A Hierarchical System Integration Approach with Application to Visual Scene Exploration for Driver Assistance

Dittes, Benjamin; Heracles, Martin; Michalke, Thomas; Kastner, Robert; Gepperth, Alexander; Fritsch, Jannik; Goerick, Christian

doi:10.1007/978-3-642-04667-4_26

Cited by 5 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…that the sending unit / process is still alive). An algorithm to achieve this loose coupling can be found in [31].…”

Section: Mapping Sys2d Designs To Software Infrastructurementioning

confidence: 99%

“…B2 (+) Coupling and dependencies are specified by the top-down and bottom-up channels. B3,4 (+) A translation to the ToolBOS [30] infrastructure is presented in [19] and allows partial execution along the bottom-up / top-down dependencies [31]. B5 (?)…”

Section: Systematicamentioning

confidence: 99%

“…B2 (+) Coupling and dependencies are specified by input roles and push/pull connections. B3 (+) The formalism can be translated to any infrastructure which supports communicating units and the three input roles used (see [31]) -which is possible in practically every infrastructure, from service-oriented systems over agents and blackboard systems to data-flow and OOP-based engines. B4 (+) The functional properties of incremental construction and complete subsystems defined in Section 5.4 aim directly at utilizing infrastructure properties of partial testing and graceful degradation.…”

Section: Evaluation Of Systematica 2d In the Measurementioning

confidence: 99%

See 2 more Smart Citations

A language for formal design of embedded intelligence research systems

Dittes

Goerick

2011

Robotics and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

“…that the sending unit / process is still alive). An algorithm to achieve this loose coupling can be found in [31].…”

Section: Mapping Sys2d Designs To Software Infrastructurementioning

confidence: 99%

Section: Systematicamentioning

confidence: 99%

Section: Evaluation Of Systematica 2d In the Measurementioning

confidence: 99%

See 1 more Smart Citation

A language for formal design of embedded intelligence research systems

Dittes

Goerick

2011

Robotics and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

“…There is extensive literature about the computational modeling of the various aspects of visual attention [20], [1], [3], [21], [22], [23], [24], as well as some limited work attempting to make use of comparable mechanisms in technical applications [25], [26], [27], [3], [2]. This body of work shows that visual attention is a potentially powerful tool to improve real-world object detection, but also that the effort to make it work in real problems is a considerable one.…”

Section: A Related Workmentioning

confidence: 99%

Robust visual pedestrian detection by tight coupling to tracking

Gepperth

Sattarov

Heisele

et al. 2014

17th International IEEE Conference on Intelligent Transportation Systems (ITSC)

Self Cite

View full text Add to dashboard Cite

Abstract-In this article, we propose a visual pedestrian detection system which couples pedestrian appearance and pedestrian motion in a Bayesian fashion, with the goal of making detection more invariant to appearance changes. More precisely, the system couples dense appearance-based pedestrian likelihoods derived from a sliding-window SVM detector to spatial prior distributions obtained from the prediction step of a particle filter based pedestrian tracker. This mechanism, which we term dynamic attention priors (DAP), is inspired by recent results on predictive visual attention in humans and can be implemented at negligible computational cost. We prove experimentally, using a set of public, annotated pedestrian sequences, that detection performance is improved significantly, especially in cases where pedestrians differ from the learned models, e.g., when they are too small, have an unusual pose or occur before strongly structured backgrounds. In particular, dynamic attention priors allow to use more restrictive detection thresholds without losing detections while minimizing false detections.

show abstract

“…The direct way is to design a system already from the beginning by means of the framework. This has been done based on a preliminary version of the framework in [30]. We will support this approach by a tool supporting this kind of design, but this is beyond the scope of this paper.…”

Section: A Applying Systematicamentioning

confidence: 99%

Towards an Understanding of Hierarchical Architectures

Goerick

2011

IEEE Trans. Auton. Mental Dev.

Self Cite

View full text Add to dashboard Cite

Abstract-Cognitive systems research aims to understand how cognitive abilities can be created in artificial systems. One key issue is the architecture of the system. It organizes the interplay between the different system elements and thus, determines the principle limits for the performance of the system. In this contribution, we focus on important properties of hierarchical cognitive systems. Therefore, we first present a framework for modeling hierarchical systems. Based on this framework, we formulate and discuss some crucial issues that should be treated explicitly in the design of a system. On this basis, we analyze and compare several well-established cognitive architectures with respect to their internal structure.Index Terms-Behavior space, cognitive architecture, hierarchical architecture, sensor space, system design.

show abstract

A Hierarchical System Integration Approach with Application to Visual Scene Exploration for Driver Assistance

Cited by 5 publications

References 14 publications

A language for formal design of embedded intelligence research systems

A language for formal design of embedded intelligence research systems

Robust visual pedestrian detection by tight coupling to tracking

Towards an Understanding of Hierarchical Architectures

Contact Info

Product

Resources

About