Charge-Coupled Device (CCD) cameras are widely used imaging sensors in computer vision systems. Many photometric algorithms, such as shape from shading, color constancy, and photometric stereo, implicitly assume that ...
详细信息
Charge-Coupled Device (CCD) cameras are widely used imaging sensors in computer vision systems. Many photometric algorithms, such as shape from shading, color constancy, and photometric stereo, implicitly assume that the image intensity is proportional to scene radiance. The actual image measurements deviate significantly from this assumption since the transformation from scene radiance to image intensity is non-linear and is a function of various factors including: noise sources in the CCD sensor, as well as various transformations occurring in the camera including: white balancing, gamma correction and automatic gain control. This paper illustrates how careful modelling of the error sources and the various processing steps enable us to accurately estimate the "response function", the inverse mapping from image measurements to scene radiance for a given camera exposure setting. It is shown that the estimation algorithm outperforms the calibration procedures known to us in terms of reduced bias and variance. Further, we demonstrate how the error modelling helps us to obtain uncertainty estimates of the camera irradiance value. The power of this uncertainty modeling is illustrated by a vision task involving High Dynamic Range image generation followed by change detection. Change can be detected reliably even in situation where the two images (the reference scene image and the current image) are taken several hours apart.
Seabed images, from multibeam hydrographic systems or from single or multibeam sidescans, convey a lot of information about seabed type. Statistical processing of portions of images can generate features adequate for ...
详细信息
ISBN:
(纸本)0933957289
Seabed images, from multibeam hydrographic systems or from single or multibeam sidescans, convey a lot of information about seabed type. Statistical processing of portions of images can generate features adequate for seabed classification that agree with both large-scale interpretation and fine details. Here we describe Quester Tangent's QTC MULTIvIEW(TM) system for statistical seabed classification, and present several results. This software uses many statistical algorithms to generate over 130 statistical features for each image patch. Principal components analysis extracts the linear combinations of features that best describe the variance in a data set of images. The selection of statistical features is thereby optimized for a particular sediment discrimination problem, rather than a set of features selected for general use. Data points are then assigned to classes by an established clustering process. Examples demonstrate the limitations imposed by sonar physics and by design details of multibeam systems. For accurate classification results, these limitations require respect, either through compensation steps in the processing or excluding pings acquired under non-standard conditions.
This paper focuses on the design of an intelligent, three-dimensional (3-D) sensing system applying artificial intelligence methodologies for quality assurance in automated manufacturing processes. An efficient 3-D ob...
详细信息
This paper focuses on the design of an intelligent, three-dimensional (3-D) sensing system applying artificial intelligence methodologies for quality assurance in automated manufacturing processes. An efficient 3-D object-oriented knowledge base and reasoning algorithm is developed. The knowledge base includes knowledge concerning the products, manufacturing processes, and inspection methods. The products knowledge base contains properties design and manufacturing. The manufacturing and inspection knowledge bases include various manufacturing techniques, criteria for detection and diagnosis of defects, and standards and limitations on various decision-making actions. A fast and reliable assurance of product quality may be achieved through fault detection and diagnosis, using symbolic knowledge processing combined with numerical analysis of data. Incorporated with the reasoning algorithms, the knowledge base assists in the design process anticipating manufacturing problems and assuring specified end product properties. The knowledge base is regularly updated using feedback of the inspection results. An inexpensive and accurate, non-contact 3-D range data measurement system is developed. In this system, multiple laser light stripes are projected onto the product and a single CCD camera is utilized to record the scene. The distortions in the projected line pattern are due to the orientation variations and surface curvature of the object. Utilizing a linear relation between the projected line distortion and surface depth, range data is recovered from a single camera image. The surface terrain information may be converted into the curvature, orientation, and depth of the shape to incorporate into the symbolic 3-D object-oriented knowledge base and reasoning algorithms.
A model of satellite images is suggested that is based on using the systems of stochastic differential equations as a compact technique of encoding statistical object properties of an observed scene. On the basis of t...
详细信息
A model of satellite images is suggested that is based on using the systems of stochastic differential equations as a compact technique of encoding statistical object properties of an observed scene. On the basis of the model, the algorithms are constructed for determining the objects boundaries, identification of the their texture type, selection of clouding and objects of the hydrographic net on multizonal space photographs. The experimental results of an algorithm study as applied to the real satellite data are given.
作者：
L.v. TranR. LenzMedia Group
Department of Science and Engineering Campus Norrköping Linkoping University Norrkoping Sweden
In many color based image retrieval systems the color properties of an image are described by the histogram of the colors in the image. Color histograms are insensitive to small object distortions and easy to compute....
