Sensible Scenes : Visual Understanding of Complex

نویسندگان

  • Matthew Brand
  • Lawrence Birnbaum
  • Arthur Andersen
چکیده

Visual Understanding of Complex Structures through Causal Analysis Matthew Brand, Lawrence Birnbaum, and Paul Cooper Northwestern University The Institute for the Learning Sciences 1890 Maple Avenue, Evanston IL 60201 [email protected] Abstract An important result of visual understanding is an explanation of a scene's causal structure: How action|usually motion|is originated, constrained, and prevented, and how this determines what will happen in the immediate future. To be useful for a purposeful agent, these explanations must also capture the scene in terms of the functional properties of its objects|their purposes, uses, and a ordances for manipulation. Design knowledge describes how the world is organized to suit these functions, and causal knowledge describes how these arrangements work. We have been exploring the hypothesis that vision is an explanatory process in which causal and functional reasoning plays an intimate role in mediating the activity of low-level visual processes. In particular, we have explored two of the consequences of this view for the construction of purposeful vision systems: Causal and design knowledge can be used to 1) drive focus of attention, and 2) choose between ambiguous image interpretations. Both principles are at work in SPROCKET, a system which visually explores simple machines, integrating diverse visual clues into an explanation of a machine's design and function. Visual understanding A fundamental purpose of vision is to relate a scene to the viewer's beliefs about how the world ought to be|to \make sense" of the scene. Understanding is the preparation we make for acting, hence our beliefs are fundamentally causal in nature; they describe the world's capacity for action and change. \Making sense" of a scene means assessing its potential for action, whether instigated by the agent, or set in motion by forces already present in the world. This work was supported in part by the National Science Foundation, under grant number IRI9110482. The Institute for the Learning Sciences was established in 1989 with the support of Andersen Consulting, part of The Arthur Andersen Worldwide Organization. The Institute receives additional support from Ameritech, North West Water Plc, Institute Partners, and from IBM. G1 G3 A1 A2

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Translation and Hybridity in Scenes and Frames Semantics

 The present study is a theoretical attempt to illustrate how Fillmore's Scenes and Frames Semantics (SFS) could be employed as a framework to portray the process of understanding and translating hybrid texts. It first reviews the origin of SFS; then it maps SFS onto Nida’s linguistic model of translation process and the Interpretive Theory of Translation; it examines in the next section, withi...

متن کامل

Statistical regularities in art: Relations with visual coding and perception

Since at least 1935, vision researchers have used art stimuli to test human response to complex scenes. This is sensible given the "inherent interestingness" of art and its relation to the natural visual world. The use of art stimuli has remained popular, especially in eye tracking studies. Moreover, stimuli in common use by vision scientists are inspired by the work of famous artists (e.g., Mo...

متن کامل

Figure-Ground Organization in Visual Cortex for Natural Scenes

Figure-ground organization and border-ownership assignment are essential for understanding natural scenes. It has been shown that many neurons in the macaque visual cortex signal border-ownership in displays of simple geometric shapes such as squares, but how well these neurons resolve border-ownership in natural scenes is not known. We studied area V2 neurons in behaving macaques with static i...

متن کامل

Visual motion pattern extraction and fusion for collision detection in complex dynamic scenes

Detecting colliding objects in complex dynamic scenes is a difficult task for conventional computer vision techniques. However, visual processing mechanisms in animals such as insects may provide very simple and effective solutions for detecting colliding objects in complex dynamic scenes. In this paper, we propose a robust collision detecting system, which consists of a lobula giant movement d...

متن کامل

A Novel Approach to Background Subtraction Using Visual Saliency Map

Generally human vision system searches for salient regions and movements in video scenes to lessen the search space and effort. Using visual saliency map for modelling gives important information for understanding in many applications. In this paper we present a simple method with low computation load using visual saliency map for background subtraction in video stream. The proposed technique i...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1993