In this paper, we develop a high-dimensional map building technique that incorporates raw pixelated semantic measurements into the map representation. The proposed technique uses Gaussian Processes (GPs) multi-class classification for map inference and is the natural extension of GP occupancy maps from binary to multi-class form. The technique exploits the continuous property of GPs and, as a r...

In this contribution a novel stereo matching technique for depth estimation in stereoscopic image pairs is pre sented The input image pair is preprocessed in the in tensity domain and edge maps together with an adap tive mesh approximating to linearly modeled regions are obtained Then an iterative stripe based quadri lateral patch matching technique is employed to esti mate the depth map from t...

In this paper, we considered two representative speaker adaptation (SA) approaches – MAP and MLLR techni -ques – for our Korean isolated word recognition task. In addition, we proposed a new speaker adaptation alg orithm to improve the performance of MAP technique. It is based on least squares method between MAP ada pted mean vectors and the corresponding SI mean vect ors. The results of our ex...

abstract a major part of iran includes mountain areas. one of the hazards which threaten these areas is the slope instability. each year the occurrence of this phenomenon causes a lot of damages to the slope lands which are exploited by man. one of the most lot hazardous of these instabilities is landslide. the goal was to investigate the causes of this process and the methods of its stabilizat...

The technique of simultaneous localization and mapping is the most important research topic in mobile robotics. In the process of building a map in its available memory, the robot memorizes environmental information on the plane of grid or topology. Several approaches about this technique have been presented so far, but most of them use mapping technique as either grid-based map or topology-bas...

Mosaic-based vehicle position estimation is a way of tracking the motion of a vehicle using real-time imagery. A vehicle equipped with a downward-looking camera, for example, can track its motion by matching camera images with a high resolution “map” image of the floor. This paper describes our current technique for constructing such a map. The challenges of the map building process include col...

The ability to pursue speciic goals is essential for purposeful autonomous navigation. Goals usually refer to objects in the environment whose position is stored in a map. To eeectively use this information, the robot needs to translate absolute positions in the map into internal coordinates, based on an estimate of its own position in the map. We describe a technique to incorporate map informa...

MapReduce has recently emerged as a new paradigm for large-scale data analysis due to its high scalability, finegrained fault tolerance and easy programming model. Since different jobs often share similar work (e.g., several jobs scan the same input file or produce the same map output), there are many opportunities to optimize the performance for a batch of jobs. In this paper, we propose two n...

Removal of speckle noise from Synthetic Aperture Radar (SAR) images is an important step before performing any image processing operations on these images. This paper presents a novel Stationary Wavelet Transform (SWT) based technique for the purpose of removing the speckle noise from the SAR returns. Maximum a posteriori probability (MAP) condition which uses a prior knowledge is used to estim...

This paper describes a technique for determining a classiication map or a hypothesis selection map using a system of reaction-diiusion equations. The reaction term of the equations is a replicator equation and provides a mutually exclusive solution. The diffusion term exploits the local consistency of the solution. The technique is eecient for problems with a small labeling space compared to an...