Probabilistic Search for Object Segmentation and Recognition

TL;DR

This paper presents a probabilistic framework for object segmentation and recognition, introducing the truncated object probability to optimize hypothesis evaluation, with experiments demonstrating its effectiveness on stereo data.

Contribution

It introduces the truncated object probability as a new statistical criterion for scene interpretation, integrating prior knowledge and data learning for improved object recognition.

Findings

Effective sequence quality for object hypotheses

Successful object segmentation and recognition from stereo data

Insight into optimal hypothesis evaluation order

Abstract

The problem of searching for a model-based scene interpretation is analyzed within a probabilistic framework. Object models are formulated as generative models for range data of the scene. A new statistical criterion, the truncated object probability, is introduced to infer an optimal sequence of object hypotheses to be evaluated for their match to the data. The truncated probability is partly determined by prior knowledge of the objects and partly learned from data. Some experiments on sequence quality and object segmentation and recognition from stereo data are presented. The article recovers classic concepts from object recognition (grouping, geometric hashing, alignment) from the probabilistic perspective and adds insight into the optimal ordering of object hypotheses for evaluation. Moreover, it introduces point-relation densities, a key component of the truncated probability, as statistical models of local surface shape.