194 results for Klette, Reinhard

  • Incremental Structured ICP Algorithm

    Geng, Haokun; Chien, J; Nicolescu, Radu; Klette, Reinhard (2014-12-08)

    Conference item
    The University of Auckland Library

    Variants of the ICP algorithm are widely used in many vision- based applications, such as visual odometry, structure from motion, 3D reconstruction, or object segmentation. Establishing correct correspon- dences between two sets of 3D points, generated by stereo vision, needs to take those uncertainties into account. We propose a novel variant of the traditional ICP algorithm for solving the mentioned alignment problem. Our method, named incremental structured iterative closest point, aims at improved registrations of 3D points calculated for real world data. Evaluations are carried out by measuring the distances between two in- puts, in both local and global perspectives, and experimental results are visually presented in this paper.

    View record details
  • Generation of Random Digital Simple Curves with Artistic Emulation

    Bhowmick, Partha; Klette, Reinhard (2014-01)

    Journal article
    The University of Auckland Library

    This paper presents two novel interdependent techniques for random digital simple curve generation. The first one is about generating a curve of finite length, producing a sequence of points defining a digital path ρ ‘on the fly’. The second is for the creation of artistic sketches from line drawings and edge maps, using multiple instances of such random digital paths. A generated digital path ρ never intersects or touches itself, and hence becomes simple and irreducible. This is ensured by detecting every possible trap formed by the previously generated part of ρ, which, if entered into, cannot be exited without touching or intersecting ρ. The algorithm is completely free of any backtracking and its time complexity is linear in the length of ρ. For artistic emulation, a curve-constrained domain is defined by the Minkowski sum of the input drawing with a structuring element whose size varies with the pencil diameter. An artist’s usual trait of making irregular strokes and sub-strokes, with varying shades while sketching, is thus captured in a realistic manner. Algorithmic solutions of non-photorealism are perceived as an enrichment of contemporary digital art. Simulation results for the presented algorithms have been furnished to demonstrate their efficiency and elegance.

    View record details
  • Evaluation of a new Coarse-to-Fine Strategy for Fast Semi-Global Stereo Matching

    Klette, Reinhard; Hermann, S (2011)

    Conference item
    The University of Auckland Library

    The paper considers semi-global stereo matching in the context of vision-based driver assistance systems. The need for real-time performance in this field requires a design change of the originally proposed method to run on current hardware. This paper proposes such a new design; the novel strategy first generates a disparity map from half-resolution input images. The result is then used as prior to restrict the disparity search space for full-resolution computation. This approach is compared to an SGM strategy as employed currently in a state-of-the-art real-time FPGA solution. Furthermore, trinocular stereo evaluation is performed on ten real-world traffic sequences with a total of 4,000 trinocular frames. An extension to the original evaluation methodology is proposed to resolve ambiguities and to incorporate disparity density in a statistically meaningful way. Evaluation results indicate that the novel SGM method is up to 40% faster when compared to the previous strategy. It returns denser disparity maps, and is also more accurate on evaluated traffic scenes.

    View record details
  • Half-Resolution Semi-Global Stereo Matching

    Hermann, Simon; Morales, Sandino; Klette, Reinhard (2011-01-01)

    Conference item
    The University of Auckland Library

    Semi-global matching is a popular choice for applications where dense and robust stereo estimation is required and real-time performance is crucial. It therefore plays an important role in vision-based driver assistance systems. The strength of the algorithm comes from the integration of multiple 1D energy paths which are minimized along eight different directions across the image domain. The contribution of this paper is twofold. First, a thorough evaluation of stereo matching quality is performed when the number of accumulation paths is reduced. Second, an alteration of semi-global matching is proposed that operates only on half of the image domain without losing disparity resolution. The evaluation is performed on four real-world driving sequences of 400 frames each, as well as on 396 frames of a synthetic image sequence where sub-pixel accurate ground truth is available. Results indicate that a reduction of accumulation paths is a very good option to improve the run-time performance without losing significant quality, even on sub-pixel level. Furthermore, operating semiglobal matching only on half the image yields almost identical results to the corresponding full path integration. This approach yields the potential to further speed up the runtime and could also be exploited for other alterations of the algorithm.

