Image Understanding Problem Research Articles

Efficient image labeling based on markov random field and error backpropagation network

A Markov Random Field (MRF) model-based approach is proposed as a systematic way for modeling, encoding and applying scene knowledge to the image understanding problem. First, the image is segmented into a set of disjoint regions and a Region Adjacency Graph (RAG) is then constructed from the resulting segmented regions based on the spatial adjacencies between regions. The problem is then formulated by defining region labels and these labels are modeled as an MRF on the corresponding RAG. The knowledge about the scene is incorporated into an energy function that consists of appropriate clique functions which constrain the possible labels for regions. However, in the image interpretation problem, it is difficult to find appropriate parameter values of the clique functions since the real scenes are variable from image to image. The clique functions are implemented as error backpropagation networks so that they can be learned from sample training data. The optimal labeling results are then achieved by finding a labeling configuration which minimizes the energy function through simulated annealing. As preliminary experiments, the proposed method is exploited to interpret the color scenes.

Image understanding research for automatic target recognition

Automatic target recognition (ATR) is an important capability for defense applications. Many aspects of image understanding (IU) research are traditionally used to solve ATR problems. The authors discuss ATR applications and problems in developing real-world ATR systems and present the status of technology for these systems. They identify several IU problems that need to be resolved in order to enhance the effectiveness of ATR-based weapon systems. They conclude that technological gains in developing robust ATR systems will lead to significant advances in many other areas of applications of image understanding.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

AN EXPERT SYSTEM FOR INTERPRETING MESOSCALE FEATURES IN OCEANOGRAPHIC SATELLITE IMAGES

Thermal infrared images of the ocean obtained from satellite sensors are widely used for the study of ocean dynamics. The derivation of mesoscale ocean information from satellite data depends to a large extent on the correct interpretation of infrared oceanographic images. The difficulty of the image analysis and understanding problem for oceanographic images is due in large part to the lack of precise mathematical descriptions of the ocean features, coupled with the time varying nature of these features and the complication that the view of the ocean surface is typically obscured by clouds, sometimes almost completely. Towards this objective, the present paper describes a hybrid technique that utilizes a nonlinear probabilistic relaxation method and an expert system for the oceanographic image interpretation problem. This paper highlights the advantages of using the contextual information in the feature labeling algorithm. The need for an expert system and its feedback in automatic interpretation of oceanic features is discussed. The paper presents some important results of the series of experiments conducted at the Remote Sensing Branch, of the Naval Oceanographic and Atmospheric Research Laboratory, on the National Oceanic and Atmospheric Administration Advanced Very High Resolution Radiometer (AVHRR) imagery data. The results clearly indicate the drastic improvement in labeling due to the oceanographic expert system.

Feature labelling in infrared oceanographic images

Thermal infrared images of the ocean obtained from satellite sensors are widely used for the study of ocean dynamics. The derivation of mesoscale ocean information from satellite data depends to a large extent on the correct interpretation of infrared oceanographie images. The difficulty of the image analysis and understanding problem for oceanographic images is due, in large part, to the lack of precise mathematical descriptions of the ocean features, coupled with the time varying nature of these features and the complication that the view of the ocean surface is typically obscured by clouds, sometimes almost completely. Towards this objective a technique that utilizes a non-linear probabilistic relaxation method for the oceanographie feature labelling problem is described. A unified mathematical framework that helps in solving the problem is presented, and the advantages of using the contextual information in the feature labelling algorithm is highlighted. The feature labelling technique makes use of a new, efficient edge detection algorithm based on cluster shade texture measures. This algorithm is found to be more suitable for labelling the mesoscale features present in the oceanographie satellite images. Some important results of a series of experiments conducted at NOARL's Remote Sensing Branch on NOAA AVHRR imagery data are presented. A motivation for using this technique to build an automatic image interpretation system is also given.