详细信息
In many color based image retrieval systems the color properties of an image are described by the histogram of the colors in the image. Color histograms are insensitive to small object distortions and easy to compute. Histogram based searches are however often inefficient for the large histogram sizes needed to represent color distributions. Therefore we introduce several new, PCA-based methods that provide efficient representations of color histograms and differences between two color histograms. We also investigate distance measures in the space of histograms which are defined by quadratic forms and which take into account the geometric structure of the underlying color space. We show that the combination of the quadratic forms based distance measure and the compression of the histogram information by difference based PCA-approximations provide new powerful and efficient retrieval algorithms for color based image retrieval.
Feature selection is an important part of most learning algorithms. Feature selection is used to select the most relevant features from the data. By selecting only the relevant features of the data, higher predictive ...
详细信息
Feature selection is an important part of most learning algorithms. Feature selection is used to select the most relevant features from the data. By selecting only the relevant features of the data, higher predictive accuracy can be achieved and the computational load of the classification system can be reduced. A simple method for feature selection using feedforward neural networks is presented. The method starts by using one input neuron and adds one input at time until the wanted classification accuracy has been achieved or all attributes have been chosen. The algorithm can also be used with other classification methods. Test results are given and they are promising. Our algorithm reduces the size of the feature space significantly and improves classification accuracy. Tests were performed on commonly used databases. Average classification accuracy, when using selected features, was between 79% and 100% depending on the used dataset.
In this paper, we focus on the total-system-energy minimization of a wireless image transmission system including both digital and analog components. Traditionally, digital power consumption has been ignored in system...
In this paper, we focus on the total-system-energy minimization of a wireless image transmission system including both digital and analog components. Traditionally, digital power consumption has been ignored in system design, since transmit power has been the most significant component. However, as we move to an era of pico-cell environments and as more complex signal processingalgorithms are being used at higher data rates, the digital power consumption of these systems becomes an issue. We present an energy-optimized image transmission system for indoor wireless applications which exploits the variabilities in the image data and the wireless multipath channel by employing dynamic algorithm transformations and joint source-channel coding. The variability in the image data is characterized by the rate-distortion curve, and the variability in the channel characteristics is characterized by the path-loss and impulse response of the channel. The system hardware configuration space is characterized by the error-correction capability of the channel encoder/decoder, number of powered-up fingers in the RAKE receiver, and transmit power of the power amplifier. An optimization algorithm is utilized to obtain energy-optimal configurations subject to end-to-end performance constraints. The proposed design is tested over QCIF images, IMT-2000 channels and 0.18μm, 2.5 v CMOS technology parameters. Simulation results over various images, various distances, two different channels, and two different rates show that the average energy savings in utilizing a total-system-energy minimization over a fixed system (designed for the worst image, the worst channel and the maximum distance) are 53.6% and 67.3%, respectively, for short-range (under 20 m) and long-range (over 20 m) systems.
We propose a block motion estimation (ME) algorithm that meets high quality requirements and allows for cost efficient vLSI realizations. It relies on a set of rules common to all fast BMA algorithms and has been desi...
详细信息
We propose a block motion estimation (ME) algorithm that meets high quality requirements and allows for cost efficient vLSI realizations. It relies on a set of rules common to all fast BMA algorithms and has been designed in order to allow for easy and prolific data reuse.
In state-of-the-art multimedia compression standards, arithmetic coding is widely used as a powerful entropy compression method. In the MPEG-4 standard a specific 4-symbol, multiple-context arithmetic coder is used fo...
详细信息
In state-of-the-art multimedia compression standards, arithmetic coding is widely used as a powerful entropy compression method. In the MPEG-4 standard a specific 4-symbol, multiple-context arithmetic coder is used for wavelet based image compression. We present an architecture capable of processing close to 1 symbol per cycle, managing a multiple context in a simple, yet cost-efficient manner. A peak performance of 200 Mbit/s is achieved when clocking this architecture at 100 MHz.
We have developed and tested alternative transforms which create different zerotree structures. These new transforms can significantly improve the performance of image compression algorithms that use zerotrees without...
详细信息
We have developed and tested alternative transforms which create different zerotree structures. These new transforms can significantly improve the performance of image compression algorithms that use zerotrees without a significant modification of the latter. A new wavelet pyramid that results in an effective non-integer up- and down-sampling of the high-frequency sub-bands is presented in this paper. Non-integer sub-sampled pyramids can also be used to reduce the data dependency in the compression algorithm, and therefore reduce the execution time in a processor with multiple parallel processing units.
暂无评论