Interocular suppression is gated by interocular feature matching

We present a new form of contrast masking in which the target is a patch of low spatial frequency grating (0.46 c/deg) and the mask is a dark thin ring that surrounds the centre of the target patch. In matching and detection experiments we found little or no effect for binocular presentation of mask and test stimuli. But when mask and test were presented briefly (33 or 200 ms) to different eyes (dichoptic presentation), masking was substantial. In a 'half-binocular' condition the test stimulus was presented to one eye, but the mask stimulus was presented to both eyes with zero-disparity. This produced masking effects intermediate to those found in dichoptic and full-binocular conditions. We suggest that interocular feature matching can attenuate the potency of interocular suppression, but unlike in previous work (McKee, S. P., Bravo, M. J., Taylor, D. G., & Legge, G. E. (1994) Stereo matching precedes dichoptic masking. Vision Research, 34, 1047) we do not invoke a special role for depth perception. © 2004 Elsevier Ltd. All rights reserved.

Sistema di visione stereo su architettura ZYNQ

Lo scopo della tesi è creare un’architettura in FPGA in grado di ricavare informazioni 3D da una coppia di sensori stereo. La pipeline è stata realizzata utilizzando il System-on-Chip Zynq, che permette una stretta interazione tra la parte hardware realizzata in FPGA e la CPU. Dopo uno studio preliminare degli strumenti hardware e software, è stata realizzata l’architettura base per la scrittura e la lettura di immagini nella memoria DDR dello Zynq. In seguito l’attenzione si è spostata sull’implementazione di algoritmi stereo (rettificazione e stereo matching) su FPGA e nella realizzazione di una pipeline in grado di ricavare accurate mappe di disparità in tempo reale acquisendo le immagini da una camera stereo.

Evaluation of aerial remote sensing techniques for vegetation management in power line corridors

The following paper presents an evaluation of airborne sensors for use in vegetation management in powerline corridors. Three integral stages in the management process are addressed including, the detection of trees, relative positioning with respect to the nearest powerline and vegetation height estimation. Image data, including multi-spectral and high resolution, are analyzed along with LiDAR data captured from fixed wing aircraft. Ground truth data is then used to establish the accuracy and reliability of each sensor thus providing a quantitative comparison of sensor options. Tree detection was achieved through crown delineation using a Pulse-Coupled Neural Network (PCNN) and morphologic reconstruction applied to multi-spectral imagery. Through testing it was shown to achieve a detection rate of 96%, while the accuracy in segmenting groups of trees and single trees correctly was shown to be 75%. Relative positioning using LiDAR achieved a RMSE of 1.4m and 2.1m for cross track distance and along track position respectively, while Direct Georeferencing achieved RMSE of 3.1m in both instances. The estimation of pole and tree heights measured with LiDAR had a RMSE of 0.4m and 0.9m respectively, while Stereo Matching achieved 1.5m and 2.9m. Overall a small number of poles were missed with detection rates of 98% and 95% for LiDAR and Stereo Matching.

Understanding the fabric of social interactions for ridesharing through mining social networking sites

The design of applications for dynamic ridesharing or carpooling is often formulated as a matching problem of connecting people with an aligned set of transport needs within a reasonable interval of time and space. This problem formulation relegates social connections to being secondary factors. Technology assisted ridesharing applications that put the matching problem first have revealed that they suffer from being unable to address the factor of social comfort, even after adding friend features or piggybacking on social networking sites. This research aims to understand the fabric of social interactions through which ridesharing happens. We take an online observation approach in order to understand the fabric of social interactions for ridesharing that is happening in highly subscribed online groups of local residents. This understanding will help researchers to identify design challenges and opportunities to support ridesharing in local communities. This paper contributes a fundamental understanding of how social interactions and social comfort precede rideshare requests in local communities.

Novelty-based visual obstacle detection in agriculture

This paper describes a novel obstacle detection system for autonomous robots in agricultural field environments that uses a novelty detector to inform stereo matching. Stereo vision alone erroneously detects obstacles in environments with ambiguous appearance and ground plane such as in broad-acre crop fields with harvested crop residue. The novelty detector estimates the probability density in image descriptor space and incorporates image-space positional understanding to identify potential regions for obstacle detection using dense stereo matching. The results demonstrate that the system is able to detect obstacles typical to a farm at day and night. This system was successfully used as the sole means of obstacle detection for an autonomous robot performing a long term two hour coverage task travelling 8.5 km.

Popular Mixed Matchings

We study the problem of matching applicants to jobs under one-sided preferences: that is, each applicant ranks a non-empty subset of jobs under an order of preference, possibly involving ties. A matching M is said to be rnore popular than T if the applicants that prefer M to T outnumber those that prefer T to M. A matching is said to be popular if there is no matching more popular than it. Equivalently, a matching M is popular if phi(M,T) >= phi(T, M) for all matchings T, where phi(X, Y) is the number of applicants that prefer X to Y. Previously studied solution concepts based oil the popularity criterion are either not guaranteed to exist for every instance (e.g., popular matchings) or are NP-hard to compute (e.g., least unpopular matchings). This paper addresses this issue by considering mixed matchings. A mixed matching is simply a probability distributions over matchings in the input graph. The function phi that compares two matchings generalizes in a natural manner to mixed matchings by taking expectation. A mixed matching P is popular if phi(P,Q) >= phi(Q,P) for all mixed matchings Q. We show that popular mixed matchings always exist. and we design polynomial time algorithms for finding them. Then we study their efficiency and give tight bounds on the price of anarchy and price of stability of the popular matching problem.