Shape reconstruction on a varying mesh

A central class of image understanding problems is concerned with reconstructing a shape from an incomplete data set, such as fitting a surface to (partially) given contours. A new theory for solving such problems is presented. Unlike the current heuristic methods, the method used starts from fundamental principles that should be followed by any reconstruction method, regardless of its mathematical or physical implementation. A mathematical procedure which conforms to these principles is presented. One major advantage of the method is the ability to handle shapes containing both smooth and sharp parts without using thresholds. A sharp variation, such as a corner, requires a high-resolution mesh for adequate representation, while slowly varying sections can be represented with sparser mesh points. Unlike current methods, this procedure fits the surface on a varying mesh. The mesh is constructed automatically to be more dense at parts of the image that have more rapid variation. Analytical examples are given in simple cases, followed by numerical experiments.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

ERNEST: a semantic network system for pattern understanding

The authors give a detailed account of a system environment for treating general problems of image and speech understanding. A framework for representing declarative and procedural knowledge based on a suitable definition of a semantic network is provided. The syntax and semantics of the network are clearly defined. The pragmatics of the network in its use for pattern understanding are defined by several rules which are problem-independent. This allows one to formulate problem-independent control algorithms. Complete software environments are available to handle the described structures. The general applicability of the network system is demonstrated by short descriptions of three applications from different task domains. >

The effect of spatial discretization on the magnitude and direction response of simple differential edge operators on a step edge

For a unit step edge, we calculate the gradient magnitude and direction reported by various simple differential edge operators as a function of the edge's actual orientation and offset with respect to the pixel grid. To be consistent with previous work (of Abdou and Pratt) we have initially chosen to analyse (among others) the Sobel, Prewitt, and Roberts Cross operators, using a digitization model in which the pixels have uniform square receptive fields that tesselate the image plane. Our quantitative results provide insights into the behavior of these commonly used operators, insights that can guide their proper application in problems of image understanding and robot vision. We also suggest novel techniques for improving the performance of these operators.

Kalman Filter Based Range Estimation for Autonomous Navigation using Imaging Sensors

The automation of rotorcraft low-altitude flight presents challenging problems in control, computer vision and image understanding. A critical element in this problem is the ability to detect and locate obstacles, using on-board sensors, and modify the nominal trajectory. This requirement is also necessary for the safe landing of an autonomous lander on Mars. This paper examines some of the issues in the location of objects using a sequence of images from a passive sensor, and describes a Kalman filter approach to improve the range estimation to obstacles. The Kalman filter is also used to track features in the images leading to a significant reduction of search effort in the feature extraction step of the algorithm. The lack of suitable flight imagery data presents a problem in the verification of concepts for obstacle detection. An experiment is designed to acquire a sequence of images along with the sensor motion parameters and the paper will present range estimation results using this imagery.

Constructing simple stable descriptions for image partitioning

A new formulation of the image partitioning problem is presented: construct a complete and stable description of an image-in terms of a specified descriptive language-that is simplest in the sense of being shortest. We show that a descriptive language limited to a low-order polynomial description of the intensity variation within each region and a chain-code-like description of the region boundaries yields intuitively satisfying partitions for a wide class of images. The advantage of this formulation is that it can be extended to deal with subsequent steps of the image understanding problem (or to deal with other attributes, such as texture) in a natural way by augmenting the descriptive language. Experiments performed on a variety of both real and synthetic images demonstrate the superior performance of this approach over partitioning techniques based on clustering vectors of local image attributes and standard edge-detection techniques.

Optimal algorithms for image understanding: Current status and future plans

We discuss four image understanding problems: 2 1 2 D sketch, three-dimensional reconstruction from projections, shape from shading, and optical flow. We point out how known general optimality results may be applied to the first three problems. We indicate some preliminary results and work in progress, concerning the numerical solution of all four problems. Algorithms which differ from those currently used in practice are proposed.

Segment-based stereo matching

Images are 2-dimensional projections of 3-dimensional scenes, therefore depth recovery is a crucial problem in image understanding, with applications in passive navigation, cartography, surveillance, and industrial robotics. Stereo analysis provides a more direct quantitative depth evaluation than techniques such as shape from shading, and its being passive makes it more applicable than active range finding imagery by laser or radar. This paper addresses the subproblem of identifying corresponding points in the two images. The primitives we use are groups of collinear connected edge points called segments, and we base the correspondence on the minimum differential criterion. The result of this processing is a sparse array disparity map of the analyzed scene. �9 1985 Academic Press, Inc.