Results 1  10
of
28
Learning to detect natural image boundaries using local brightness, color, and texture cues
 PAMI
, 2004
"... Abstract—The goal of this work is to accurately detect and localize boundaries in natural scenes using local image measurements. We formulate features that respond to characteristic changes in brightness, color, and texture associated with natural boundaries. In order to combine the information from ..."
Abstract

Cited by 407 (16 self)
 Add to MetaCart
Abstract—The goal of this work is to accurately detect and localize boundaries in natural scenes using local image measurements. We formulate features that respond to characteristic changes in brightness, color, and texture associated with natural boundaries. In order to combine the information from these features in an optimal way, we train a classifier using human labeled images as ground truth. The output of this classifier provides the posterior probability of a boundary at each image location and orientation. We present precisionrecall curves showing that the resulting detector significantly outperforms existing approaches. Our two main results are 1) that cue combination can be performed adequately with a simple linear model and 2) that a proper, explicit treatment of texture is required to detect boundaries in natural images. Index Terms—Texture, supervised learning, cue combination, natural images, ground truth segmentation data set, boundary detection, boundary localization. 1
Mobile Robot Localisation and Mapping in Extensive Outdoor Environments
, 2002
"... This thesis addresses the issues of scale for practical implementations of simultaneous localisation and mapping (SLAM) in extensive outdoor environments. Building an incremental map while also using it for localisation is of prime importance for mobile robot navigation but, until recently, has bee ..."
Abstract

Cited by 47 (3 self)
 Add to MetaCart
This thesis addresses the issues of scale for practical implementations of simultaneous localisation and mapping (SLAM) in extensive outdoor environments. Building an incremental map while also using it for localisation is of prime importance for mobile robot navigation but, until recently, has been confined to smallscale, mostly indoor, environments. The critical problems for largescale implementations are as follows. First, data association finding correspondences between map landmarks and robot sensor measurementsbecomes difficult in complex, cluttered environments, especially if the robot location is uncertain. Second, the information required to maintain a consistent map using traditional methods imposes a prohibitive computational burden as the map increases in size. And third, the mathematics for SLAM relies on assumptions of small errors and nearlinearity, and these become invalid for larger maps.
Linear Assignment Problems and Extensions
"... This paper aims at describing the state of the art on linear assignment problems (LAPs). Besides sum LAPs it discusses also problems with other objective functions like the bottleneck LAP, the lexicographic LAP, and the more general algebraic LAP. We consider different aspects of assignment problems ..."
Abstract

Cited by 41 (0 self)
 Add to MetaCart
This paper aims at describing the state of the art on linear assignment problems (LAPs). Besides sum LAPs it discusses also problems with other objective functions like the bottleneck LAP, the lexicographic LAP, and the more general algebraic LAP. We consider different aspects of assignment problems, starting with the assignment polytope and the relationship between assignment and matching problems, and focusing then on deterministic and randomized algorithms, parallel approaches, and the asymptotic behaviour. Further, we describe different applications of assignment problems, ranging from the well know personnel assignment or assignment of jobs to parallel machines, to less known applications, e.g. tracking of moving objects in the space. Finally, planar and axial threedimensional assignment problems are considered, and polyhedral results, as well as algorithms for these problems or their special cases are discussed. The paper will appear in the Handbook of Combinatorial Optimization to be published
Semimatchings for bipartite graphs and load balancing
 In Proc. 8th WADS
, 2003
"... We consider the problem of fairly matching the lefthand vertices of a bipartite graph to the righthand vertices. We refer to this problem as the optimal semimatching problem; it is a relaxation of the known bipartite matching problem. We present a way to evaluate the quality of a given semimatchi ..."
Abstract

Cited by 13 (0 self)
 Add to MetaCart
We consider the problem of fairly matching the lefthand vertices of a bipartite graph to the righthand vertices. We refer to this problem as the optimal semimatching problem; it is a relaxation of the known bipartite matching problem. We present a way to evaluate the quality of a given semimatching and show that, under this measure, an optimal semimatching balances the load on the right hand vertices with respect to any Lpnorm. In particular, when modeling a job assignment system, an optimal semimatching achieves the minimal makespan and the minimal flow time for the system. The problem of finding optimal semimatchings is a special case of certain scheduling problems for which known solutions exist. However, these known solutions are based on general network optimization algorithms, and are not the most efficient way to solve the optimal semimatching problem. To compute optimal semimatchings efficiently, we present and analyze two new algorithms. The first algorithm generalizes the Hungarian method for computing maximum bipartite matchings, while the second, more efficient algorithm is based on a new notion of costreducing paths. Our experimental results demonstrate that the second algorithm is vastly superior to using known network optimization algorithms to solve the optimal semimatching problem. Furthermore, this same algorithm can also be used to find maximum bipartite matchings and is shown to be roughly as efficient as the best known algorithms for this goal. Key words: bipartite graphs, loadbalancing, matching algorithms, optimal algorithms, semimatching
Fast Multiple Shape Correspondence by PreOrganizing Shape Instances
"... Accurately identifying corresponded landmarks from a population of shape instances is the major challenge in constructing statistical shape models. In general, shapecorrespondence methods can be grouped into one of two categories: global methods and pairwise methods. In this paper, we develop a new ..."
Abstract

