Showing papers on "Bounding overwatch published in 2015"

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Abstract: Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the performance of deep networks that usually benefit from more training data. In this paper, we propose a method that achieves competitive accuracy but only requires easily obtained bounding box annotations. The basic idea is to iterate between automatically generating region proposals and training convolutional networks. These two steps gradually recover segmentation masks for improving the networks, and vise versa. Our method, called BoxSup, produces competitive results supervised by boxes only, on par with strong baselines fully supervised by masks under the same setting. By leveraging a large amount of bounding boxes, BoxSup further unleashes the power of deep convolutional networks and yields state-of-the-art results on PASCAL VOC 2012 and PASCAL-CONTEXT.

An enhanced stability criterion for time-delay systems via a new bounding technique

Abstract: In the past few years, a great deal of effort has been devoted to improve delay-dependent conditions for stability of linear systems with an interval time-varying delay. To reduce conservatism of stability conditions, in the framework of the Lyapunov–Krasovskii functional (LKF) method, the bounding technique plays a key role. In this paper, a new bounding technique based on a new integral inequality is proposed. By employing the newly bounding technique proposed in this paper, an enhanced stability criterion for a class of linear systems with an interval time-varying delay is derived. The effectiveness and a significant improvement of the obtained results are shown by numerical examples.

Global optimization of generalized semi-infinite programs via restriction of the right hand side

Abstract: The algorithm proposed in Mitsos (Optimization 60(10---11):1291---1308, 2011) for the global optimization of semi-infinite programs is extended to the global optimization of generalized semi-infinite programs. No convexity or concavity assumptions are made. The algorithm employs convergent lower and upper bounds which are based on regular (in general nonconvex) nonlinear programs (NLP) solved by a (black-box) deterministic global NLP solver. The lower bounding procedure is based on a discretization of the lower-level host set; the set is populated with Slater points of the lower-level program that result in constraint violations of prior upper-level points visited by the lower bounding procedure. The purpose of the lower bounding procedure is only to generate a certificate of optimality; in trivial cases it can also generate a global solution point. The upper bounding procedure generates candidate optimal points; it is based on an approximation of the feasible set using a discrete restriction of the lower-level feasible set and a restriction of the right-hand side constraints (both lower and upper level). Under relatively mild assumptions, the algorithm is shown to converge finitely to a truly feasible point which is approximately optimal as established from the lower bound. Test cases from the literature are solved and the algorithm is shown to be computationally efficient.

Boosting sensor network calculus by thoroughly bounding cross-traffic

Abstract: Sensor Network Calculus (SensorNC) provides a framework for worst-case analysis of wireless sensor networks The analysis proceeds in two steps: For a given flow, (1) the network is reduced to a tandem of nodes by computing the arrival bounds of cross-traffic; (2) the flow is separated from the cross-traffic by subtracting cross-flows and concatenating nodes on its path While the second step has seen much treatment, the first step has not at all This is in sharp contrast to the fact that arrival bounding takes roughly 80% of the total analysis time and is equally crucial for the tightness of the bounds Therefore, we turn our attention to this first SensorNC analysis step with the goal to boost the performance and applicability of the overall framework The main technical contribution is a generalized version of the concatenation theorem within the SensorNC setting This generalization is instrumental in simplifying and streamlining the cross-traffic arrival bound computations such that run times can be reduced by more than a factor of 5 Even more important, it enables a localization of the information necessary to execute the calculations at the node level, thus enabling a distribution of the SensorNC analysis within a self-modeling WSN

UWB rapid-bit-exchange system for distance bounding

Abstract: Distance bounding protocols enable one device (the verifier) to securely establish an upper bound on its distance to another device (the prover). These protocols can be used for secure location verification and detection of relay attacks, even in presence of strong attackers. The rapid-bit-exchange is the core of distance bounding protocols---the verifier sends single bit challenges, which the prover is expected to answer with minimal and stable processing delay. Based on the measured round trip time of flight, the verifier calculates its upper bound to the prover. Although several aspects of distance bounding implementations have been discussed in the past, no full implementation of a wireless distance bounding system has been presented so far.In this work, we present the first full realization of a rapid bit exchange system for distance bounding. Our system consists of an Ultra-Wideband (UWB) ranging radio and of an efficient digital processing implemented on an Field-Programmable-Gate-Array (FPGA) board; it achieves a ranging accuracy of 7:5 cm and a short processing delay at the prover (

