Interactive Object Learning and Recognition with Multiclass Support Vector Machines

In this paper we describe the first stage of a new learning system for object detection and recognition. For our system we propose Boosting [5] as the underlying learning technique. This allows the use of very diverse sets of visual features in the learning process within a common framework: Boosting — together with a weak hypotheses finder — may choose very inhomogeneous features as most relevant for combination into a final hypothesis. As another advantage the weak hypotheses finder may search the weak hypotheses space without explicit calculation of all available hypotheses, reducing computation time. This contrasts the related work of Agarwal and Roth [1] where Winnow was used as learning algorithm and all weak hypotheses were calculated explicitly. In our first empirical evaluation we use four types of local descriptors: two basic ones consisting of a set of grayvalues and intensity moments and two high level descriptors: moment invariants [8] and SIFTs [12]. The descriptors are calculated from local patches detected by an interest point operator. The weak hypotheses finder selects one of the local patches and one type of local descriptor and efficiently searches for the most discriminative similarity threshold. This differs from other work on Boosting for object recognition where simple rectangular hypotheses [22] or complex classifiers [20] have been used. In relatively simple images, where the objects are prominent, our approach yields results comparable to the state-of-the-art [3]. But we also obtain very good results on more complex images, where the objects are located in arbitrary positions, poses, and scales in the images. These results indicate that our flexible approach, which also allows the inclusion of features from segmented regions and even spatial relationships, leads us a significant step towards generic object recognition.

Identification of objects in a real world plays a key role for human-computer interaction in a computer-augmented environment using augmented reality techniques. For providing natural interaction in such environments, it is necessary for an interface system to know which objects a user is using. In the previously developed interface systems, real objects are identified by using specially designed tags attached to objects. In this work, we propose a new method for interactive object recognition and registration for more natural and intuitive interaction without using any tags. In particular, we introduce interactive object registration and recognition by combining direct manipulation with user's hands and a color-based object recognition algorithm.

Traditionally, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. As supported by our human studies, this contextual information is necessary for accurate recognition in low resolution images. This scenario with impoverished appearance information, as opposed to using images of higher resolution, provides an appropriate venue for studying the role of context in recognition. In this paper, we explore the role of context for dense scene labeling in small images. Given a segmentation of an image, our algorithm assigns each segment to an object category based on the segment’s appearance and contextual information. We explicitly model context between object categories through the use of relative location and relative scale, in addition to co-occurrence. We perform recognition tests on low and high resolution images, which vary significantly in the amount of appearance information present, using just the object appearance information, the combination of appearance and context, as well as just context without object appearance information (blind recognition). We also perform these tests in human studies and analyze our findings to reveal interesting patterns. With the use of our context model, our algorithm achieves state-of-the-art performance on MSRC and Corel. datasets.

Object recognition is a typical task of aerial reconnaissance and especially in military applications, to determine the class of an unknown object on the battlefield can give valuable information on its capabilities and its threat. RecceMan (Reconnaissance Manual) is a decision support system for object recognition developed by the Fraunhofer IOSB. It supports object recognition by automating the tedious task of matching the object features with the set of possible object classes, while leaving the assessment of features to the trained human interpreter. The quality of the features assessed by the user is influenced by several factors such as the quality of the image of the object. These factors are potential sources of error, which can lead to an incorrect classification and therefore have to be considered by the system. To address this issue, two methods for consideration of uncertainty in human feature assessment - a probabilistic and a heuristic approach - are presented and compared based on an experiment in the exemplary domain of flower recognition.

This paper describes the design of an integrated system for humanoid robotics that consists of three key components, 3D vision, motion planning and bipedal control. Layered system design is adopted to achieve concurrency as well as small latency. Implementation using our humanoid type robot H7 and experiments with this architecture are described. The H7 is expected to be a common test-bed in experiments and discussion for various aspects of intelligent humanoid robotics.

General object recognition is specific: Evidence from novel and familiar objects

With the development of the concept of Industry 4.0, research relating to robots is being paid more and more attention, among which the humanoid robot is a very important research topic. The humanoid robot is a robot with a bipedal mechanism. Due to the physical mechanism, humanoid robots can maneuver more easily in complex terrains, such as going up and down the stairs. However, humanoid robots often fall from imbalance. Whether or not the robot can stand up on its own after a fall is a key research issue. However, the often used method of hand tuning to allow robots to stand on its own is very inefficient. In order to solve the above problems, this paper proposes an automatic learning system based on Particle Swarm Optimization (PSO). This system allows the robot to learn how to achieve the motion of rebalancing after a fall. To allow the robot to have the capability of object recognition, this paper also applies the Convolutional Neural Network (CNN) to let the robot perform image recognition and successfully distinguish between 10 types of objects. The effectiveness and feasibility of the motion learning algorithm and the CNN based image classification for vision system proposed in this paper has been confirmed in the experimental results.

