2,279 results for Report

  • Adaptive Mean Shift-Based Clustering

    Li, Fajie; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). This report proposes an adaptive mean shift clustering algo- rithm. Its application is demonstrated for simulated data, by nding old clusters which are highly overlapping. The obtained clustering result is actually close to an estimated upper bound, derived for those simulated data elsewhere.

    View record details
  • An Approach for Evaluating Robustness of Edge Operators on Real-World Driving Scenes

    Al-Sarraf, Ali; Vaudrey, Tobi; Klette, Reinhard; Woo, Young Woon (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). Over the past 20 years there have been many papers that compare and evaluate di erent edge operators. Most of them focus on accuracy and also do comparisons against synthetic data. This paper focuses on real-world driver assistance scenes and does a comparison based on robustness. The three edge operators compared are Sobel, Canny and the under-publicized phase-based Kovesi-Owens operator. The Kovesi- Owens operator has the distinct advantage that it uses one pre-selected set of parameters and can work across almost any type of scene, where as other operators require parameter tuning. The results from our comparison show that the Kovesi-Owens operator is the most robust of the three, and can get decent results, even under weak illumination and varying gradients in the images.

    View record details
  • Evaluation of Moving Object Segmentation Comparing 6D-Vision and Monocular Motion Constraints

    Vaudrey, Tobi; Wedel, Andreas; Rabe, Clemens; Klappstein, Jens; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). Detecting moving objects is a very important aspect of driver assistance systems (DAS). This paper handles this issue by using a vision based system mounted within the vehicle. The pipeline for both a stereoscopic and monocular approach are covered. Both approaches use image sequences and compare moving feature points over time. This sparse information is then segmented using the optimal graph-cut algorithm, by also incorporating the grey-scale images. This paper then evaluates and contrasts the two approaches to identify the accuracy and robustness of each approach. The two methods both work in real-time on normal PC hardware (Quad Core CPU).

    View record details
  • Fast Trilateral Filtering

    Vaudrey, Tobi; Klette, Reinhard (2009)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=127&Itemid=113 . All other rights are reserved by the author(s). This paper compares the original implementation of the trilateral filter with two proposed speed improvements. One is using simple look-up-tables, and leads to exactly the same results as the original filter. The other technique is using a novel way of truncating the look-up-table to a user specified required accuracy. Here, results differ from those of the original filter, but to a very minor extent. The paper shows that measured speed improvements of this second technique are in the order of several magnitudes, compared to the original or LUT trilateral filter.

    View record details
  • Tracking small artists

    Russell, James; Klette, Reinhard (2009)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=127&Itemid=113 . All other rights are reserved by the author(s). Tracks of small animals are important in environmental surveillance, where pattern recognition algorithms allow species identification of the individuals creating tracks. These individuals can also be seen as artists, presented in their natural environments with a canvas upon which they can make prints. We present tracks of small mammals and reptiles which have been collected for identification purposes, and reinterpret them from an esthetic point of view. We re-classify these tracks not by their geometric qualities as pattern recognition algorithms would, but through interpreting the `artist', their brush strokes and intensity. We describe the algorithms used to enhance and present the work of the `artists'.

    View record details
  • Improving Optical Flow using Residual Images

    Vaudrey, Tobi; Wedel, Andreas; Klette, Reinhard (2009)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=127&Itemid=113 . All other rights are reserved by the author(s). Optical flow is a highly researched area in low-level computer vision. It is a complex problem which tries to solve a 2D search in continuous space, while the input data is 2D discrete data. The major assumption in most optical flow applications is the intensity consistency assumption, introduced by Horn and Schunck. This constraint is often violated in practice. This paper proposes and generalises one such approach; using residual images (high-frequencies) of images, to remove the illumination differences between corresponding images.

    View record details
  • Belief Propagation for Stereo Analysis of Night-Vision Sequences

    Guan, Shushi; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original CITR web site; http://citr.auckland.ac.nz/techreports/ under terms that include this permission. All other rights are reserved by the author(s). This paper studies different specifications of belief propagation for stereo analysis of seven rectified stereo night-vision sequences (provided by Daimler AG). As it was shown earlier by the authors, Sobel preprocessing of images had obvious impacts on improving disparity calculations. This paper also considers other options of preprocessing (Canny and Kovesi-Owens edge operators), and concludes with a recommended setting for belief propagation on those sequences.