Bonsai: Rapid Bounding Volume Hierarchy Generation using Mini Trees

Abstract: We present an algorithm, called Bonsai, for rapidly building bounding volume hierarchies for ray tracing. Our method starts by computing midpoints of the triangle bounding boxes and then performs a rough hierarchical top-down split using the midpoints, creating triangle groups with tight bounding boxes. For each triangle group, a mini tree is built using an improved sweep SAH method. Once all mini trees have been built, we use them as leaves when building the top tree of the bounding volume hierarchy. We also introduce a novel and inexpensive optimization technique, called mini-tree pruning, that can be used to detect and improve poorly built parts of the tree. We achieve a little better than 100% in ray-tracing performance compared to a "ground truth" greedy top-down sweep SAH method, and our build times are the lowest we have seen with comparable tree quality. (Less)

Querying Web-Scale Information Networks Through Bounding Matching Scores

Abstract: Web-scale information networks containing billions of entities are common nowadays. Querying these networks can be modeled as a subgraph matching problem. Since information networks are incomplete and noisy in nature, it is important to discover answers that match exactly as well as answers that are similar to queries. Existing graph matching algorithms usually use graph indices to improve the efficiency of query processing. For web-scale information networks, it may not be feasible to build the graph indices due to the amount of work and the memory/storage required. In this paper, we propose an efficient algorithm for finding the best k answers for a given query without precomputing graph indices. The quality of an answer is measured by a matching score that is computed online. To speed up query processing, we propose a novel technique for bounding the matching scores during the computation. By using bounds, we can efficiently prune the answers that have low qualities without having to evaluate all possible answers. The bounding technique can be implemented in a distributed environment, allowing our approach to efficiently answer the queries on web-scale information networks. We demonstrate the effectiveness and the efficiency of our approach through a series of experiments on real-world information networks. The result shows that our bounding technique can reduce the running time up to two orders of magnitude comparing to an approach that does not use bounds.

Detecting roadway objects in real-time images

Abstract: The disclosure includes a method that receives a real-time image of a road from a camera sensor communicatively coupled to an onboard computer of a vehicle The method includes dividing the real-time image into superpixels The method includes merging the superpixels to form superpixel regions The method includes generating prior maps from a dataset of road scene images The method includes drawing a set of bounding boxes where each bounding box surrounds one of the superpixel regions The method includes comparing the bounding boxes in the set of bounding boxes to a road prior map to identify a road region in the real-time image The method includes pruning bounding boxes from the set of bounding boxes to reduce the set to remaining bounding boxes The method may include using a categorization module that identifies the presence of a road scene object in the remaining bounding boxes

SubmodBoxes: near-optimal search for a set of diverse object proposals

Abstract: This paper formulates the search for a set of bounding boxes (as needed in object proposal generation) as a monotone submodular maximization problem over the space of all possible bounding boxes in an image. Since the number of possible bounding boxes in an image is very large O(#pixels2), even a single linear scan to perform the greedy augmentation for submodular maximization is intractable. Thus, we formulate the greedy augmentation step as a Branch-and-Bound scheme. In order to speed up repeated application of B&B, we propose a novel generalization of Minoux's 'lazy greedy' algorithm to the B&B tree. Theoretically, our proposed formulation provides a new understanding to the problem, and contains classic heuristic approaches such as Sliding Window+Non-Maximal Suppression (NMS) and and Efficient Subwindow Search (ESS) as special cases. Empirically, we show that our approach leads to a state-of-art performance on object proposal generation via a novel diversity measure.

Systems and methods for reducing a plurality of bounding regions

Abstract: A method performed by an electronic device is described. The method includes generating a plurality of bounding regions based on an image. The method also includes determining a subset of the plurality of bounding regions based on at least one criterion and a selected area in the image. The method further includes processing the image based on the subset of the plurality of bounding regions.

