Conference Paper

System approach for multi-purpose representations of traffic scene elements

Honda Res. Inst. Eur. GmbH, Offenbach, Germany
DOI: 10.1109/ITSC.2010.5625234 Conference: Intelligent Transportation Systems (ITSC), 2010 13th International IEEE Conference on
Source: IEEE Xplore

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.

0 Bookmarks
 · 
63 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: The construction of complex artifacts of artificial intelligence requires large-scale system integration and collaboration. System architectures are a central issue to enable this process. To develop these, hypotheses must be formulated, validated and evolved. We therefore present Systematica 2d, a formalism suitable for both flexible description of hierarchical architecture concepts as well as functional design of the resulting system integration process. We motivate the approach and relate it to other formal descriptions by means of a new formalization measure. It consists of a set of criteria to evaluate how well a formalism supports the expression, construction and reuse of intelligent systems. Systematica 2d is compared with existing formalization languages under this measure and shown to have at least their level of expression. In addition, the system properties of incremental composition, partial testability and global deadlock-free operation are formally defined and proven in the formalism.
    Robotics and Autonomous Systems. 01/2011; 59:181-193.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this contribution, we explore the possibilities of learning in large-scale, multimodal processing systems operating under real-world conditions. Using an instance of a large-scale object detection system for complex traffic scenes, we demonstrate that there is a great deal of very robust correlations between high-level processing results quantities, and that such correlations can be autonomously detected and exploited to improve performance. We formulate requirements for performing system-level learning (online operation, scalability to high-dimensional inputs, data mining ability, generality and simplicity) and present a suitable neural learning strategy. We apply this method to infer the identity of objects from multimodal object properties (“context”) computed within the correlated system and demonstrate strong performance improvements as well as significant generalization. Finally, we compare our approach to state-of-the-art learning methods, Locally Weighted Projection Regression (LWPR) and Multilayer Perceptron (MLP), and discuss the results in terms of the requirements for system-level learning.
    Artificial Neural Networks - ICANN 2010 - 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part III; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes an embedded real time method for detecting and tracking of multiobjects including vehicles, pedestrians, motorbikes and bicycles in urban environment. The features of different objects are learned as a deformable object model through the combination of a latent support vector machine (LSVM) and histograms of oriented gradients (HOG). Laser depth data have been used as a priori to generate objects hypothesis regions and estimate HOG feature pyramid level to reduce the detection time of previously presented algorithm. Detected objects are tracked through a particle filter which fuses the observations from laser map and sequential images. We use the accurate laser data for state predication and use image HOG information for likelihood calculation. The likelihood finds the maximum HOG feature compatibility for both root and parts of the tracked objects to increase tracking accuracy for deformable objects such as pedestrians in crowded scenes. Extensive experiments with urban scenarios showed that the proposed method can improve the detection and tracking in urban environment.
    01/2011;

Full-text (2 Sources)

View
45 Downloads
Available from
May 16, 2014