Abstract

Intermodal (IM) trains are typically the fastest freight trains operated in North America. The aerodynamic characteristics of many of these trains are often relatively poor resulting in high fuel consumption. However, considerable variation in fuel efficiency is possible depending on how the loads are placed on railcars in the train. Consequently, substantial potential fuel savings are possible if more attention is paid on the loading configurations of trains. A wayside machine vision (MV) system was developed to automatically scan passing IM trains and assess their aerodynamic efficiency. MV algorithms are used to analyse these images, detect and measure gaps between loads. In order to make use of the data, a scoring system was devel- oped based on two attributes – the aerodynamic coefficient and slot efficiency. The aerodynamic coefficient is calculated using the Aerodynamic Subroutine of the Train Energy Model. Slot effi- ciency represents the difference between the actual and ideal loading configuration given the particular set of railcars in the train. This system can provide IM terminal managers feedback on loading performance for trains and be integrated into the software support systems used for loading assignment.

Abstract

We present a strategy for resolving multiple hypotheses of a robot's state during global localization. The strategy operates in two stages. In the first stage a unique direction of the motion is sought that resolves or eliminates maximum number of hypotheses. In the second stage, among the frontier areas arising from the multiple hypotheses states, that frontier is chosen which resolves the maximum number of the hypotheses. The two stages are alternated till a unique hypothesis emerges. Simulation and experimental results verify the efficacy of this method. A comparison with other methods based on entropy minimization, and minimum distance travel portrays the advantage of the current methodology. A convergence proof for the algorithm is also presented.

Abstract

Different methodologies exist to direct the motion of sensors to detect targets moving across an environment in various scenarios. However, some of these do not model that navigation scenario in an environment in which obstacles are present. We extend our earlier algorithm for optimal target detection, as well as other algorithms reported in literature, to this case, and make a detailed comparison of their performance. This makes clear that the current algorithm is competitive in applications where target statistics are known in advance; otherwise, a heuristic technique by Sukhatme and Jung performs best.

Abstract

RS paths for a robot with both front and rear wheel steer. We call such robots as FR steer. The occurrence of such paths is due to the additional maneuver possible in such a robot which we call parallel steer, in addition to the ones already present in a vehicle with only front wheel steering. Hence we extend the optimal path set, containing only a single element to a set, containing n elements, thereby extending its configuration set along the optimal path from the initial to the final configuration. This extension of the set to set is made possible by introducing a special set, which we call the Parallel Steer (PS) Set. Such an extension of the configuration set would increase the size of the final configuration set achievable by a path that is optimal in free space. In the following discussion, we shall term all paths whose length is equal to an RS path as optimal.

Abstract

We present in this paper a methodology for computing the maximum velocity profile over a trajectory planned for a mobile robot. Environment and robot dynamics as well as the constraints of the robot sensors determine the profile. The planned profile is indicative of maximum speeds that can be possessed by the robot along its path without colliding with any of the mobile objects that could intercept its future trajectory. The mobile objects could be arbitrary in number and the only information available regarding them is their maximum possible velocity. The velocity profile also enables one to deform planned trajectories for better trajectory time. The methodology has been adopted for holonomic and nonholonomic motion planners. An extension of the approach to an online real-time scheme that modifies and adapts the path as well as velocities to changes in the environment such that both safety and execution time are not compromised is also presented for the holonomic case. Simulation and experimental results demonstrate the efficacy of this methodology.

Abstract

Automatic identification of the author of a document has a variety of applications for both online and offline handwritten data such as facilitating the use of write dependent recognizers, verification of claimed identity for security, enabling personalized HCI and countering repudiations for legal purposes. Most of the existing writer identification techniques require the data to be from a specific text or a recognizer be available, which is not always feasible. Text-independent approaches often require large amount of data to be confident of good results. In this work, we propose a text-independent writer identification framework that uses a specified set of primitives of online handwritten data to ascertain the identity of the writer. The framework allows us to learn the properties of the script and the writers simultaneously and hence can be used with multiple languages or scripts. We demonstrate the applicability of our framework by choosing shapes of curves as primitives and show results on five different scripts and on different data sets.