Bounding defaults in egress models

Abstract: Egress model developers are in a difficult position. It is in their interest to develop models that are simplified representations of reality and at the same time reduce inadvertent misuse. While default values enable immediate (i.e. out-of-the-box) use of models without in-depth familiarization with modelling assumptions, defaults often represent optimistic and/or even unrealistic evacuee behaviours. In this paper, the term ‘default’ relates to a preset, fixed setting or value (or distribution) for a parameter or algorithm. Most egress models provide default values for five core behavioural elements: pre-evacuation time, travel speeds, route usage, route availability and flow conditions. These behavioural elements typically need to be represented in order for the model to function. The authors suggest that bounding default settings, rather than optimistic values, should be provided for each behavioural element. Here, a bounding default setting is a value derived from relevant empirical data that prolongs the overall evacuation time produced for a particular design. If a user wishes to decrease the conservative nature of a setting, he or she would be required to justify the modification of the bounding default value(s). This approach allows immediate model use but forces the user to modify the settings to obtain credible design scenarios. (Less)

Decompression and traversal of a bounding volume hierarchy

Abstract: Embodiments provide for a graphics processing apparatus including a graphics processing unit having bounding volume logic to operate on a compressed bounding volume hierarchy, wherein each bounding volume node stores a parent bounding volume and multiple child bounding volumes that are encoded relative to the parent bounding volume.

Creation of bounding boxes on a 3d modeled assembly

Abstract: It is proposed a computer-implemented method for creating a set of bounding boxes on a three-dimensional modeled assembly in a three-dimensional scene. The method comprises providing three-dimensional modeled objects forming a three-dimensional modeled assembly in a three-dimensional scene; computing a main bounding box encompassing the three-dimensional modeled assembly; creating a set of three-dimensional modeled objects that meet at least one property of the three-dimensional modeled assembly; computing two or more bounding boxes encompassed by the main bounding box, one of the two or more bounding boxes comprising the three-dimensional modeled objects of the set.

Design and Utilization of Bounding Box in Human Detection and Activity Identification

Abstract: All video surveillance system uses some important steps to detach moving object from background and thus differentiate all the objects in video image frames. The main endeavor of this paper is to use an object bounding box concept to detect the human blob and human activity detection using a system. The images are captured by using single static camera to make the system cost effective. The bounding box that bounds each object in the image frames can be utilized to track and detect activities of the moving objects in further frames. These bounding boxes can be utilized to detect human and human activities like crowd and the estimation of crowd. This paper gives the implementation results of bounding box for activity detection.

Achieving an appropriate security level for distance bounding protocols over a noisy channel

Abstract: A relay attack is probably the most popular assault that is normally executed over RFID security protocols. To protect RFID systems against this attack, distance bounding protocols are commonly employed. Within such protocols, the reader estimates an upper bound for the physical distance between the tag and itself as well as authenticating the tag. In this paper, as a general case, the concept of a distance bounding protocol is introduced with five adjustable security parameters characterized by $$p_d$$pd, $$k$$k, $$n$$n, $$t_1$$t1 and $$t_2$$t2. Since RFID systems and distance bounding protocols are principally vulnerable to noise, the security analysis for the introduced distance bounding protocol is performed over a noisy channel. With such analysis, the attacker's success probability due to mafia fraud and distance fraud attacks are obtained in a closed form through the five security parameters and the probability of erroneous transmission. The analytic results show that, with the proper selection of the mentioned security parameters in a known noisy environment, a distance bounding protocol provides the optimal attackers' success probabilities with the desirable number of iterations and memory requirements.

Secure positioning with non-ideal distance bounding protocols

Abstract: Distance bounding protocols are secure protocols to determine an upper bound to the distance between two devices. These protocols have shown to be useful for many tasks, from proximity verification to secure positioning. Unfortunately, real distance bounding protocols hardly fulfill the claimed property. Attacks at the PHY layer may cause significant reductions on the estimated upper bound. These attacks can be mitigated, not eliminated, by changing the receiver architecture and the PHY layer. Every distance bounding protocol is thus non-ideal. In this paper, we study the impact of non-ideal distance bounding on the reliability of secure positioning techniques. We show that a reduction of 10 meters, which is possible against a real PHY layer, allows the adversary to falsify a position of 21 meters. We also propose two countermeasures to mitigate the problem, and then estimate their efficacy by simulations.

