| |
Records |
Links |
|
Author  |
Cristhian A. Aguilera, Cristhian Aguilera, Cristóbal A. Navarro, & Angel D. Sappa |
|
| |
Title |
Fast CNN Stereo Depth Estimation through Embedded GPU Devices |
Type |
Journal Article |
| |
Year |
2020 |
Publication |
Sensors 2020 |
Abbreviated Journal |
|
|
| |
Volume |
Vol. 2020-June |
Issue |
11 |
Pages |
pp. 1-13 |
|
| |
Keywords |
stereo matching; deep learning; embedded GPU |
|
| |
Abstract |
Current CNN-based stereo depth estimation models can barely run under real-time
constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art
evaluations usually do not consider model optimization techniques, being that it is unknown what is
the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models
on three different embedded GPU devices, with and without optimization methods, presenting
performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth
estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture
for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically
augmenting the runtime speed of current models. In our experiments, we achieve real-time inference
speed, in the range of 5–32 ms, for 1216 368 input stereo images on the Jetson TX2, Jetson Xavier,
and Jetson Nano embedded devices. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
English |
Summary Language |
English |
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
14248220 |
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
|
Approved |
no |
|
| |
Call Number |
cidis @ cidis @ |
Serial |
132 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Charco, J.L., Sappa, A.D., Vintimilla, B.X., Velesaca, H.O. |
|
| |
Title |
Camera pose estimation in multi-view environments:from virtual scenarios to the real world |
Type |
Journal Article |
| |
Year |
2021 |
Publication |
In Image and Vision Computing Journal. (Article number 104182) |
Abbreviated Journal |
|
|
| |
Volume |
Vol. 110 |
Issue |
|
Pages |
|
|
| |
Keywords |
Relative camera pose estimation, Domain adaptation, Siamese architecture, Synthetic data, Multi-view environments |
|
| |
Abstract |
This paper presents a domain adaptation strategy to efficiently train network architectures for estimating the relative camera pose in multi-view scenarios. The network architectures are fed by a pair of simultaneously acquired
images, hence in order to improve the accuracy of the solutions, and due to the lack of large datasets with pairs of
overlapped images, a domain adaptation strategy is proposed. The domain adaptation strategy consists on transferring the knowledge learned from synthetic images to real-world scenarios. For this, the networks are firstly
trained using pairs of synthetic images, which are captured at the same time by a pair of cameras in a virtual environment; and then, the learned weights of the networks are transferred to the real-world case, where the networks are retrained with a few real images. Different virtual 3D scenarios are generated to evaluate the
relationship between the accuracy on the result and the similarity between virtual and real scenarios—similarity
on both geometry of the objects contained in the scene as well as relative pose between camera and objects in the
scene. Experimental results and comparisons are provided showing that the accuracy of all the evaluated networks for estimating the camera pose improves when the proposed domain adaptation strategy is used,
highlighting the importance on the similarity between virtual-real scenarios. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
English |
Summary Language |
English |
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
|
Approved |
no |
|
| |
Call Number |
cidis @ cidis @ |
Serial |
147 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Carlos Monsalve; Alain April and Alain Abran |
|
| |
Title |
Measuring software functional size from business process models |
Type |
Journal Article |
| |
Year |
2011 |
Publication |
International Journal of Software Engineering and Knowledge Engineering |
Abbreviated Journal |
|
|
| |
Volume |
Vol. 21 |
Issue |
|
Pages |
pp. 311–338 |
|
| |
Keywords |
|
|
| |
Abstract |
ISO 14143-1 specifies that a functional size measurement (FSM) method must provide measurement procedures to quantify the functional user requirements (FURs) of software. Such quantitative information, functional size, is typically used, for instance, in software estimation. One of the international standards for FSM is the COSMIC FSM method — ISO 19761 — which was designed to be applied both to the business application (BA) software domain and to the real-time software domain. A recurrent problem in FSM is the availability and quality of the inputs required for measurement purposes; that is, well documented FURs. Business process (BP) models, as they are commonly used to gather requirements from the early stages of a project, could be a valuable source of information for FSM. In a previous article, the feasibility of such an approach for the BA domain was analyzed using the Qualigram BP modeling notation. This paper complements that work by: (1) analyzing the use of BPMN for FSM in the BA domain; (2) presenting notation-independent guidelines for the BA domain; and (3) analyzing the possibility of using BP models to perform FSM in the real-time domain. The measurement results obtained from BP models are compared with those of previous FSM case studies. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
English |
Summary Language |
English |
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
|
Approved |
no |
|
| |
Call Number |
cidis @ cidis @ |
Serial |
19 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Armin Mehri; Parichehr Behjati; Angel Domingo Sappa |
|
| |
Title |
TnTViT-G: Transformer in Transformer Network for Guidance Super Resolution. |
Type |
Journal Article |
| |
Year |
2023 |
Publication |
IEEE Access |
Abbreviated Journal |
|
|
| |
Volume |
Vol. 11 |
Issue |
|
Pages |
pp. 11529-11540 |
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
21693536 |
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
|
Approved |
no |
|
| |
Call Number |
cidis @ cidis @ |
Serial |
207 |
|
| Permanent link to this record |
