Knowledge-based improvement of automatic image interpretation for restricted scenes: two case studies

The paper explores the usefulness and applicability of knowledge-based image interpretation. By limiting the analysis to ‘restricted’ scenes, a bottom-up strategy has been developed to improve a primal image segmentation. Two case studies are discussed: the first deals with medical X-rays, the second with satellite images (SPOT). In both projects, generic geometrical knowledge is encoded in the format of production rules. The results obtained so far are encouraging and are already of practical use. Ways to extend the knowledge bases by more specific domain knowledge are mentioned.     

Frame-based system for image interpretation

This paper describes a frame-based computer vision system named FABIUS implemented in Prolog. Advantages of using frames for computer vision are that they are modular and understandable; structural, decomposable objects can be described by part frame hierarchies, and specialization frame hierarchies enable property inheritance and flexible, efficient object classification. Image processing operations, written in C, are triggered as demons when specific slots in a frame are accessed. Prolog provides the problem solving facilities of backtracking and pattern matching. The system is shown to be well suited to rapid development of applications and alternative interpretation strategies, and its operation is illustrated when applied to the task of identifying vehicles in cluttered real-world scenes.     

Environments for image processing algorithm development

The development of image processing algorithms can be greatly assisted by a software environment which is suitable for rapidly implementing and testing new ideas. This paper looks at a traditional approach to providing such an environment and highlights its weaknesses. The requirements of an ideal system are summarized and some observations are made about alternative software approaches.     

Knowledge organization and its role in representation and interpretation for time-varying data: the ALVEN system

The so-called "first generation" expert systems were rule-based and offered a successful framework for building applications systems for certain kinds of tasks. Spatial, temporal, and causal reasoning, knowledge abstractions, and structuring are among topics of research for "second generation" expert systems. It is proposed that one of the keys for such research is knowledge organization. Knowledge organization determines control structure design, explanation and evaluation capabilities for the resultant knowledge base, and has strong influence on system performance. We are exploring a framework for expert system design that focuses on knowledge organization, for a specific class of input data, namely, continuous, time-varying data (image sequences or other signal forms). Such data are rich in temporal relationships as well as temporal changes of spatial relations, and are thus a very appropriate testbed for studies involving spatio-temporal reasoning. In particular, the representation formalism specifies the semantics of the organization of knowledge classes along the relationships of generalization/specialization, decomposition/aggregation, temporal precedence, instantiation, and expectation-activated similarity. Á hypothesize-and-test control structure is driven by the class organizational principles, and includes several interacting dimensions of search (data-driven, model-driven, goal-driven temporal, and failure-driven search). The hypothesis ranking scheme is based on temporal cooperative computation, with hypothesis "fields of influence" being defined by the hypothesis' organizational relationships. This control structure has proven to be robust enough to handle a variety of interpretation tasks for continuous temporal data. A particular incarnation, the ALVEN system, for left ventricular performance assessment from X-ray image sequences, will be summarized in this paper.     

Knowledge-based region labeling for remote sensing image interpretation

The increasing availability of High Spatial Resolution (HSR) satellite images is an opportunity to characterize and identify urban objects. Thus, the augmentation of the precision led to a need of new image analysis methods using region-based (or object-based) approaches. In this field, an important challenge is the use of domain knowledge for automatic urban objects identification, and a major issue is the formalization and exploitation of this knowledge. In this paper, we present the building steps of a knowledge-base of urban objects allowing to perform the interpretation of HSR images in order to help urban planners to automatically map the territory. The knowledge-base is used to assign segmented regions (i.e. extracted from the images) into semantic objects (i.e. concepts of the knowledge-base). A matching process between the regions and the concepts of the knowledge-base is proposed, allowing to bridge the semantic gap between the images content and the interpretation. The method is validated on Quickbird images of the urban areas of Strasbourg and Marseille (France). The results highlight the capacity of the method to automatically identify urban objects using the domain knowledge.     