    View record details
  • Approximate shortest paths in simple polyhedra

    Li, F; Klette, Reinhard (2011)

    Conference item
    The University of Auckland Library

    Since the pioneering work by (Cohen and Kimmel, 1997) on finding a contour as a minimal path between two end points, shortest paths in volume images have raised interest in computer vision and image analysis. This paper considers the calculation of a Euclidean shortest path (ESP) in a three-dimensional (3D) polyhedral space Π. We propose an approximate κ(ε)⋅O(M|V|) 3D ESP algorithm, not counting time for preprocessing. The preprocessing time complexity equals O(M|E|+|F|+|V|log|V|) for solving a special, but ‘fairly general’ case of the 3D ESP problem, where Π does not need to be convex. V and E are the sets of vertices and edges of Π, respectively, and F is the set of faces (triangles) of Π. M is the maximal number of vertices of a so-called critical polygon, and κ(ε) = (L 0 − L)/ε where L 0 is the length of an initial path and L is the true (i.e., optimum) path length. The given algorithm solves approximately three (previously known to be) NP-complete or NP-hard 3D ESP problems in time κ(ε)⋅O(k) , where k is the number of layers in a stack, which is introduced in this paper as being the problem environment. The proposed approximation method has straightforward applications for ESP problems when analyzing polyhedral objects (e.g., in 3D imaging), of for ‘flying’ over a polyhedral terrain.

    View record details
  • Ground Truth Evaluation of Stereo Algorithms for Real World Applications

    Morales, S; Klette, Reinhard (2010)

    Conference item
    The University of Auckland Library

    Current stereo algorithms are capable to calculate accurate (as defined, e.g., by needs in vision-based driver assistance) dense disparity maps in real time. They have become the source of three-dimensional data for several indoor and outdoor applications. However, ground truth-based evaluation of such algorithms has been typically limited to data sets generated indoors in laboratories. In this paper we present a new approach to evaluate stereo algorithms using ground-truth over real world data sets. Ground truth is generated using range measurements acquired with a high-end laser range-finder. For evaluating as many points as possible in a given disparity map, we use two evaluation approaches: A direct comparison for those pixels with available range data, and a confidence measure for the remaining pixels.

    View record details
  • Approximate ground truth in the real world for testing optical flow algorithms

    Yang, X; Klette, Reinhard (2011)

    Conference item
    The University of Auckland Library

    Vision-based driver assistance requires basic vision modules for stereo analysis or optic flow calculation. Driving situations change frequently, and methods need to be evaluated in the real world. The paper proposes ways for evaluating optic flow techniques by using estimated geometries for surrounding buildings or 'road furniture'. It demonstrates the value of such an evaluation by discussing four different optic flow techniques.

    View record details
  • A comparative study of two vertical road modelling techniques

    Schauwecker, K; Klette, Reinhard (2011)

    Conference item
    The University of Auckland Library

    Binocular vision combined with stereo matching algorithms can be used in vehicles to gather data of the spatial proximity. To utilize this data we propose a new method for modeling the vertical road profile from a disparity map. This method is based on a region-growing technique, which iteratively performs a least-squares fit of a B-spline curve to a region of selected points. We compare this technique to two variants of the v-disparity method using either an envelope function or a planarity assumption. Our findings are that the proposed road-modeling technique outperforms both variants of the v-disparity technique, for which the planarity assumption is slightly better than the envelope version.

    View record details
  • Feature extraction and classification for insect footprint recognition

    Shin, Bok Suk; Klette, Reinhard; Russell, James (2012)

    Conference item
    The University of Auckland Library

    We propose a method to extract and classify insect footprints for the purpose of recognition. Our four-level procedural feature extraction model is defined as follows: First, images produce new data via the trace transform. Second, for reducing the dimensionality of the produced data, we apply some mathematical conversions. Third, dimensionality-reduced data are converted into frequency components. Finally, characteristic signals with significant components of representative values are created by excluding insignificant factors such as those related to noise. For classification, based on uncertain features, we propose a decision method defined by fuzzy weights and a fuzzy weighted mean. The proposed fuzzy weight decision method estimates weights according to degrees of contribution. Weights are assigned by ranking the degree of a feature's contribution. We present experimental results of classification by using the proposed method on scanned insect footprints. Experiments show that the proposed method is suitable for noisy footprints with irregular directions, or symmetrical patterns in the extracted segments.