Voting Paths

We consider a variant of the popular matching problem here. The input instance is a bipartite graph $G=(\mathcal{A}\cup\mathcal{P},E)$, where vertices in $\mathcal{A}$ are called applicants and vertices in $\mathcal{P}$ are called posts. Each applicant ranks a subset of posts in an order of preference, possibly involving ties. A matching $M$ is popular if there is no other matching $M'$ such that the number of applicants who prefer their partners in $M'$ to $M$ exceeds the number of applicants who prefer their partners in $M$ to $M'$. However, the “more popular than” relation is not transitive; hence this relation is not a partial order, and thus there need not be a maximal element here. Indeed, there are simple instances that do not admit popular matchings. The questions of whether an input instance $G$ admits a popular matching and how to compute one if it exists were studied earlier by Abraham et al. Here we study reachability questions among matchings in $G$, assuming that $G=(\mathcal{A}\cup\mathcal{P},E)$ admits a popular matching. A matching $M_k$ is reachable from $M_0$ if there is a sequence of matchings $\langle M_0,M_1,\dots,M_k\rangle$ such that each matching is more popular than its predecessor. Such a sequence is called a length-$k$ voting path from $M_0$ to $M_k$. We show an interesting property of reachability among matchings in $G$: there is always a voting path of length at most 2 from any matching to some popular matching. Given a bipartite graph $G=(\mathcal{A}\cup\mathcal{P},E)$ with $n$ vertices and $m$ edges and any matching $M_0$ in $G$, we give an $O(m\sqrt{n})$ algorithm to compute a shortest-length voting path from $M_0$ to a popular matching; when preference lists are strictly ordered, we have an $O(m+n)$ algorithm. This problem has applications in dynamic matching markets, where applicants and posts can enter and leave the market, and applicants can also change their preferences arbitrarily. After any change, the current matching may no longer be popular, in which case we are required to update it. However, our model demands that we switch from one matching to another only if there is consensus among the applicants to agree to the switch. Hence we need to update via a voting path that ends in a popular matching. Thus our algorithm has applications here.

An SIMD machine for low-level vision

This paper presents an SIMD machine which has been tuned to execute low-level vision algorithms employing the relaxation labeling paradigm. Novel features of the design include: 1. (1) a communication scheme capable of window accessing under a single instruction. 2. (2) flexible I/O instructions to load overlapped data segments; and 3. (3) data-conditional instructions which can be nested to an arbitrary degree. A time analysis of the stereo correspondence problem, as implemented on a simulated version of the machine using the probabilistic relaxation technique, shows a speed up of almost N2 for an N × N array of PEs.

Exact bounds for distributed graph colouring

A distributed system is a collection of networked autonomous processing units which must work in a cooperative manner. Currently, large-scale distributed systems, such as various telecommunication and computer networks, are abundant and used in a multitude of tasks. The field of distributed computing studies what can be computed efficiently in such systems. Distributed systems are usually modelled as graphs where nodes represent the processors and edges denote communication links between processors. This thesis concentrates on the computational complexity of the distributed graph colouring problem. The objective of the graph colouring problem is to assign a colour to each node in such a way that no two nodes connected by an edge share the same colour. In particular, it is often desirable to use only a small number of colours. This task is a fundamental symmetry-breaking primitive in various distributed algorithms. A graph that has been coloured in this manner using at most k different colours is said to be k-coloured. This work examines the synchronous message-passing model of distributed computation: every node runs the same algorithm, and the system operates in discrete synchronous communication rounds. During each round, a node can communicate with its neighbours and perform local computation. In this model, the time complexity of a problem is the number of synchronous communication rounds required to solve the problem. It is known that 3-colouring any k-coloured directed cycle requires at least ½(log* k - 3) communication rounds and is possible in ½(log* k + 7) communication rounds for all k ≥ 3. This work shows that for any k ≥ 3, colouring a k-coloured directed cycle with at most three colours is possible in ½(log* k + 3) rounds. In contrast, it is also shown that for some values of k, colouring a directed cycle with at most three colours requires at least ½(log* k + 1) communication rounds. Furthermore, in the case of directed rooted trees, reducing a k-colouring into a 3-colouring requires at least log* k + 1 rounds for some k and possible in log* k + 3 rounds for all k ≥ 3. The new positive and negative results are derived using computational methods, as the existence of distributed colouring algorithms corresponds to the colourability of so-called neighbourhood graphs. The colourability of these graphs is analysed using Boolean satisfiability (SAT) solvers. Finally, this thesis shows that similar methods are applicable in capturing the existence of distributed algorithms for other graph problems, such as the maximal matching problem.