    View record details
  • Space-Time Multi-Resolution Banded Graph-Cut for Fast Segmentation. (Technical Report)

    Vaudrey, Tobi; Gruber, Daniel; Wedel, Andreas; Klappstein, Jens (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). Applying real-time segmentation is a major issue when processing every frame of image sequences. In this paper, we propose a modi cation of the well known graph-cut algorithm to improve speed for discrete segmentation. Our algorithm yields real-time segmentation, using graph-cut, by performing a single cut on an image with regions of di erent resolutions, combining space-time pyramids and narrow bands. This is especially suitable for image sequences, as segment borders in one image are re ned in the next image. The fast computation time allows one to use information contained in every image frame of an input image stream at 20 Hz, on a standard PC. The algorithm is applied to traf- c scenes, using a monocular camera installed in a moving vehicle. Our results show the segmentation of moving objects with similar results to standard graph-cut, but with improved speed.

    View record details
  • Efficient Dense Scene Flow from Sparse or Dense Stereo Data

    Wedel, Andreas; Rabe, Clemens; Vaudrey, Tobi; Brox, Thomas; Cremers, Daniel (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). This paper presents a technique for estimating the threedimensional velocity vector field that describes the motion of each visible scene point (scene flow). The technique presented uses two consecutive image pairs from a stereo sequence. The main contribution is to decouple the position and velocity estimation steps, and to estimate dense velocities using a variational approach. We enforce the scene flow to yield consistent displacement vectors in the left and right images. The decoupling strategy has two main advantages: Firstly, we are independent in choosing a disparity estimation technique, which can yield either sparse or dense correspondences, and secondly, we can achieve frame rates of 5 fps on standard consumer hardware. The approach provides dense velocity estimates with accurate results at distances up to 50 meters.

    View record details
  • Recovery Rate of Clustering Algorithms. (2008)

    Li, Fajie; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). This article provides a simple and general way for de ning the recovery rate of clustering algorithms using a given family of old clusters for evaluating the performance of the algorithm when calculating a family of new clusters. Under the assumption of dealing with simulated data (i.e., known old clusters), the recovery rate is calculated using one proposed exact (but slow) algorithm, or one proposed approximate algorithm (with feasible run time).

    View record details
  • Stereo-Vision-Support for Intelligent Vehicles - The Need for Quantified Evidence

    Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). Vision-based driver assistance in modern cars has to perform automated real-time understanding or modeling of tra c environments based on multiple sensor inputs, using `normal' or specialized (such as night vision) stereo cameras as default input devices. Distance measurement, lane-departure warning, tra c sign recognition, or trajectory calculation are examples of current developments in the eld, contributing to the design of intelligent vehicles. The considered application scenario is as follows: two or more cameras are installed in a vehicle (typically a car, but possibly also a boat, a wheelchair, a forklift, and so forth), and the operation of this vehicle (by a driver) is supported by analyzing in real-time video sequences recorded by those cameras. Possibly, further sensor data (e.g., GPS, radar) are also analyzed in an integrated system. Performance evaluation is of eminent importance in car production. Crash tests follow international standards, de ning exactly conditions under which a test has to take place. Camera technology became recently an integral part of modern cars. In consequence, perfectly speci ed and standardized tests (`camera crash tests') are needed very soon for the international car industry to identify parameters of stereo or motion analysis, or of further vision-based components. This paper reports about current performance evaluation activities in the .enpeda.. project at The University of Auckland. Test data are so far recti ed stereo sequences (provided by Daimler A.G., Germany, in 2007), and stereo sequences recorded with a test vehicle on New Zealand's roads.

    View record details
  • Moving Object Segmentation using Optical Flow and Depth Information

    Klappstein, Jens; Vaudrey, Tobi; Rabe, Clemens; Wedel, Andreas; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). This paper discusses the detection of moving objects (being a crucial part of driver assistance systems) using monocular or stereo- scopic computer vision. In both cases, object detection is based on motion analysis of individually tracked image points (optical ow), providing a motion metric which corresponds to the likelihood that the tracked point is moving. Based on this metric, points are segmented into objects by employing a globally optimal graph-cut algorithm. Both approaches are comparatively evaluated using real-world vehicle image sequences.

    View record details
  • Fractal Art based on "The Butterfly Effect" of Chaos Theory

    Chang, Yin-Wei; Huang, Fay (2009)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=127&Itemid=113 . All other rights are reserved by the author(s). This paper proposes and demonstrates a new integration of the theory of fractals and the butterfly effect of chaos theory. They both have long histories in creating digital artworks, but besides of many existing fractal software programs, none of them allowed us to achieve the proposed integration. Moreover, our program is the first to provide the functional concepts of overlapping results and sequential transformations, which allow us to generate a wider variety of patterns. Our program not only has the potential of creating 2D digital artworks but also supports the creation of animated abstract artworks.