    View record details
  • Real-world stereo-analysis evaluation

    Morales, S; Hermann, S; Klette, Reinhard (2012)

    Conference item
    The University of Auckland Library

    Evaluation of stereo-analysis algorithms is usually done by analysing the performance of stereo matchers on data sets with available ground truth. The trade-off between precise results, obtained with this sort of evaluation, and the limited amount (in both, quantity and diversity) of data sets, needs to be considered if the algorithms are required to analyse real-world environments. This chapter discusses a technique to objectively evaluate the performance of stereo-analysis algorithms using real-world image sequences. The lack of ground truth is tackled by incorporating an extra camera into a multi-view stereo camera system. The relatively simple hardware set-up of the proposed technique can easily be reproduced for specific applications.

    View record details
  • Optimality in combinations of confidence measures for stereo vision

    Haeusler, R; Klette, Reinhard (2012)

    Conference item
    The University of Auckland Library

    Confidence measures for stereo vision are already popular for some time. Yet, comprehensive results on their performance evaluation are rare. There is still not yet any agreement on answering the question 'what is a good confidence measure'. Very little work has been done for improving discriminativity by exploiting information from combinations of different confidence measures. We present a method to determine an upper bound for performance increase possible by combining given confidence measures. We also provide a solution for a fusion of measures resulting in improved confidence accuracy on popular stereo benchmark data.

    View record details
  • Disparity confidence measures on engineered and outdoor data

    Haeusler, R; Klette, Reinhard (2012)

    Conference item
    The University of Auckland Library

    Confidence measures for stereo analysis are not yet a subject of detailed comparative evaluations. There have been some studies, but still insufficient for estimating the performance of these measures. We comparatively discuss confidence measures whose performance appeared to be ‘promising’ to us, by evaluating their performance on commonly used stereo test data. Those data are either engineered and come with accurate ground truth (for disparities), or they are recorded outdoors and come with approximate ground truth. The performance of confidence measures varies widely between these two types of data. We propose modifications of confidence measures which can improve their performance on outdoor data.

    View record details
  • Improved segmentation for footprint recognition of small mammals

    Shin, Bok Suk; Zheng, Y; Russell, James; Klette, Reinhard (2012)

    Conference item
    The University of Auckland Library

    In this paper we improve the automatic extraction of segments by resolving some of the issues for collected rat footprints, such as incomplete, fading, merged, or overlapping prints, or cuts due to the applied rectangular clipping process. First, binarization is by an adaptive method (proposed by Otsu) on the given input segment. Second, we remove small artefacts with a subsequent adaptive method. Third, merged regions are separated by a morphological method using an adaptive mask. Next, we find meaningful pads (central pad or toes) by analysing geometric relations defined by triangulation. Finally we reconstruct damaged footprints by using a convex-hull algorithm. We present experimental results of reconstructed footprints, and distributions of extracted features for improved segments. In the proposed technique, we automatically improve the quality and reliability of a scanned footprint image so as not to lose potential information for subsequent identification steps.

    View record details
  • Evaluation of Stereo Confidence Measures on Synthetic and Recorded Image Data

    Haeusler, Ralf; Klette, Reinhard (2012-01-01)

    Conference item
    The University of Auckland Library

    We comparatively discuss a set of confidence measures for stereo analysis by testing them on semi-global matching (SGM) cost functions. The aim is a prediction of (potentially) erroneous areas in calculated disparity maps. The evaluation is done by using the sparsification technique which provides more information than commonly used RMS or NCC measures. We also present an approach for combining different confidence measures. This allows us to perform a quantisation of confidence estimates in terms of disparity errors.

    View record details
  • Robustness of point feature detection

    Song, Z; Klette, Reinhard (2013)

    Conference item
    The University of Auckland Library

    This paper evaluates 2D feature detection methods with respect to invariance and efficiency properties. The studied feature detection methods are as follows: Speeded Up Robust Features, Scale Invariant Feature Transform, Binary Robust Invariant Scalable Keypoints, Oriented Binary Robust Independent Elementary Features, Features from Accelerated Segment Test, Maximally Stable Extremal Regions, Binary Robust Independent Elementary Features, and Fast Retina Keypoint. A long video sequence of traffic scenes is used for testing these feature detection methods. A brute-force matcher and Random Sample Consensus are used in order to analyse how robust these feature detection methods are with respect to scale, rotation, blurring, or brightness changes. After identifying matches in subsequent frames, RANSAC is used for removing inconsistent matches; remaining matches are taken as correct matches. This is the essence of our proposed evaluation technique. All the experiments use a proposed repeatability measure, defined as the ratio of the numbers of correct matches, and of all keypoints.

