The model-based vision requires object appearances in the computer. How 8n object appears in the image is a result of interaction between the object properties and the sensor characteristics. Thus, in model-based vision, we ought to model the sensor as well as modeling the object. In the past, however, the sensor model was not used in the model-based vision or, at least, was contained in the object model implicitly.

A 3D object localization task may be divided into two steps. First, one object appearance will be classified into one of the topologically equivalent classes of the 3D object appearances, referred to as aspects of the object (aspect classification). Then, the precise attitude and position of the object will be determined within one aspect (linear shape change determination (LSCD)). We have been working on designing a compiler which automatically generates an object localization program from a given object and sensor model; the compiler adheres to the above two-step strategy of aspect classification and linear change determination. For the first step, the compiler generates a decision tree structure program. Each branch node of the tree represents a necessary decision, such as comparing the area size of a visible face, to classify one object appearance into a smaller number of aspect groups. Along this tree, an object appearance is to be classified into one particular aspect at a leaf node of the tree. This paper will investigate the design of the compiler component to generate the second step. The compiler extends each leaf node of the tree and connects several nodes so that it performs the LSCD. The compiler chooses the largest 3D face as the primal face among several visible faces at the aspect corresponding to a leaf node. The compiler has priority rules which will select one particular method out of several possible ones; this rule defines a face coordinate system on a primal face. By using these rules, it analyzes the primal face, defines the face coordinate system on it and registers the defining method to a node connected to the leaf node. The compiler also embodies the transformation from the face to the body coordinate system at the node. In order to increase the accuracy of the attitude and position, the compiler further puts two more nodes at each branch of the program. The first node establishes correspondences between model edges and image edges. The second node iteratively solves the transformation equation to determine the object's attitude and position using these correspondences. We have prepared a program library, which is a collection of prototypical objects to perform tasks mentioned before. In compile mode, the compiler retrieves necessary strategies defined at each node, finds proper prototypical objects from the program library, instantiates and inserts these objects to the node. In run mode, these instance objects run and determine the object's attitude and position through message-passing between objects.

Modeling sensor performance for model-based vision

Determining linear shape change: toward automatic generation of object recognition programs

Reactive real-time embedded systems are pervasive in the electronics system industry. Vehicle control or remote sensing are applications where specifications may change continuously, and time-to-market strongly affects success. This calls for the use of software programmable components with behaviour that can be fairly easily changed. Formal verification and automatic synthesis of implementations are emerging technologies but today, embedded systems are still designed with an ad hoc approach that is heavily based on earlier experience with similar products and on manual design. We report on the specification and design of an ultrasonic intelligent sensor able to perceive its environment in terms of plans, edges and corners. We focus more particularly on the sensor design which follows a hierarchical modular decomposition approach in order to satisfy specification requirements.

An ultrasonic sound intelligent sensor for a mobile robot perception system. Principles, design and experimentations

Simulations for Hand-eye Systems

A 3D object localization task may be divided into two steps. First, one object appearance will be classified into one of the topologically equivalent classes of the 3D object appearances, referred to as aspects of the object (aspect classification). Then, the precise attitude and position of the object will be determined within one aspect (linear shape change determination (LSCD)). We have been working on designing a compiler which automatically generates an object localization program from a given object and sensor model; the compiler adheres to the above two-step strategy of aspect classification and linear change determination. For the first step, the compiler generates a decision tree structure program. Each branch node of the tree represents a neceSSary decision, such as comparing the area size of a visible face, to classify one object appearance into a smaller number of aspect groups. Along this tree, an object appearance is to be classified into one particular aspect at a leaf node of the tree. This paper will investigate the design of the compiler component to generate the second step. The compiler extends each leaf node of the tree and connects several nodes so that it performs the LSCD. The compiler chooses the largest 3D face as the primal face among several visible faces at the aspect corresponding to a leaf node. The compiler has priority rules which will select one particular method out of several possible ones; this rule defines a face coordinate system on a primal face. By using these rules, it analyzes the primal face, defines the face coordinate system on it, and registers the defining method to a node connected to the leaf node. The compiler also embodies the transformation from the face to the body coordinate system at the node. In order to increase the accuracy of the attitude and p i tion, the compiler further puts two more nodes at each branch of the program. The first node establishes correspondences between model edges and image edges. The second node iteratively solves the transformation equation to determine the object’s attitude and position using these correspondences. We have prepared a program library, which is a collection of prototypical objects to perform tasks mentioned before. In compile mode, the compiler

/pdf/determi-ling-linear-shape-change-toward-automatic-ger-object-223liapqkv.pdf

Determi ling Linear Shape Change: Toward Automatic Ger Object Recognition Programs*

/pdf/modeling-sensor-performance-for-model-based-vision-44ixx09a22.pdf

Modeling sensor performance for model-based vision

Citations

Determining linear shape change: toward automatic generation of object recognition programs

An ultrasonic sound intelligent sensor for a mobile robot perception system. Principles, design and experimentations

Simulations for Hand-eye Systems

Determi ling Linear Shape Change: Toward Automatic Ger Object Recognition Programs*

Related Papers (5)

Multisensor Object Recognition From 3D Models

Recognizing object function through reasoning about partial shape descriptions and dynamic physical properties

Manipulator and object tracking for in-hand 3D object modeling

Active Object Search Exploiting Probabilistic Object-Object Relations

Relation Networks for Object Detection