptors for the Classification of 3D Data in Precision Farming

Experimental Evaluation of the Performance of Local Shape Descriptors for the Classification of 3D Data in Precision Farming

Signature of position angles histograms for 3D object recognition

Simple and efficient improvement of spin image for three-dimensional object recognition

Contact Info

Product

Resources

About