CV-SDF - a model for real-time computer vision applications

Stichling, Dirk; Kleinjohann, Bernd

doi:10.1109/acv.2002.1182202

Cited by 10 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is based on a design methodology developed for real-time CV algorithms called CV-SDF (Computer Vision Synchronous Data Flow), which is described in detail in [6].…”

Section: Figure 3 Ar-soccer and The Edge-tracking Algorithmmentioning

confidence: 99%

Foot-based mobile interaction with games

Paelke¹,

Reimann

Stichling

2004

Proceedings of the 2004 ACM SIGCHI International Conference on Advances in Computer Entertainment Technology

View full text Add to dashboard Cite

Interaction with mobile applications is often awkward due to the limited and miniaturized input modalities available. This is especially problematic for games where the only incentive to use an application is the pleasure derived from the interaction. It is therefore interesting to examine novel forms of interaction in order to increase the "playability" of mobile games.In this paper we present a simple mobile gaming application on a standard Pocket PC PDA that employs computer vision (CV) as it's main interaction modality. Practical experience with the application demonstrates the feasibility of CV as a primary interaction modality and indicates the high potential of CV as an input modality for mobile devices in the future. Our approach exploits the video capabilities that are becoming ubiquitous on camera equipped smart-phones and PDAs to provide a fun solution for interaction tasks in games like "Pong", "Break-out" or soccer.

show abstract

“…It is based on a design methodology developed for real-time CV algorithms called CV-SDF (Computer Vision Synchronous Data Flow), which is described in detail in [6].…”

Section: Figure 3 Ar-soccer and The Edge-tracking Algorithmmentioning

confidence: 99%

Foot-based mobile interaction with games

Paelke¹,

Reimann

Stichling

2004

Proceedings of the 2004 ACM SIGCHI International Conference on Advances in Computer Entertainment Technology

View full text Add to dashboard Cite

show abstract

“…Although dataflow models are well suited for stream based application domains to the best of the authors knowledge mapping CV algorithms to the dataflow model to exploit parallel hardware is largely unexplored with a few notable exceptions [6]- [8]. One possible reason is that CV algorithms cannot trivially be parallelised.…”

Section: Introductionmentioning

confidence: 99%

Profile driven dataflow optimisation of mean shift visual tracking

Bhowmik

Wallace

Stewart

et al. 2014

2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

Abstract-Profile guided optimisation is a common technique used by compilers and runtime systems to shorten execution runtimes and to optimise locality aware scheduling and memory access on heterogeneous hardware platforms. Some profiling tools trace the execution of low level code, whilst others are designed for abstract models of computation to provide rich domainspecific context in profiling reports. We have implemented mean shift, a computer vision tracking algorithm, in the RVC-CAL dataflow language and use both dynamic runtime and static dataflow profiling mechanisms to identify and eliminate bottlenecks in our naive initial version. We use these profiling reports to tune the CPU scheduler reducing runtime by 88%, and to optimise our dataflow implementation that reduces runtime by a further 43% -an overall runtime reduction of 93%. We also assess the portability of our mean shift optimisations by trading off CPU runtime against resource utilisation on FPGAs. Applying all dataflow optimisations reduces FPGA design space significantly, requiring fewer slice LUTs and less block memory.

show abstract

“…This includes embedded realtime architectures [2,5,[14][15][16][17], real-time vision [2,[14][15][16][17], learning and adaptation from limited sensor data, skill learning and methods to propagate learned skills and behaviors in the robot team [13,12,9]. However, our goal is not to carry out research for specific solutions in the robotic soccer domain, but to use and test advanced techniques from different research projects.…”

Section: Introductionmentioning

confidence: 99%

The Paderkicker Team: Autonomy in Realtime Environments

Richert

Kleinjohann

Koch

et al.

From Model-Driven Design to Resource Management for Distributed Embedded Systems

View full text Add to dashboard Cite

Abstract:The Paderkickers are a robot soccer team that makes heavy use of automotive technology Uke C167 micro-controllers or communication over CAN bus. All sensor data is processed on these decentralized embedded nodes to yield a high degree of reliability and hardware layer abstraction. In this paper, we describe how the complex system copes with perception and action in real-time and integrates it in the higher strategy layer to achieve autonomous behavior.

show abstract

CV-SDF - a model for real-time computer vision applications

Cited by 10 publications

References 8 publications

Foot-based mobile interaction with games

Foot-based mobile interaction with games

Profile driven dataflow optimisation of mean shift visual tracking

The Paderkicker Team: Autonomy in Realtime Environments

Contact Info

Product

Resources

About