Knowledge-based systems in computer-assisted production — a review

With the development of ‘expert’ or ‘knowledgeåsed’ systems, the efforts of artificial intelligence research have attained commercial application. While there have been to date, only a few investigations concerning the extent of this transfer, assessment of the extent of manufacturing applications has been mostly the result of speculation. By means of a comprehensive survey of documented systems in the USA, UK and FRG, the state-of-the-art of production applications of knowledge-based systems is described. Detailed discussion i is made of reasons leading to computer assistance and integrated solutions. Computer-assisted technological s systems are reviewed under their specific task areas — that is, construction and design, production planning, production control, production of parts, quality assurance, assembly, maintenance and customer service. Solutions for the connection of islands of automation are dealt with under the heading of Computer Integrated Manufacturing.     

Knowledge-based analysis of carotid angiograms

The project described is concerned with the development of a practical system for interpreting carotid angiograms. The general requirements of such a system are identified and some of the design considerations are discussed. The analysis strategies and types of knowledge used by an expert in recognizing and naming vessels and categorizing abnormalities on a single-plane angiogram are described- Two distinct types of knowledge are identified: ‘facts’ knowledge which is drawn from various areas of science, and ‘strategy’ knowledge which determines how the facts should be used. It is suggested that confidence parameters should be associated with each type of knowledge and these should be used in the control of the analysis of an angiogram. The ‘facts’ and ‘strategy’ knowledge bases have a hierarchical structure which, if exploited, would enable the system to be easily adapted for use in other application areas.     

滑坡高分辨率遥感多维解译方法及其应用

目的:高分辨率遥感影像技术的发展使得对于地质灾害体的要素组成、形态结构的遥感解译成为可能。目前,遥感影像解译存在着过度依赖影像色彩、纹理、阴影等光学要素,片面追求影像解译标志,DEM数据利用程度低,对基于DEM、GIS的影像复合分析、空间分析、3D可视化等技术方法的应用较少等问题。方法：本文以灾前灾后高精度DEM和高分辨率遥感影像为基础,探讨了地质灾害滑坡的一维、二维、三维三种遥感解译方法,分析了三者之间的互补关系,并应用三种遥感解译方法对贵州关岭“6.28”特大滑坡进行了遥感解译分析,文章最后对有关滑坡多维遥感解译方法体系的建立进行了讨论。结果：研究结果表明：滑坡高分辨率遥感多维解译方法中,一维高程曲线计算、二维影像对比分析、三维场景精细解译分别属于滑坡遥感解译的初判方法、动态分析方法、定量计算方法;结论：其中,一维高程曲线计算为滑坡遥感的二、三维解译提供了有关滑坡崩塌区、滑坡区、堆积区的可能分区参考框架,而二维影像对比分析向三维场景精细解译的发展则体现了以人机交互方式为主要手段的滑坡高分辨率遥感影像解译由定性监测向定量计算的发展。     

头盔瞄准具精度鉴定试飞图像判读技术研究

头盔瞄准具精度鉴定课题是我国某新型直升机进行鉴定试飞的重要科目之一。飞行实验中采用了基于机载数字影像的头盔瞄准具精度鉴定非接触测量方法,其中对头盔运动影像序列中测量特征点图像坐标进行精确判读是实现该方法的重要环节。基于Kalman滤波的特征点跟踪算法、相关性原理的图像匹配算法、Harris算子和角点定位算子实现特征点图像坐标亚像素判读,得到每帧影像中测量特征点的精确二维图像坐标,为后续的头盔运动姿态测量解算提供精度保证。     

The interpretation of laser radar images by a knowledge-based system

This paper presents a knowledge-based system to interpret laser radar (ladar) images. The objective of this research is to detect and recognize man-made objects in outdoor scenes. Our system applies themultisensor fusion approach to multiple ladar modalities to improve both segmentation and interpretation. The segmentation modules are written in C. The knowledge-based interpretation system is constructed usingKEE and Lisp. Low-level attributes of image segments (regions) are computed by the segmentation modules and then converted to theKEE format. The interpretation system applies forward chaining in a bottom-up fashion to derive object-level interpretation from input generated by low-level processing and segmentation modules. The interpretation modules detect man-made objects from the background using low-level attributes. Segments are grouped into objects, which are then classified into predefined categories (vehicles, ground, etc.). The efficiency of the interpretation system is enhanced by transferring nonsymbolic processing tasks to a concurrent service manager (program). Experimental results using ladar data are presented.     

