Real-Time Fine Grained Occupancy Estimation Using Depth Sensors on ARM Embedded Platforms

2017 ◽  
Author(s):  
Sirajum Munir ◽  
Ripudaman Singh Arora ◽  
Craig Hesling ◽  
Juncheng Li ◽  
Jonathan Francis ◽  
...  
Keyword(s):  
Real Time ◽  
Fine Grained ◽  
Depth Sensors ◽  
Occupancy Estimation ◽  
Embedded Platforms

Real-time, High-resolution Depth Upsampling on Embedded Accelerators

2021 ◽  
Vol 20 (3) ◽  
pp. 1-22
Author(s):  
David Langerman ◽  
Alan George
Keyword(s):  
High Resolution ◽  
Low Power ◽  
Real Time ◽  
Mixed Reality ◽  
Graphics Processing Unit ◽  
Processing Unit ◽  
Reconfigurable Logic ◽  
Depth Sensors ◽  
Time Requirements ◽  
Graphics Processing

High-resolution, low-latency apps in computer vision are ubiquitous in today’s world of mixed-reality devices. These innovations provide a platform that can leverage the improving technology of depth sensors and embedded accelerators to enable higher-resolution, lower-latency processing for 3D scenes using depth-upsampling algorithms. This research demonstrates that filter-based upsampling algorithms are feasible for mixed-reality apps using low-power hardware accelerators. The authors parallelized and evaluated a depth-upsampling algorithm on two different devices: a reconfigurable-logic FPGA embedded within a low-power SoC; and a fixed-logic embedded graphics processing unit. We demonstrate that both accelerators can meet the real-time requirements of 11 ms latency for mixed-reality apps. 1

scholarly journals The interactional achievement of speaker meaning: Toward a formal account of conversational inference

2018 ◽  
Vol 15 (5) ◽  
pp. 593-625 ◽  
Author(s):  
Chi-Hé Elder ◽  
Michael Haugh
Keyword(s):  
Real Time ◽  
Theoretical Assumption ◽  
Fine Grained ◽  
Local Process ◽  
Speaker Meaning ◽  
Pragmatic Analysis ◽  
Proposed Model ◽  
Partial Representation ◽  
Meaning Negotiation ◽  
Theories Of Meaning

Abstract Dominant accounts of “speaker meaning” in post-Gricean contextualist pragmatics tend to focus on single utterances, making the theoretical assumption that the object of pragmatic analysis is restricted to cases where speakers and hearers agree on utterance meanings, leaving instances of misunderstandings out of their scope. However, we know that divergences in understandings between interlocutors do often arise, and that when they do, speakers can engage in a local process of meaning negotiation. In this paper, we take insights from interactional pragmatics to offer an empirically informed view on speaker meaning that incorporates both speakers’ and hearers’ perspectives, alongside a formalization of how to model speaker meanings in such a way that we can account for both understandings – the canonical cases – and misunderstandings, but critically, also the process of interactionally negotiating meanings between interlocutors. We highlight that utterance-level theories of meaning provide only a partial representation of speaker meaning as it is understood in interaction, and show that inferences about a given utterance at any given time are formally connected to prior and future inferences of participants. Our proposed model thus provides a more fine-grained account of how speakers converge on speaker meanings in real time, showing how such meanings are often subject to a joint endeavor of complex inferential work.

scholarly journals Real-Time Support in the Proposal for Fine-Grained Parallelism in Ada

2015 ◽  
Author(s):  
Luis Miguel Pinho ◽  
Brad Moore ◽  
Stephen Michell ◽  
S. Tucker Taft
Keyword(s):  
Real Time ◽  
Fine Grained ◽  
Fine Grained Parallelism

scholarly journals Real-Time Continuous Action Recognition Using Pose Contexts With Depth Sensors

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 51708-51720 ◽  
Author(s):  
Hejun Wu ◽  
Zhenye Huang ◽  
Biao Hu ◽  
Zhi Yu ◽  
Xiying Li ◽  
...  
Keyword(s):  
Real Time ◽  
Action Recognition ◽  
Continuous Action ◽  
Depth Sensors
Sign in / Sign up

Export Citation Format

Share Document