Measuring Impact of Random Jumps Without Sample Path Generation

Abstract: We develop a novel method for measuring the impact of random jumps in the expectation of functionals of jump-diffusion processes, without simulating sample paths of jump-diffusion processes for Monte Carlo estimation. The proposed method constructs deterministic upper and lower bounding functions for the expectation of making full use of a similar structure in the infinitesimal generator of diffusion and jump-diffusion processes. Our hard bounding functions have the form of Markov-type inequalities, parametrized by the jump intensity parameter, so that the upper and lower bounding functions converge to each other when the jump intensity tends to zero. Hard bounding functions are derived also for the sensitivities of the expectation with respect to the jump intensity. The proposed method requires only well-developed numerical methods for PDEs (not partial integro-differential equations) and some elementary numerical integration of smooth functions. Numerical results are presented throughout the paper to su...

Hyperorthogonal Well-Folded Hilbert Curves

Abstract: R-trees can be used to store and query sets of point data in two or more dimensions. An easy way to construct and maintain R-trees for two-dimensional points, due to Kamel and Faloutsos, is to keep the points in the order in which they appear along the Hilbert curve. The R-tree will then store bounding boxes of points along contiguous sections of the curve, and the efficiency of the R-tree depends on the size of the bounding boxes - smaller is better. Since there are many different ways to generalize the Hilbert curve to higher dimensions, this raises the question which generalization results in the smallest bounding boxes. Familiar methods, such as the one by Butz, can result in curve sections whose bounding boxes are a factor Omega(2^{d/2}) larger than the volume traversed by that section of the curve. Most of the volume bounded by such bounding boxes would not contain any data points. In this paper we present a new way of generalizing Hilbert's curve to higher dimensions, which results in much tighter bounding boxes: they have at most 4 times the volume of the part of the curve covered, independent of the number of dimensions. Moreover, we prove that a factor 4 is asymptotically optimal.

Efficient packing of objects

Abstract: Systems, apparatuses and/or methods may provide for generating a packing order of items within a container that consolidates the items into a reduced space Items may be scanned with a three-dimensional ( 3 D) imager, and models may be generated of the items based on the data from the 3 D imager The items may be located within minimal-volume enclosing bounding boxes, which may be analyzed to determine whether they may be merged together in one of their bounding boxes, or into a new bounding box that is spatially advantageous in terms of packing If a combination of items is realizable and is determined to take up less space in a bounding box than the bounding boxes of the items considered separately, then they may be merged into a single bounding box Thus, a spatially efficient packing sequence for a plurality of real objects may be generated to maximize packing efficiency

TIGHT: A Cross-Layer RF Distance Bounding Realization for Passive Wireless Devices

Abstract: As distance bounding can be leveraged for solving numerous security issues, extensive studies have been carried out for its implementation. Realizing RF distance bounding in battery-less or constrained devices is quite challenging because of inadequate harvested energy and large signal processing delays. We present TIGHT, an RF distance bounding scheme based on Signal Conditioning and Polarization Selection , with which a prover codes and reflects the incident challenges as a polarization function at analog RF at 1 nsec. In addition, our focus lies in designing TIGHT as a full duplex energy optimized system while considering the device synchronization in passive hardware. Security analysis shows that TIGHT is resilient to attacks most concerned in distance bounding. We demonstrate our scheme through prototype implementation and practical evaluation for delay measurements and calculate bit error rate while considering channel interference at ten outdoor and indoor places. Dealing with noise, we estimate the protocol failure, false-acceptance and false-rejection probabilities for TIGHT. Our results show that TIGHT is an effective RF distance bounding approach for passive wireless devices, especially the RFID tokens.

