Reconstructing Superquadrics from Intensity and Color Images

Tomašević, Darian; Peer, Peter; Solina, Franc; Jaklič, Aleš

doi:10.3390/s22145332

Cited by 2 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these works focused on obtaining rough dimensions for an object for grasping and did not attempt to quantify how accurately the dimensions of the object can be determined in various environments and orientations. Other existing works have employed superquadric fitting to point cloud data for identifying and classifying objects [29][30][31]. The focus of these works is to generally classify objects.…”

Section: Objectmentioning

confidence: 99%

Dimensioning Cuboid and Cylindrical Objects Using Only Noisy and Partially Observed Time-of-Flight Data

Rodriguez,

Rangarajan,

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

One of the challenges of using Time-of-Flight (ToF) sensors for dimensioning objects is that the depth information suffers from issues such as low resolution, self-occlusions, noise, and multipath interference, which distort the shape and size of objects. In this work, we successfully apply a superquadric fitting framework for dimensioning cuboid and cylindrical objects from point cloud data generated using a ToF sensor. Our work demonstrates that an average error of less than 1 cm is possible for a box with the largest dimension of about 30 cm and a cylinder with the largest dimension of about 20 cm that are each placed 1.5 m from a ToF sensor. We also quantify the performance of dimensioning objects using various object orientations, ground plane surfaces, and model fitting methods. For cuboid objects, our results show that the proposed superquadric fitting framework is able to achieve absolute dimensioning errors between 4% and 9% using the bounding technique and between 8% and 15% using the mirroring technique across all tested surfaces. For cylindrical objects, our results show that the proposed superquadric fitting framework is able to achieve absolute dimensioning errors between 2.97% and 6.61% when the object is in a horizontal orientation and between 8.01% and 13.13% when the object is in a vertical orientation using the bounding technique across all tested surfaces.

show abstract

Section: Objectmentioning

confidence: 99%

Dimensioning Cuboid and Cylindrical Objects Using Only Noisy and Partially Observed Time-of-Flight Data

Rodriguez,

Rangarajan,

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

The Concept of Processing, Analysis and Visualization of Geophysical Data Based on Elements of Tensor Calculus

Vorobeva,

Vorobev,

Orlov

2024

View full text Add to dashboard Cite

One of the main approaches to processing, analysis and visualization of geophysical data is the use of geographic information systems and technologies, which is due to their geospatial reference. At the same time, the complexity of presenting geophysical data is associated with their complex structure, which involves many components that have the same geospatial reference. Vivid examples of data of such a structure and format are gravitational and geomagnetic fields, which in the general case are specified by three and four-component vectors with multidirectional coordinate axes. At the same time, today there are no solutions that allow visualizing these data in a complex without decomposing them into individual scalar values, which, in turn, can be presented in the form of one or many spatial layers. In this regard, the work proposes a concept that uses elements of tensor calculus for processing, storing and visualizing information of this format. In particular, a mechanism for tensor representation of field components has been formalized with the possibility of combining it with other data of the same format, on the one hand, and convolution when combined with data of a lower rank. Using the example of a hybrid relational-hierarchical data model, a mechanism for storing information on tensor fields is proposed, which provides for the possibility of describing and subsequently applying transformation instructions when transitioning between different coordinate systems. The paper discusses the use of this approach in the transition from the Cartesian to the spherical coordinate system when representing the parameters of the geomagnetic field. For complex visualization of tensor field parameters, an approach based on the use of tensor glyphs is proposed. The latter are superellipses with axes corresponding to the rank of the tensor. In this case, the attribute values themselves are proposed to be visualized relative to the corresponding axes of the graphic primitive in such a way that the data distribution can be specified by varying the gradient of the corresponding monochrome representation of the parameter along the corresponding axis. The performance of the proposed concept was investigated during a comparative analysis of the tensor approach with known solutions based on the scalar decomposition of the corresponding complex values with their subsequent representation in the form of one or many spatial layers. The analysis showed that the use of the proposed approach will significantly increase the visibility of the generated geospatial image without the need for complex overlapping of spatial layers.

show abstract

Reconstructing Superquadrics from Intensity and Color Images

Cited by 2 publications

References 47 publications

Dimensioning Cuboid and Cylindrical Objects Using Only Noisy and Partially Observed Time-of-Flight Data

Dimensioning Cuboid and Cylindrical Objects Using Only Noisy and Partially Observed Time-of-Flight Data

The Concept of Processing, Analysis and Visualization of Geophysical Data Based on Elements of Tensor Calculus

Contact Info

Product

Resources

About