Abstract

Annotated datasets of handwriting are a prerequisite to attempt a variety of problems such as building recognizers, developing writer identification algorithms, etc. However, the annotation of large datasets is a tedious and expensive process, especially at the character or stroke level. In this paper we propose a novel, automated method for annotation at the character level, given a parallel corpus of online handwritten data and the corresponding text. The method employs a model-based handwriting synthesis unit to map the two corpora to the same space and the annotation is propagated to the word level and then to the individual characters using elastic matching. The initial results of annotation are used to improve the handwriting synthesis model for the user under consideration, which in turn refines the annotation. The method can take care of errors in the handwriting such as spurious and missing strokes or characters. The output is stored in the UPXInkML format

Abstract

Most of the state-of-the-art segmentation algorithms are de-signed to handle complex document layouts and backgrounds, while assuming a simple script structure such as in Roman script. They perform poorly when used with Indian languages, where the components are not strictly collinear. In this paper, we propose a document segmentation algorithm that can handle the complexity of Indian scripts in large document image collections. Segmentation is posed as a graph cut problem that incorporates the a prior information from script structure in the objective function of the cut. We show that this information can be learned automatically and be adapted within a collection of documents (a book)and across collections to achieve accurate segmentation. We show the results on Indian language documents in Telugu script. The approach is also applicable to other languages with complex scripts such as Bangla,Kannada, Malayalam, and Urdu

Abstract

The great devastating tsunamigenic earthquake of 26 December 2004 (M9.0) in Sumatra was quickly followed by another great one on 28 March 2005 (M8.7) in the same region. This is for the first time in the known history of Seismology that 2 great earthquakes have occurred in close spatial proximity in such a quick succession. In the present study we highlight the role of the multiple plate junction comprising the India, Burma, Australia and Sunda plates, in generation of such great earthquakes. The 26 December 2004 and the 28 March 2005 earthquakes in the Andaman-Sumatra arc seem to have occurred on distinct India-Burma and Australia-Sunda mega-thrust segments possibly separated by a stress barrier or a lithospheric break at the junction that prevented stress transfer along the arc during both earthquakes. This is evidenced by the confinement of aftershock activity on either sides of the barrier during each of the earthquakes. It appears that the large impulsive co-seismic deformation during the first earthquake of 26 December 2004 triggered the already saturated adjoining segment of the Australia-Sunda plate boundary within a short period of 3 months, generating the second one on 28 March 2005. An examination of the locations of the world’s 12 largest earthquakes since the year 1900 indicates a strong correlation (>80%) w

Abstract

The great devastating tsunamigenic earthquake of 26 December 2004 (M9.0) in Sumatra was quickly followed by another great one on 28 March 2005 (M8.7) in the same region. This is for the first time in the known history of Seismology that 2 great earthquakes have occurred in close spatial proximity in such a quick succession. In the present study we highlight the role of the multiple plate junction comprising the India, Burma, Australia and Sunda plates, in generation of such great earthquakes. The 26 December 2004 and the 28 March 2005 earthquakes in the Andaman-Sumatra arc seem to have occurred on distinct India-Burma and Australia-Sunda mega-thrust segments possibly separated by a stress barrier or a lithospheric break at the junction that prevented stress transfer along the arc during both earthquakes. This is evidenced by the confinement of aftershock activity on either sides of the barrier during each of the earthquakes. It appears that the large impulsive co-seismic deformation during the first earthquake of 26 December 2004 triggered the already saturated adjoining segment of the Australia-Sunda plate boundary within a short period of 3 months, generating the second one on 28 March 2005. An examination of the locations of the world’s 12 largest earthquakes since the year 1900 indicates a strong correlation (>80%) with multiple plate junctions. Apart from the 2 great Sumatran earthquakes observed at the quadruple plate junction of India, Burma, Australia and Sunda, even the 2 greatest earthquakes in the Himalayas – the 1897 Shillong and the 1950 Assam earthquakes – each of magnitude 8.7, occurred at a quadruple junction near the eastern Himalayan syntaxis, comprising the India, Eurasia, Burma and Sunda plates. Finite element modeling of stress field at plate junctions indicates the mechanism of great stress build-up due to the plate geometry and variable plate velocities. In general, it is inferred that triple and quadruple plate junctions are potential targets for future great earthquakes.