A literature review of bounding volumes hierarchy focused on collision detection

Abstract: A bounding volume is a common method to simplify object representation by using the composition of geometrical shapes that enclose the object; it encapsulates complex objects by means of simple volumes and it is widely useful in collision detection applications and ray tracing for rendering algorithms They are popular in computer graphics and computational geometry Most popular bounding volumes are spheres, Oriented-Bounding Boxes (OBB's), Axis-Aligned Bounding Boxes (AABB's); moreover, the literature review includes ellipsoids, cylinders, sphere packing, sphere shells, k-DOP's, convex hulls, cloud of points, and minimal bounding boxes, among others A Bounding Volume Hierarchy is usually a tree in which the complete object is represented tighter fitting every level of the hierarchy Additionally, each bounding volume has a cost associated to construction, update, and interference tests For instance, spheres are invariant to rotation and translations, then they do not require being updated; their constructions and interference tests are more straightforward then OBB's; however, their tightness is lower than other bounding volumes Finally, three comparisons between two polyhedra; seven different algorithms were used, of which five are public libraries for collision detection

Revisión de literatura de jerarquía volúmenes acotantes enfocados en detección de colisiones

Abstract: A bounding volume is a common method to simplify object representation by using the composition of geometrical shapes that enclose the object; it encapsulates complex objects by means of simple volumes and it is widely useful in collision detection applications and ray tracing for rendering algorithms. They are popular in computer graphics and computational geometry. Most popular bounding volumes are spheres, Oriented-Bounding Boxes (OBB’s), Axis-Aligned Bounding Boxes (AABB’s); moreover, the literature review includes ellipsoids, cylinders, sphere packing, sphere shells,k-DOP’s, convex hulls, cloud of points, and minimal bounding boxes, among others. A Bounding Volume Hierarchy is usually a tree in which the complete object is represented tighter fitting every level of the hierarchy. Additionally, each bounding volume as a cost associated to construction, update, and interference tests. For instance, spheres are invariant to rotation and translations, then they do not require being updated; their constructions and interference tests are more straightforward then OBB’s; however, their tightness is lower than other bounding volumes. Finally, three comparisons between two polyhedra; seven different algorithms were used, of which five are public libraries for collision detection.

Stochastic Bounding Models for Performance Analysis of Clouds

Abstract: We propose to evaluate the performance of a cloud node (data center) using hysteresis queueing systems and stochastic bound methods. We represent the dynamic behavior of the cloud node by a hysteresis queueing system with forward and backward threshold vectors. The client requests (or jobs) are represented by bulk arrivals entering the buffer, and executed by Virtual Machines (VMs) which are activated and deactivated according to the occupation of the queue, and the threshold sequences. As the system is quite difficult to analyze, we propose to define different bounding systems "less complex" and easier to study. Two approaches are used, one by aggregating the probability distribution of the batch arrivals and another by taking models with the same sequences of forward and backward thresholds. We show the relevance of the proposed bounding systems by presenting some numerical results for the performance measures of a data center.

Orientational Spatial Part Modeling for Fine-Grained Visual Categorization

Abstract: Although significant success has been achieved in fine-grained visual categorization, most of existing methods require bounding boxes or part annotations for training and test, resulting in limited usability and flexibility To conquer these limitations, we aim to automatically detect the bounding box and parts for fine-grained object classification The bounding boxes are acquired by a transferring strategy which infers the locations of objects from a set of annotated training images Based on the generated bounding box, we propose a multiple-layer Orientational Spatial Part (OSP) model to generate a refined description for the object Finally, we employ the output of deep Convolutional Neural Network (dCNN) as the feature and train a linear SVM as object classifier Extensive experiments on public benchmark datasets manifest the impressive performance of our method, ie, Classification accuracy achieves 639% on CUB-200-2011 and 756% on Aircraft, which are actually higher than many existing methods using manual annotations

Exact Bounding Spheres by Iterative Octant Scan

Abstract: We propose an exact minimum bounding sphere algorithm for large point sets in low dimensions. It aims to reduce the number of required passes by retrieving a well-balanced set of outliers in each l ...