An effective human-robot interaction is essential for wide penetration of service robots into the market. Such robot needs a vision system to recognize objects. It is, however, difficult to realize vision systems that can work in various conditions. More robust techniques of object recognition and image segmentation are essential. Thus, we have proposed to use the human user's assistance for objects recognition through speech. This paper presents a system that recognizes objects in occlusion and/or multicolor cases using geometric and photometric analysis of images. Based on the analysis results, the system makes a hypothesis of the scene. Then, it asks the user for confirmation by describing the hypothesis. If the hypothesis is not correct, the system generates another hypothesis until it correctly understands the scene. Through experiments on a real mobile robot, we have confirmed the usefulness of the system.

Primal access recognition of visual objects (PARVO), a computer vision system that addresses the problem of fast and generic recognition of unexpected 3D objects from single 2D views, is considered. Recently, recognition by components (RBC), which is a new human image understanding theory, based on some psychological results, has been proposed as an explanation of how PARVO works. However, no systematic computational evaluation of its many aspects has yet been reported. The PARVO system discussed is a first step toward this goal, since its design respects and makes explicit the main assumptions of the proposed theory. It analyzes single-view 2D line drawings of 3D objects typical of the ones used in human image understanding studies. It is designed to handle partially occluded objects of different shape and dimension in various spatial orientations and locations in the image plane. The system is shown to successfully compute generic descriptions and then recognize many common man-made objects.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Humanoid robots are becoming increasingly competent in perception of their surroundings and in providing intelligent responses to worldly events. A popular paradigm to realize such responses is the idea of attention itself. There are two important aspects of attention in the context of humanoid robots. First, perception describes how to design the sensory system to filter out useful salient features in the sensory field and perform subsequent higher level processing to perform tasks such as face recognition. Second, the behavioral response defines how the humanoid should act when it encounters the salient features. A model of attention enables the humanoid to achieve a semblance of liveliness that goes beyond exhibiting a mechanized repertoire of responses. It also facilitates progress in realizingmodels of higher-level cognitive processes such as having people direct the robot’s attention to a specific target stimulus(Cynthia et al., 2001). Studies indicate that humans employ attention as a mechanism for preventing sensory overload(Tsotsos et al., 2005),(Komatsu, 1994) – a finding which is relevant to robotics given that information bandwidth is often a concern. The neurobiologically inspired models of Itti (Tsotsos et al., 2005), initially developed for modeling visual attention have been improved(Dhavale et al., 2003) and their scope has been broadened to include even auditory modes of attention(Kayser et al., 2008). Such models have formed the basis of multi-modal attention mechanisms in (humanoid) robots(Maragos, 2008),(Rapantzikos, 2007). Typical implementations of visual attention mechanisms employ a bottom-up processing of camera images to arrive at the so-called map, which encodes the unconstrained salience of the scene. Salient regions identified from saliency map are processed by higher-level modules such as object and face recognition. The results of these modules are then used as referential entities for the task at hand(e.g. acknowledging a familiar face, noting the location of a recognized object). Building upon the recent additions to Itti’s original model(Tsotsos et al., 2005), some implementations also use top-down control mechanisms to constrain the salience(Cynthia et al., 2001),(Navalpakkam and Itti, 2005),(Moren et al., 2008). In most of the implementations, the cameras are held fixed, simplifying processing and consequent attention mechanism modeling. However, this restricts the visual scope of attention, particularly in situations when the robot has to interact with multiple people who may be spread beyond its limited field-of-view. Moreover, they may choose to advertise their presence through a non-visual modality such as speech utterances. Attempts to overcome this situation lead naturally to the idea of widening the visual scope and therefore, to the idea of a panoramic attention. In most of the implementations which 11

