Conference Paper

Cross-Articulation Learning for Robust Detection of Pedestrians.

DOI: 10.1007/11861898_25 Conference: Pattern Recognition, 28th DAGM Symposium, Berlin, Germany, September 12-14, 2006, Proceedings
Source: DBLP

ABSTRACT Recognizing categories of articulated objects in real-world scenarios is a challenging problem for today's vision algorithms. Due to the large appearance changes and intra-class variability of these objects, it is hard to define a model, which is both general and discriminative enough to capture the properties of the category. In this work, we pro- pose an approach, which aims for a suitable trade-off for this problem. On the one hand, the approach is made more discriminant by explic- itly distinguishing typical object shapes. On the other hand, the method generalizes well and requires relatively few training samples by cross- articulation learning. The effectiveness of the approach is shown and compared to previous approaches on two datasets containing pedestri- ans with different articulations.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Over the last few years, visual people detection has made impressive progress. The paper gives an overview of some of the most successful techniques for people detection and also summarizes a recent quantitative comparison of sev- eral state-of-the-art methods. As a proof-of-concept we show that the combination of visual and laser-based peo- ple detection can result in a significant increase in perfor- mance. We also briefly discuss future research directions for visual people detection.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Popular Hough Transform-based object detection approaches usually construct an appearance codebook by clustering local image features. However, how to choose appropriate values for the parameters used in the clustering step remains an open problem. Moreover, some popular histogram features extracted from overlapping image blocks may cause a high degree of redundancy and multicollinearity. In this paper, we propose a novel Hough Transform-based object detection approach. First, to address the above issues, we exploit a Bridge Partial Least Squares (BPLS) technique to establish context-encoded Hough Regression Models (HRMs), which are linear regression models that cast probabilistic Hough votes to predict object locations. BPLS is an efficient variant of Partial Least Squares (PLS). PLS-based regression techniques (including BPLS) can reduce the redundancy and eliminate the multicollinearity of a feature set. And the appropriate value of the only parameter used in PLS (i.e., the number of latent components) can be determined by using a cross-validation procedure. Second, to efficiently handle object scale changes, we propose a novel multi-scale voting scheme. In this scheme, multiple Hough images corresponding to multiple object scales can be obtained simultaneously. Third, an object in a test image may correspond to multiple true and false positive hypotheses at different scales. Based on the proposed multi-scale voting scheme, a principled strategy is proposed to fuse hypotheses to reduce false positives by evaluating normalized pointwise mutual information between hypotheses. In the experiments, we also compare the proposed HRM approach with its several variants to evaluate the influences of its components on its performance. Experimental results show that the proposed HRM approach has achieved desirable performances on popular benchmark datasets.
    Neurocomputing 11/2014; · 2.01 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Die Detektion oder Erkennung von Fußgängern im Straßenverkehr ist eines der wichtigsten, zugleich aber auch eines der schwierigsten Probleme der Sensorverarbeitung. Um dem Fahrer optimale Assistenz leisten zu können, sind idealerweise alle Fußgänger unabhängig von Sichtverhältnissen robust zu erkennen. Dies wird jedoch durch verschiedenste Umweltfaktoren erschwert. Problematisch sind insbesondere wechselnde Wetter- und Sichtverhältnisse, schwierige Beleuchtungssituationen und Straßenverhältnisse. Des Weiteren erschweren individuelle Kleidung und die Verdeckung von Fußgängern beispielsweise durch parkende Autos die Detektionsaufgabe. Weiterhin zeichnen sich Fußgänger im Vergleich zu vielen anderen Objekten in Straßenverkehrsszenen durch einen hohen Grad an Artikulation aus, die insbesondere umrissbasierte Verfahren erschwert.
    Handbuch Fahrerassistenzsysteme. 01/2009;