Organizing multimodal perception for autonomous learning and interactive systems

Schmuedderich, Jens; Brandl, Holger; Bolder, Bram; Heracles, Martin; Janßen, H.; Mikhailova, Inna; Goerick, Christian

doi:10.1109/ichr.2008.4755989

Cited by 14 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These ProtoObjects can be considered as a pointer to objects in the environment: As long as this pointer remains valid, all visual information can be obtained by referencing this pointer and extracting the information from the image [15]. In the following, the term P t C,i will be used to refer to the ith Proto-Object of the Proto-Object list P t C created by the Classifier Cue at time t, whereas P t S,i will refer in an analogous way to a Proto-Object created by the Stereo-Cue.…”

Section: System Architecture and Elementsmentioning

confidence: 99%

“…Thus, the decision to bind an existing model to a detection is made by predicting all available models towards the timestep t c of the detection and perform a comparison between the detection and the predicted models. If a detection is associated to a model, the model is updated as described in [15]. This traditional approach exhibits three limitations for the automotive domain:…”

Section: E Proto-object Fusionmentioning

confidence: 99%

See 1 more Smart Citation

System approach for multi-purpose representations of traffic scene elements

Schmuedderich

Einecke

Hasler

et al. 2010

13th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

Abstract-A major step towards intelligent vehicles lies in the acquisition of an environmental representation of sufficient generality to serve as the basis for a multitude of different assistance-relevant tasks. This acquisition process must reliably cope with the variety of environmental changes inherent to traffic environments. As a step towards this goal, we present our most recent integrated system performing object detection in challenging environments (e.g., inner-city or heavy rain). The system integrates unspecific and vehicle-specific methods for the detection of traffic scene elements, thus creating multiple object hypotheses. Each detection method is modulated by optimized models of typical scene context features which are used to enhance and suppress hypotheses. A multi-object tracking and fusion process is applied to make the produced hypotheses spatially and temporally coherent. In extensive evaluations we show that the presented system successfully analyzes scene elements under diverse conditions, including challenging weather and changing scenarios. We demonstrate that the used generic hypothesis representations allow successful application to a variety of tasks including object detection, movement estimation, and risk assessment by time-to-contact evaluation.

show abstract

Section: System Architecture and Elementsmentioning

confidence: 99%

Section: E Proto-object Fusionmentioning

confidence: 99%

System approach for multi-purpose representations of traffic scene elements

Schmuedderich

Einecke

Hasler

et al. 2010

13th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

show abstract

“…Since our approach requires object annotations, we perform hypothesis generation only for images with existing object annotations (roughly every tenth image). The detection threshold of the visual detection subsystem is set to a sufficiently low value so as to produce at least 40 hypotheses 3 . Each hypothesis is subsequently assigned an object identity of "vehicle" if it (mutually) intersects more than 80% of an existing vehicle annotation ("non-vehicle" otherwise).…”

Section: Benchmark Taskmentioning

confidence: 99%

“…Prominent examples for this development are, e.g., humanoid robots [2,3] and intelligent vehicles [4,5]. Numerous ways exist for coping with this additional complexity, such as formal hierarchical design languages [6], component-based graphical development systems [7] or machine learning methods [8,9].…”

Section: Introductionmentioning

confidence: 99%

The contribution of context information: A case study of object recognition in an intelligent car

2012

View full text Add to dashboard Cite

In this article, we explore the potential contribution of multimodal context information to object detection in an "intelligent car". The used car platform incorporates subsystems for the detection of objects from local visual patterns, as well as for the estimation of global scene properties (sometimes denoted "scene context" or just "context") such as the shape of the road area or the 3D position of the ground plane. Annotated data recorded on this platform is publicly available as the "HRI RoadTraffic" vehicle video dataset, which forms the basis for this investigation.In order to quantify the contribution of context information, we investigate whether it can be used to infer object identity with little or no reference to local patterns of visual appearance. Using a challenging vehicle detection task based on the "HRI RoadTraffic" dataset, we train selected algorithms ("context models") to estimate object identity from context information alone. In the course of our performance evaluations, we also analyze the effect of typical real-world conditions (noise, high input dimensionality, environmental variation) on context model performance.As a principal result, we show that the learning of context models is feasible with all tested algorithms, and that object identity can be estimated from context information with similar accuracy as by relying on local pattern recognition methods. We also find that the use of basis function representations [1] (also known as "population codes") allows the simplest (and therefore most efficient) learning methods to perform best in the benchmark, suggesting that the use of context is feasible even in systems operating under strong performance constraints.

show abstract

“…The focus of this paper is not on the single elements but rather on the system design and the key properties of the architecture. For a detailed discussion of the the visual and speech processing of our system please see [2].…”

Section: Introductionmentioning

confidence: 99%

Expectation-driven autonomous learning and interaction system

Bolder

Brandl

Heracles

et al. 2008

Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots

View full text Add to dashboard Cite

Abstract-We introduce our latest autonomous learning and interaction system instance ALIS 2. It comprises different sensing modalities for visual (depth blobs, planar surfaces, motion) and auditory (speech, localization) signals and selfcollision free behavior generation on the robot ASIMO. The system design emphasizes the split into a completely autonomous reactive layer and an expectation generation layer. Different feature channels can be classified and named with arbitrary speech labels in on-line learning sessions. The feasibility of the proposed approach is shown by interaction experiments.

show abstract

Organizing multimodal perception for autonomous learning and interactive systems

Cited by 14 publications

References 13 publications

System approach for multi-purpose representations of traffic scene elements

System approach for multi-purpose representations of traffic scene elements

The contribution of context information: A case study of object recognition in an intelligent car

Expectation-driven autonomous learning and interaction system

Contact Info

Product

Resources

About