    View record details
  • Analysis of KITTI data for stereo analysis with stereo confidence measures

    Haeusler, R; Klette, Reinhard (2012)

    Conference item
    The University of Auckland Library

    The recently published KITTI stereo dataset provides a new quality of stereo imagery with partial ground truth for benchmarking stereo matchers. Our aim is to test the value of stereo confidence measures (e.g. a left-right consistency check of disparity maps, or an analysis of the slope of a local interpolation of the cost function at the taken minimum) when applied to recorded datasets, such as published with KITTI. We choose popular measures as available in the stereo-analysis literature, and discuss a naive combination of these. Evaluations are carried out using a sparsification strategy. While the best single confidence measure proved to be the right-left consistency check for high disparity map densities, the best overall performance is achieved with the proposed naive measure combination. We argue that there is still demand for more challenging datasets and more comprehensive ground truth.

    View record details
  • ADR shape descriptor – Distance between shape centroids versus shape diameter

    Klette, Reinhard; Žunić, Joviša (2012-06)

    Journal article
    The University of Auckland Library

    In this paper we study the ADR shape descriptor ρ(S), where ADR is short for “asymmetries in the distribution of roughness”. This descriptor was defined in 1998 as the ratio of the squared distance between two different shape centroids (namely of area and frontier) to the squared shape diameter. After known for more than ten years, the behavior of ρ(S) was not well understood till today, thus hindering its application. Two very basic questions remained unanswered so far: –What is the range for ρ(S), if S is any bounded compact shape? –How do shapes look like having a large ρ(S) value? This paper answers both questions. We show that ρ(S) ranges over the interval [0, 1). We show that the established upper bound 1 is the best possible by constructing shapes whose ρ(S) values are arbitrary close to 1. In experiments we provide examples to indicate the kind of shapes that have relatively large ρ(S) values.

    View record details
  • A new feature detector and stereo matching method for accurate high-performance sparse stereo matching

    Schauwecker, K; Klette, Reinhard; Zell, A (2012)

    Conference item
    The University of Auckland Library

    Hardware platforms with limited processing power are often incapable of running dense stereo analysis algorithms at acceptable speed. Sparse algorithms provide an alternative but generally lack in accuracy. To overcome this predicament, we present an efficient sparse stereo analysis algorithm that applies a dense consistency check, leading to accurate matching results. We further improve matching accuracy by introducing a new feature detector based on FAST, which exhibits a less clustered feature distribution. The new feature detector leads to a superior performance of our stereo analysis algorithm. Performance evaluation shows that the proposed stereo matching system achieves processing rates above 200 frames per second on a commodity dual core CPU, and faster than video frame-rate processing on a low-performance embedded platform. The stereo matching results prove to be superior to those obtained with ordinary sparse matching algorithms.

    View record details
  • 3D trajectory estimation of simulated fruit flies

    Tao, J; Risse, B; Jiang, X; Klette, Reinhard

    Conference item
    The University of Auckland Library

    This paper addresses 3D trajectory estimation of simulated fruit flies assuming a time-synchronized and calibrated 3-camera system. Because the objects have almost the same appearance, both stereo matching and temporal tracking are challenging. In this paper, a third camera is introduced to verify matching and tracking results based on epipolar geometry and projection consistency. This reduces the ambiguity, fetches missed matches and corrects incorrect matches during tracking. Since matching and tracking affect each other, we process both in interaction instead of separately. Unscented Kalman filters are adopted to track objects by modelling motion information, as no distinguishing appearance features are available.

    View record details
  • Analysis of a shape descriptor: Distance between two shape centroids versus shape diameter

    Žunić, J; Klette, Reinhard (2012)

    Conference item
    The University of Auckland Library

    In this paper we study a shape descriptor ρ(S) that is defined as the ratio of the squared distance between centroids and the squared diameter of shape S (i.e., a set in the plane). This descriptor has been discussed for more than ten years, but its behaviour is not yet well studied, thus hindering its wide-spread application. There are two open basic questions to be answered: 1. What is the range of ρ(S)? 2. How do shapes look like with large ρ(S) values? This paper answers both open questions. We show that ρ(S) values are in the interval [0; 1), meaning in particular that value 1 is not taken, that 1 is the best possible upper bound, and and we give examples of shapes whose ρ(S) values are arbitrarily close to 1.

    View record details