Recognition of 3-d Objects Having Ambiguous Views Recognition of 3-d Objects Having Ambigious Views
نویسندگان
چکیده
We present an e cent method within an active vision framework for recognizing objects which are ambiguous from certain viewpoints The approach uses an ob ject representation that is structural and appearance based At rst a preliminary object classi cation is obtained using the CRG algorithm In case of ambiguous classi cation results the system repositions its sensor and acquires additional data We give an algorithm on this sensor planning task and also on how to integrate the information gathered from various views
منابع مشابه
Classifier Independent Viewpoint Selection for 3-D Object Recognition
3–D object recognition has been tackled by passive approaches in the past. This means that based on one image a decision for a certain class and pose must be made or the image must be rejected. This neglects the fact that some other views might exist, which allow for a more reliable classification. This situation especially arises if certain views of or between objects are ambiguous. In this pa...
متن کاملObject recognition using appearance representations derived from solid models of objects
We advance active computer vision algorithms for exible manufacturing systems that classify objects and estimate their pose from intensity images. Our algorithms automatically re-position the sensor if the class or pose of an object is ambiguous in a given image and incorporate data from multiple object views in determining the nal object classi cation A feature space trajectory (FST) in a glob...
متن کاملUtilizing Temporal Associations for View-based 3-d Object Recognition I. Utilizing Temporal Associations for Viewer Centered Representations Ii. Overview of the Recognition System
We propose an architecture for the recognition of three-dimensional objects on the basis of viewer centered representations and temporal associations. Motivated by biological ndings and by successful computational implementations we have chosen a viewer centered representation scheme. In contrast to other implementations , special attention is paid to the temporal order of the views, which prov...
متن کاملObject recognition using appearance representations derived from solidmodels of objectsMichael
We advance active computer vision algorithms for exible manufacturing systems that classify objects and estimate their pose from intensity images. Our algorithms automatically re-position the sensor if the class or pose of an object is ambiguous in a given image and incorporate data from multiple object views in determining the nal object classiication A feature space trajectory (FST) in a glob...
متن کاملRecognition by humans and pigeons of novel views of 3-D objects and their photographs.
Humans and pigeons were trained to discriminate between 2 views of actual 3-D objects or their photographs. They were tested on novel views that were either within the closest rotational distance between the training views (interpolated) or outside of that range (extrapolated). When training views were 60 degrees apart, pigeons, but not humans, recognized novel views of actual objects better th...
متن کاملذخیره 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 1998