Knowledge-based environment for investigating multicomputer architectures

Multicomputers for massively parallel processing will eventually employ billions of processing elements, each of which will be capable of communicating with every other processing element. A knowledge-based modelling and simulation environment (KBMSE) for investigating such multicomputer architecture at a discrete-event system level is described. The KBMSE implements the discrete-event system specification (DEVS) formalism in an object-oriented programming system of Scheme (a dialect), which supports building models in a hierarchical, modular manner, a systems-oriented approach not possible in conventional simulation languages. The paper presents a framework for knowledge-based modelling and simulation by exemplifying modelling a hypercube multicomputer architecture in the KBMSE. The KBMSE has been tested on a variety of domains characterized by complex, hierarchical structures such as advanced multicomputer architectures, local area computer networks, intelligent multi-robot organizations, and biologically based life-support systems.     

Knowledge-based facility planning: a review and a framework

The knowledge-based facility planning (KBFP) problem is reviewed. The aim of KBFP is to provide a more comprehensive planning package for users so that their expertise can be augmented with proven knowledge, and yield significantly better plans. The categories reviewed include facilities equipment selection, software model selection, and the generative task of creating a facility planning solution. The employed problem representation and problem-solving techniques are reviewed. Finally, the development of an integrated framework for KBFP is discussed.     

HTE 3.0: Knowledge-based systems in cascade for familial hypercholesterolemia detection and dyslipidemia treatment

HTE 3.0 aims to support clinicians in the detection of patients with dyslipidemia, especially patients with familial hypercholesterolemia (FH), and in the recommendation of personalized lipid-lowering treatments. The core of HTE 3.0 is a clinical decision support system in which several knowledge-based systems are serialized: patient detection, therapeutic target setting, personalized treatment assessment, and treatment combination and prioritization, according to different criteria. The experimental evaluation of HTE 3.0 shows that the use of HTE 3.0 would mean increasing the capacity to detect FH by 5.7 times compared with usual clinical practice. Regarding the lipid-lowering treatment, a comparison of 18 cases among seven lipidologists shows that the differences between treatments provided by HTE 3.0 and human lipidologists are smaller than the differences between human experts.     

几种典型图像采集和处理系统设计与效率分析

以图像采集和处理系统总体框架为基础,介绍了几种典型设计方案,分析了不同方案中系统的时间效率及影响因素.通过实验测试,验证理论分析的正确性,总结了不同方案的合理使用建议.     

KIMS: knowledge-based image management system

A knowledge-based image management system called KIMS is developed for storage and retrieval of images. The aim of the system is to overcome some of the limitations inherent in Micro-IDBMS, a microcomputer-based image database management system. These limitations include abrupt failure and the inability to capture the concept of an image. Abrupt failure may occur during retrieval when there are no images that have the specified attribute value. The inability to capture the concept of an image is related to the general idea that an image is a representation.

KIMS basically consists of an image knowledge base and an inference mechanism, in addition to Micro-IDBMS. The paper describes the rolé of image knowledge and presents the design and implementation details of KIMS.     

Expert system support for environmental assessment of manufacturing products and facilities

The goal of environmentally conscious design for manufacturing is to select materials and processes that minimize environmental impact. This paper describes a general and uniform way to analyze the environmental impact of manufacturing based on the product decomposition, the materials used in the manufacturing processes, and the particular view of the environment. To accomplish this task, we developed a computer program, called EcoSys, that assists manufacturing engineers and environmental reviewers in assessing the environmental consequences of their manufacturing decisions.     

Knowledge-based learning using Conceptual Transformers

The notion of concept based on the semantics of objects is defined and illustrated. An underlying thread connecting a subset of concepts is identified. This class of concepts, called the Conceptual Transformer is defined and illustrated with real-world examples. This class finds a natural application in any area where objects can be characterized by functionality. Some interesting application areas are knowledge classification, manufacturing automation, and pattern synthesis. The salient features of this class are elaborated and a knowledge structure for representing concepts is proposed. The effect of these transformers on knowledge-directed classification, which results in the formation of virtual clusters, is examined in detail. We make use of examples from real life to bring out the efficacy of the proposed transformerbased, concept-directed classification.