    View record details
  • Monocular 3D Reconstruction of Objects Based on Cylindrical Panoramas

    Haeusler, Ralf; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). This paper discusses ways of using a single panoramic image (captured by a rotating sensor-line camera having very-high spatial resolution) for the geometric shape recovery of a shown object. The objective is to create a sparse polyhedral model, only allowing a few interactive user inputs for a given single panoramic image. The study was motivated by the general question whether a single panoramic image projection allows some kind of 3D shape recovery, possibly bene tting from available monocular approaches for standard (say, pinhole-type) camera models.

    View record details
  • Effective Feature Extraction by Trace Transform for Insect Footprint Recognition

    Shin, Bok-Suk; Cha, Eui-Young; Cho, Kyoung-Won; Klette, Reinhard; Woo, Young Woon (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). The report discusses insect footprint recognition. Footprint segments are extracted from scanned footprints, and appropriate features are calculated for those segments (or cluster of segments) in order to discriminate species of insects. The selection or identification of such features is crucial for this classification process.

    View record details
  • Performance Evaluation of Stereo and Motion Analysis on Rectified Image Sequences

    Liu, Zhifeng (2007)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). This paper introduces into seven real-world road driving stereo sequences (provided by Daimler AG, Germany; now freely available for academic research); it also informs about their use for performance evaluation in some experiments using common stereo and motion analysis algorithms. Often, such algorithms are tested on a few frames only, or on synthetic sequences, but not on long real-world sequences. The provided sequences have 250 to 300 stereo pairs each; they have been used at Daimler AG for testing 6D vision, which fuses disparity and motion data (by using a Kalman filter). In this paper we introduce into those seven sequences (and inform about the download web site); we discuss a few approaches how to use those sequences for testing either stereo or motion algorithms, or both combined together. Certainly, those sequences do have many more potentials for future performance evaluations for stereo and motion analysis algorithms.

    View record details
  • The Topology of Incidence Pseudographs

    James, Thomas R; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). An incidence pseudograph models a (re exive and symmetric) incidence relation between sets of various dimensions, contained in a countable family. Work by Klaus Voss in 1993 suggested that this general discrete model allows to introduce a topol- ogy, and some authors have done some studies into this direction in the past. This paper provides a comprehensive overview about the topology of incidence pseudo- graphs. This topology has various applications, such as in modeling basic data in 2D or 3D digital picture analysis. This paper addresses especially also partially open sets which occur in common (non-binary) picture analysis.

    View record details
  • Approximate Shortest Path Calculations in Simple Polyhedra

    Li, Fajie; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). This paper considers the calculation of a Euclidean shortest path (ESP) in a three-dimenisonal (3D) polyhedral space II. We propose an approximate K(E).O(M|V|) 3D ESP algorithm (excluding preprocessing), with preprocessing time complexity O(M|E| + |S| + |V| log |V|) for solving a special, but `fairly general' case of the 3D ESP problem, where does not need to be convex, V and E are the sets of vertices and edges of , respectively, and S is the set of faces (triangles) of II; M is the maximal number of vertices of a so-called critical polygon; K(E)=(Lo-L)/E where Lo is the length of the 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 K(E).O(k) where k is the number of layers in a stack, which is introduced in this paper as the problem environment. The proposed approximation method is only an example of a general technique, for which the authors also see further potentials to support e cient approximate solutions for more general 3D ESP problems.

    View record details
  • Approximate Algorithms for Touring a Sequence of Polygons

    Li, Fajie; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). Given two points p and q and a nite number of simple poly- gons in a plane. The basic version of a touring-a-sequence-of-polygons problem (in brief: a touring polygons problem, TPP) is how to nd a shortest path such that it starts at p, then it visits these polygons in the given order, and nally it ends at q. This paper describes approximate algorithms for di erent versions of touring polygons problems. Among its important results it provides, for example, an answer to the previ- ously open problem \What is the complexity of the touring polygons problem for pairwise disjoint nonconvex simple polygons?" by providing a (")-linear approximate algorithm for solving this problem, with (") = (L0 􀀀 L1)=" where L0 is the length of the initial path and L is the true (i.e., optimum) path length. As a further example, this paper nds an approximate so- lution to the unconstrained touring polygons problem which is known to be NP-hard.

    View record details
  • Dynamic Programming Stereo on Real-World Sequences

    Liu, Zhifeng; Klette, Reinhard (2008)

    Report
    The University of Auckland Library

    You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the original MI_tech website http://www.mi.auckland.ac.nz/index.php?option=com_content&view=article&id=91&Itemid=76 . All other rights are reserved by the author(s). This paper proposes a way to approximate ground truth for real-world stereo sequences, and applies this for evaluating the performance of di erent variants of dynamic programming stereo analysis. This illustrates a way of performance evaluation, also allowing to derive sequence analysis diagrams. Obtained results di er from those obtained for the discussed algorithms on smaller, or engineered test data. This also shows the value of real-world testing.

    View record details