Popular mixed matchings

We study the problem of matching applicants to jobs under one-sided preferences; that is, each applicant ranks a non-empty subset of jobs under an order of preference, possibly involving ties. A matching M is said to be more popular than T if the applicants that prefer M to T outnumber those that prefer T to M. A matching is said to be popular if there is no matching more popular than it. Equivalently, a matching M is popular if phi(M, T) >= phi(T, M) for all matchings T, where phi(X, Y) is the number of applicants that prefer X to Y. Previously studied solution concepts based on the popularity criterion are either not guaranteed to exist for every instance (e.g., popular matchings) or are NP-hard to compute (e.g., least unpopular matchings). This paper addresses this issue by considering mixed matchings. A mixed matching is simply a probability distribution over matchings in the input graph. The function phi that compares two matchings generalizes in a natural manner to mixed matchings by taking expectation. A mixed matching P is popular if phi(P, Q) >= phi(Q, P) for all mixed matchings Q. We show that popular mixed matchings always exist and we design polynomial time algorithms for finding them. Then we study their efficiency and give tight bounds on the price of anarchy and price of stability of the popular matching problem. (C) 2010 Elsevier B.V. All rights reserved.

A Simple Label Switching Algorithm for Semisupervised Structural SVMs

In structured output learning, obtaining labeled data for real-world applications is usually costly, while unlabeled examples are available in abundance. Semisupervised structured classification deals with a small number of labeled examples and a large number of unlabeled structured data. In this work, we consider semisupervised structural support vector machines with domain constraints. The optimization problem, which in general is not convex, contains the loss terms associated with the labeled and unlabeled examples, along with the domain constraints. We propose a simple optimization approach that alternates between solving a supervised learning problem and a constraint matching problem. Solving the constraint matching problem is difficult for structured prediction, and we propose an efficient and effective label switching method to solve it. The alternating optimization is carried out within a deterministic annealing framework, which helps in effective constraint matching and avoiding poor local minima, which are not very useful. The algorithm is simple and easy to implement. Further, it is suitable for any structured output learning problem where exact inference is available. Experiments on benchmark sequence labeling data sets and a natural language parsing data set show that the proposed approach, though simple, achieves comparable generalization performance.

Low Resolution Face Recognition Across Variations in Pose and Illumination

We propose a completely automatic approach for recognizing low resolution face images captured in uncontrolled environment. The approach uses multidimensional scaling to learn a common transformation matrix for the entire face which simultaneously transforms the facial features of the low resolution and the high resolution training images such that the distance between them approximates the distance had both the images been captured under the same controlled imaging conditions. Stereo matching cost is used to obtain the similarity of two images in the transformed space. Though this gives very good recognition performance, the time taken for computing the stereo matching cost is significant. To overcome this limitation, we propose a reference-based approach in which each face image is represented by its stereo matching cost from a few reference images. Experimental evaluation on the real world challenging databases and comparison with the state-of-the-art super-resolution, classifier based and cross modal synthesis techniques show the effectiveness of the proposed algorithm.

基于线性不变矩和角度向量的立体匹配算法

针对室内场景双目立体匹配有别于一般场景立体匹配的特殊性,提出了一种计算简便、准确度高的立体图像匹配算法。该算法首先利用canny算子检测物体的边缘,根据边缘的线性不变矩寻找出目标物体,然后提取出目标物体轮廓的特征点,利用角度直方图计算出左右图像的旋转角度,最后利用角度向量实现左右图像的对应像素点的匹配。线性不变矩有效地将计算复杂度由二维降低到一维,大大降低了计算量。角度向量的提出降低了特征点匹配的复杂度,而且计算简便,准确率高。实验表明,该算法对图像的缩放、旋转、平移均免疫,具有较高的识别精度和良好的抗干扰性,计算效率高于传统方法,有着较高的应用价值。

基于外极线分区的动态立体匹配算法

基于区域的立体匹配算法仅针对支撑窗内的灰度信息定义匹配代价函数,导致在弱(无)纹理区域采用WTA优化出现歧义性。该文在外极线分区的基础上,改用区域作为匹配基元,针对歧义性区域,在代价函数中引入遮挡项和平滑项,并按照区域优先级的高低,动态匹配相应区域,获得可靠的视差信息。实验证明,该算法在保持实时性的同时对弱纹理区域处理具有有效性。

基于点集曲面投影算法的自由曲面匹配

测量数据的精确定位是实现复杂曲面加工检测的关键,针对测量点云数据与NURBS表示的CAD自由曲面模型匹配中求最近点计算方面存在的问题,提出了一种简单、有效的寻找最近点的方法。该方法与由测量点集评估给定曲面上的最近点的传统算法相反,采用点集曲面(point set surface,PSS)投影算法,对给定自由曲面模型上有限个点与不附加任何几何和拓扑信息的散乱点集之间进行粗匹配获得初始位置,进而以最近点迭代算法(ICP)完成测量数据定位的精确调整,达到全局及局部最优的目标。实验结果表明,采用PSS投影算法法寻找最近点不仅效率高,而且能得到全局匹配结果,可以为精匹配提供较好的计算初值,减少了ICP算法进行二次匹配时,迭代次数及执行时间并且精度得到了较大提高。