Cited by 11 (1 self)
 Add to MetaCart
Accurately identifying corresponded landmarks from a population of shape instances is the major challenge in constructing statistical shape models. In general, shapecorrespondence methods can be grouped into one of two categories: global methods and pairwise methods. In this paper, we develop a new method that attempts to address the limitations of both the global and pairwise methods. In particular, we reorganize the input population into a tree structure that incorporates global information about the population of shape instances, where each node in the tree represents a shape instance and each edge connects two very similar shape instances. Using this organized tree, neighboring shape instances can be corresponded efficiently and accurately by a pairwise method. In the experiments, we evaluate the proposed method and compare its performance to five available shape correspondence methods and show the proposed method achieves the accuracy of a global method with speed of a pairwise method. 1.
Implications Of AreaArray I/o For RowBased Placement Methodology
 in IC/Package Design Integration, IEEE Symposium on, pp. 93 – 98
, 1998
"... We empirically study the implications of areaarray I/O for placement methodology. Our work develops a threeaxis testbed that examines (1) I/O regime (areaarray vs. peripheral pad locations), (2) I/O and core placement methodology (variants of alternating vs. simultaneous I/O and core placement ap ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
We empirically study the implications of areaarray I/O for placement methodology. Our work develops a threeaxis testbed that examines (1) I/O regime (areaarray vs. peripheral pad locations), (2) I/O and core placement methodology (variants of alternating vs. simultaneous I/O and core placement approaches), and (3) placement engine (hierarchical quadratic for both core and I/O cells vs. pure mincut for core cells and assignment for I/O). Experimental data show that the areaarray I/O regime is somewhat "more forgiving " of bad placement methodologies than the peripheral I/O regime. On the other hand, the wrong methodology can still entail substantial losses in solution quality and efficiency. Last, we hypothesize that reductions of onchip wirelength from adopting the areaarray I/O regime may be correlated with topological depth of circuits. 1. INTRODUCTION IC packaging technologies with peripheral I/O pads have wellknown shortcomings. Observed system Rent parameters suggest tha...
Permutation invariant svms
 In International Conference on Machine Learning, ICML
, 2006
"... We extend Support Vector Machines to input spaces that are sets by ensuring that the classifier is invariant to permutations of subelements within each input. Such permutations include reordering of scalars in an input vector, reorderings of tuples in an input matrix or reorderings of general obje ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
We extend Support Vector Machines to input spaces that are sets by ensuring that the classifier is invariant to permutations of subelements within each input. Such permutations include reordering of scalars in an input vector, reorderings of tuples in an input matrix or reorderings of general objects (in Hilbert spaces) within a set as well. This approach induces permutational invariance in the classifier which can then be directly applied to unusual setbased representations of data. The permutation invariant Support Vector Machine alternates the Hungarian method for maximum weight matching within the maximum margin learning procedure. We effectively estimate and apply permutations to the input data points to maximize classification margin while minimizing data radius. This procedure has a strong theoretical justification via well established error probability bounds. Experiments are shown on character recognition, 3D object recognition and various UCI datasets.
Evaluating shape correspondence for statistical shape analysis: A benchmark study
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2008
"... This paper introduces a new benchmark study to evaluate the performance of landmarkbased shape correspondence used for statistical shape analysis. Different from previous shapecorrespondence evaluation methods, the proposed benchmark first generates a large set of synthetic shape instances by ran ..."
Abstract

Cited by 5 (3 self)
 Add to MetaCart
This paper introduces a new benchmark study to evaluate the performance of landmarkbased shape correspondence used for statistical shape analysis. Different from previous shapecorrespondence evaluation methods, the proposed benchmark first generates a large set of synthetic shape instances by randomly sampling a given statistical shape model that defines a groundtruth shape space. We then run a test shapecorrespondence algorithm on these synthetic shape instances to identify a set of corresponded landmarks. According to the identified corresponded landmarks, we construct a new statistical shape model which defines a new shape space. We finally compare this new shape space against the groundtruth shape space to determine the performance of the test shapecorrespondence algorithm. In this paper, we introduce three new performance measures that are landmark independent to quantify the difference between the groundtruth and the newly derived shape spaces. By introducing a groundtruth shape space that is defined by a statistical shape model and three new landmarkindependent performance measures, we believe the proposed benchmark allows for a more objective evaluation of shape correspondence than previous methods. In this paper, we focus on developing the proposed benchmark for 2D shape correspondence. However, it can easily be extended to 3D cases.
Continuous Spatial Assignment of Moving Users
, 2008
"... Consider a large set of wireless access points owned by a company, which are scattered in a city. Each access point has a coverage region (i.e., an area it can transmit/receive data in) and a capacity (i.e., a maximum number of users it can serve). The company maintains a central coordinator, which ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
Consider a large set of wireless access points owned by a company, which are scattered in a city. Each access point has a coverage region (i.e., an area it can transmit/receive data in) and a capacity (i.e., a maximum number of users it can serve). The company maintains a central coordinator, which assigns every user to one access point subject to the coverage and capacity constraints. To offer the highest quality of service (e.g., signal strength), the company wishes to minimize the average distance between users and their assigned access point. This is an instance of a wellstudied problem in operations research, termed optimal assignment. Even though there exist several solutions for the static case (where user locations are fixed), there is currently no method for dynamic settings. In this paper, we consider the continuous assignment problem (CAP), where an optimal assignment must be constantly maintained between mobile users and a set of servers (e.g., access points). The fact that users are mobile necessitates realtime reassignment so that the quality of service remains high. The large scale and the timecritical nature of targeted applications require fast CAP solutions. We propose an algorithm that utilizes the geometric characteristics of the problem and significantly accelerates the initial assignment computation and its subsequent maintenance. Our method applies to different cost functions (e.g., average squared distance) and to any Minkowski distance metric (e.g., Euclidean, L1 norm, etc).