Mid-level vision and recognition of non-rigid objects

نویسنده

  • J. Brian Subirana-Vilanova
چکیده

In this dissertation I address the problem of visual recognition of non rigid objects I introduce the frame alignment approach to recognition and illustrate it in two types of non rigid objects contour textures and elongated exible objects Frame alignment is based on matching stored models to images and has three stages rst a frame curve and a corresponding object are computed in the image Second the object is brought into correspondence with the model by aligning the model axis with the object axis if the object is not rigid it is unbent achieving a canonical description for recognition Finally object and model are matched against each other Rigid and elongated exible objects are matched using all contour information Contour textures are matched using lter outputs around the frame curve The central contribution of this thesis is Curved Inertia Frames C I F a scheme for computing frame curves directly on the image C I F is the rst algorithm which can compute probably global and curved lines and is based on three novel concepts rst a de nition of curved axis of inertia second the use of non cartisean networks third a ridge detector that automatically locates the right scale of objects The use of the ridge detector enables C I F to perform mid level tasks without the need of early vision C I F can also be used in other tasks such as early vision perceptual organization computation of focus of attention and part decomposition I present evidence against frame alignment in human perception However this ev idence suggests that frame curves have a role in gure ground segregation and in fuzzy boundaries and that their outside near top incoming regions are more salient These ndings agree with a model in which human perception begins by setting a frame of refer ence prior to early vision and proceeds by successive processing of convex structures or holes The schemes presented for contour texture and elongated exible objects use a comon two level representation of shape and contour texture which may also be useful to recog nize other non rigid transformations such as holes rigid objects articulated objects and symbolic objects Most of the schemes have been tested on the Connection Machine and compared against human perception Some work on part segmentation and holes is also presented Thesis Committee Prof W Eric L Grimson Prof Tomas Lozano Perez Prof Tomaso Poggio Prof Whitman Richards Prof Shimon Ullman

برای دانلود 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

Self-organizing shape description for tracking and classifying multiple interacting objects

The problem faced in this work is related to tracking and recognition of rigid and non-rigid interacting objects in complex scenes from a static camera. The processing steps leading to the description of the behavior of objects in terms of trajectories and typology will be illustrated in details and the performances of the system will be discussed. The proposed approach uses an empty reference ...

متن کامل

Handbook of Pattern Recognition and Computer Vision, Pp. 863{882 Viewer-centered Representations in Object Recognition: a Computational Approach

Visual object recognition is a process in which representations of objects are used to identify those objects in images. Recent psychophysical and physiological studies indicate that the visual system uses viewer-centered representations. In this chapter a recognition scheme that uses viewer-centered representations is presented. The scheme requires storing only a small number of views to repre...

متن کامل

Comparison of Different Targets Used in Augmented Reality Applications in Ubiquitous GIS

Drilling requires accurate information about locations of underground infrastructures or it can cause serious damages. Augmented Reality (AR) as a technology in Ubiquitous GIS (UBIGIS) can be used to visualize underground infrastructures on smartphones. Since smartphone’s sensors do not provide such accuracy, another approaches should be applied. Vision based computer vision systems are well kn...

متن کامل

The effect of shoe insole stiffness on electromyography activity pattern of selected lower extremity muscles during running on treadmill

 The purpose of this study was to determine the immediate effect of three types of shoe insoles, on electromyography activity of selected lower extremity muscles during running on treadmill. The electromyography activity of the rectus femoris, vastus lateralis, vastus medialis, biceps femoris, tibialis anterior and gastrocnemius lateralis muscles of 14 male athletes were recorded in non-insole,...

متن کامل

Human Behavior Recognition in Shopping Settings

This paper presents a new application that improves communication between digital media and customers at a point of sale. The system uses several methods from various areas of computer vision such as motion detection, object tracking, behavior analysis and recognition, semantic description of behavior, and scenario recognition. Specifically, the system is divided in three parts: low-level, mid-...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1993