In the context of improved navigation for micro aerial vehicles, a new scene recognition visual descriptor, called spatial color gist wavelet descriptor (SCGWD), is proposed. SCGWD was developed by combining proposed Ohta color-GIST wavelet descriptors with census transform histogram (CENTRIST) spatial pyramid representation descriptors for categorizing indoor versus outdoor scenes. A binary and multiclass support vector machine (SVM) classifier with linear and non-linear kernels was used to classify indoor versus outdoor scenes and indoor scenes, respectively. In this paper, we have also discussed the feature extraction methodology of several, state-of-the-art visual descriptors, and four proposed visual descriptors (Ohta color-GIST descriptors, Ohta color-GIST wavelet descriptors, enhanced Ohta color histogram descriptors, and SCGWDs), in terms of experimental perspectives. The proposed enhanced Ohta color histogram descriptors, Ohta color-GIST descriptors, Ohta color-GIST wavelet descriptors, SCGWD, and state-of-the-art visual descriptors were evaluated, using the Indian Institute of Technology Madras Scene Classification Image Database two, an Indoor-Outdoor Dataset, and the Massachusetts Institute of Technology indoor scene classification dataset [(MIT)-67]. Experimental results showed that the indoor versus outdoor scene recognition algorithm, employing SVM with SCGWDs, produced the highest classification rates (CRs)—95.48% and 99.82% using radial basis function kernel (RBF) kernel and 95.29% and 99.45% using linear kernel for the IITM SCID2 and Indoor-Outdoor datasets, respectively. The lowest CRs—2.08% and 4.92%, respectively—were obtained when RBF and linear kernels were used with the MIT-67 dataset. In addition, higher CRs, precision, recall, and area under the receiver operating characteristic curve values were obtained for the proposed SCGWDs, in comparison with state-of-the-art visual descriptors.

This paper describes a hybrid brain-computer interface (BCI) technique that combines the P300 potential, the steady state visually evoked potential (SSVEP), and event related de-synchronization (ERD) to solve a complicated multi-task problem consisting of humanoid robot navigation and control along with object recognition using a low-cost BCI system. Our approach enables subjects to control the navigation and exploration of a humanoid robot and recognize a desired object among candidates. This study aims to demonstrate the possibility of a hybrid BCI based on a low-cost system for a realistic and complex task. It also shows that the use of a simple image processing technique, combined with BCI, can further aid in making these complex tasks simpler. An experimental scenario is proposed in which a subject remotely controls a humanoid robot in a properly sized maze. The subject sees what the surrogate robot sees through visual feedback and can navigate the surrogate robot. While navigating, the robot encounters objects located in the maze. It then recognizes if the encountered object is of interest to the subject. The subject communicates with the robot through SSVEP and ERD-based BCIs to navigate and explore with the robot, and P300-based BCI to allow the surrogate robot recognize their favorites. Using several evaluation metrics, the performances of five subjects navigating the robot were quite comparable to manual keyboard control. During object recognition mode, favorite objects were successfully selected from two to four choices. Subjects conducted humanoid navigation and recognition tasks as if they embodied the robot. Analysis of the data supports the potential usefulness of the proposed hybrid BCI system for extended applications. This work presents an important implication for the future work that a hybridization of simple BCI protocols provide extended controllability to carry out complicated tasks even with a low-cost system.

A neural multiclassifier system for object recognition in robotic vision applications

We explore the use of holistic shape matching for recognition using bottom-up image structures such as image contours, for object shape detection and segmentation. Holistic shape matching utilizes global information about object shape for matching, rather than local image features which often contain too little information to match reliably to the object model. By examining several different tasks related to object recognition, we demonstrate the value of holistic shape matching in a broad range of problems, including perceptual grouping, human pose estimation, and generic object recognition.

The visual recognition problem is central to computer vision research. From robotics to information retrieval, many desired applications demand the ability to identify and localize categories, places, and objects. This tutorial overviews computer vision algorithms for visual object recognition and image classification. We introduce primary representations and learning approaches, with an emphasis on recent advances in the field. The target audience consists of researchers or students working in AI, robotics, or vision who would like to understand what methods and representations are available for these problems. This lecture summarizes what is and isn't possible to do reliably today, and overviews key concepts that could be employed in systems requiring visual categorization. Table of Contents: Introduction / Overview: Recognition of Specific Objects / Local Features: Detection and Description / Matching Local Features / Geometric Verification of Matched Features / Example Systems: Specific-Object Recognition / Overview: Recognition of Generic Object Categories / Representations for Object Categories / Generic Object Detection: Finding and Scoring Candidates / Learning Generic Object Category Models / Example Systems: Generic Object Recognition / Other Considerations and Current Challenges / Conclusions