Al Mansur

Specific and Class Object Recognition for Service Robots through Autonomous and Interactive Methods

Service robots need to be able to recognize and identify objects located within complex backgrounds. Since no single method may work in every situation, several methods need to be combined and robots have to select the appropriate one automatically. In this paper we propose a scheme to classify situations depending on the characteristics of the object of interest and user demand. We classify situations into four groups and employ different techniques for each. We use Scale-invariant feature transform (SIFT), Kernel Principal Components Analysis (KPCA) in conjunction with Support Vector Machine (SVM) using intensity, color, and Gabor features for five object categories. We show that the use of appropriate features is important for the use of KPCA and SVM based techniques on different kinds of objects. Through experiments we show that by using our categorization scheme a service robot can select an appropriate feature and method, and considerably improve its recognition performance. Yet, recognition is not perfect. Thus, we propose to combine the autonomous method with an interactive method that allows the robot to recognize the user request for a specific object and class when the robot fails to recognize the object. We also propose an interactive way to update the object model that is used to recognize an object upon failure in conjunction with the users feedback.

Integration of multiple methods for robust object recognition

Service robots need to be able to recognize and identify objects located within complex backgrounds. Since no single method may work in every situation, several methods need to be combined so that robots can select the appropriate one automatically. In this paper we propose a scheme to classify situations depending on the characteristics of the object of interest and user demand. We classify situations into four categories and employ different techniques for each. We use SIFT, kernel PC A (KPCA) in conjunction with support vector machine (SVM) using intensity, color, and Gabor features for four categories. We show that the use of appropriate features is important for the use of KPCA and SVM based techniques on different kinds of objects. Through experiments we show that by using our categorization scheme a service robot can select an appropriate feature and method, and considerably improve its recognition performance. Yet, recognition is not perfect. Thus, we propose to combine the autonomous method with an interactive method that allows the robot to recognize the user request for a specific object and class when the robot fails to recognize the object.

Human robot interaction through simple expressions for object recognition

Service robots need to be able to recognize and identify objects located within complex backgrounds. Since no single method may work in every situation, several methods need to be combined. However, there are several cases when autonomous recognition methods fail. We propose an interactive recognition method in these cases. To develop a natural human robot interaction (HRI), it is necessary that the robot should unambiguously perceive the description of an object given by human. This paper reports on our experiment in which we examined the expressions humans use in describing ordinary objects. The results show that humans typically describe objects using one of multiple colors. The color is usually either that of the object background or that of the largest object portion. Based on these results, we describe our development of a robot vision system that can recognize objects when a user adopts simple expressions to describe the objects. This research suggests the importance of connecting dasiasymbolic expressionspsila with the dasiareal worldpsila in human-robot interaction.

An Integrated Method for Multiple Object Detection and Localization

The objective of this paper is to use computer vision to detect and localize multiple object within an image in the presence of a cluttered background, substantial occlusion and significant scale changes. Our approach consists of first generating a set of hypotheses for each object using a generative model (pLSA) with a bag of visual words representing each image. Then, the discriminative part verifies each hypothesis using a multi-class SVM classifier with merging features that combines both spatial shape and color appearance of an object. In the post-processing stage, environmental context information is used to improve the performance of the system. A combination of features and context information are used to investigate the performance on our local database. The best performance is obtained using object-specific weighted merging features and the context information. Our approach overcomes the limitations of some state of the art methods.

Recognition of Plain Objects Using Local Region Matching

Conventional interest point based matching requires computationally expensive patch preprocessing and is not appropriate for recognition of plain objects with negligible detail. This paper presents a method for extracting distinctive interest regions from images that can be used to perform reliable matching between different views of plain objects or scene. We formulate the correspondence problem in a Naive Bayesian classification framework and a simple correlation based matching, which makes our system fast, simple, efficient, and robust. To facilitate the matching using a very small number of interest regions, we also propose a method to reduce the search area inside a test scene. Using this method, it is possible to robustly identify objects among clutter and occlusion while achieving near real-time performance. Our system performs remarkably well on plain objects where some state-of-the art methods fail. Since our system is particularly suitable for the recognition of plain object, we refer to it as Simple Plane Object Recognizer (SPOR).

Improving Recognition through Object Sub-categorization

We propose a method to improve the recognition rate of Bayesian classifiers by splitting the training data and using separate classifier to learn each sub-category. We use probabilistic Latent Semantic Analysis (pLSA) to split the training set automatically into sub-categories. This sub-categorization is based on the similarity of training images in terms of objects appearance or background content. In some cases, clear separation does not exist in the training set, and splitting results in worse performance. We compute the average difference between posteriors from the pLSA model, and observing this parameter, we can decide whether splitting is useful or not. This approach has been tested on eight object categories. Experimental results validate the benefit of splitting the training set.

Integration of multiple methods for class and specific object recognition

Service robots need object recognition strategy that can work on various objects and backgrounds. Since no single method can work well in various situations, we need to combine several methods so that the robots can use an appropriate one automatically. In this paper we propose a scheme to classify situations depending on the characteristics of object of interest, background and user demand. We classify the situations into three categories and employ different techniques for each one. We use SIFT and biologically motivated object recognition techniques developed by Serre et al. for two categories. These two methods do not work well on the remaining category of situations. We propose a contour based technique for this remaining category. Through our experiments, we show that the contour based method performs better than the previously mentioned two methods for this category of situations.

Recognition of household objects by service robots through interactive and autonomous methods

Service robots need to be able to recognize and identify objects located within complex backgrounds. Since no single method may work in every situation, several methods need to be combined. However, there are several cases when autonomous recognition methods fail. We propose several types of interactive recognition methods in those cases. Each one takes place at the failures of autonomous methods in different situations. We proposed four types of interactive methods such that robot may know the current situation and initiate the appropriate interaction with the user. Moreover we propose the grammar and sentence patterns for the instructions used by the user. We also propose an interactive learning process which can be used to learn or improve an object model through failures.

Object Recognition Based on Parallel Classifiers using Oriented Features

Service robots need object recognition strategy that can work on various objects and backgrounds. We need to combine several methods so that robot can use the appropriate one. In this paper we propose a scheme to classify the situations depending on the characteristics of object of interest, background and user demand. We classify the situations into two categories and employ different techniques for different groups. We use SIFT in a particular situation and propose a kernel principal component based technique for the remaining category which uses Gabor filters for feature extraction and multiple support vector classifiers. Through experiments, we show that our method performs better than a state-of-the-art technique for the remaining category.