Miguel Oliveira

Unsupervised local color correction for coarsely registered images

The current paper proposes a new parametric local color correction technique. Initially, several color transfer functions are computed from the output of the mean shift color segmentation algorithm. Secondly, color influence maps are calculated. Finally, the contribution of every color transfer function is merged using the weights from the color influence maps. The proposed approach is compared with both global and local color correction approaches. Results show that our method outperforms the technique ranked first in a recent performance evaluation on this topic. Moreover, the proposed approach is computed in about one tenth of the time.

A perceptual memory system for grounding semantic representations in intelligent service robots

This paper addresses the problem of grounding semantic representations in intelligent service robots. In particular, this work contributes to addressing two important aspects, namely the anchoring of object symbols into the perception of the objects and the grounding of object category symbols into the perception of known instances of the categories. The paper discusses memory requirements for storing both semantic and perceptual data and, based on the analysis of these requirements, proposes an approach based on two memory components, namely a semantic memory and a perceptual memory. The perception, memory, learning and interaction capabilities, and the perceptual memory, are the main focus of the paper. Three main design options address the key computational issues involved in processing and storing perception data: a lightweight, NoSQL database, is used to implement the perceptual memory; a thread-based approach with zero copy transport of messages is used in implementing the modules; and a multiplexing scheme, for the processing of the different objects in the scene, enables parallelization. The system is designed to acquire new object categories in an incremental and open-ended way based on user-mediated experiences. The system is fully integrated in a broader robot system comprising low-level control and reactivity to high-level reasoning and learning.

Interactive Open-Ended Learning for 3D Object Recognition: An Approach and Experiments

Abstract3D object detection and recognition is increasingly used for manipulation and navigation tasks in service robots. It involves segmenting the objects present in a scene, estimating a feature descriptor for the object view and, finally, recognizing the object view by comparing it to the known object categories. This paper presents an efficient approach capable of learning and recognizing object categories in an interactive and open-ended manner. In this paper, “open-ended” implies that the set of object categories to be learned is not known in advance. The training instances are extracted from on-line experiences of a robot, and thus become gradually available over time, rather than at the beginning of the learning process. This paper focuses on two state-of-the-art questions: (1) How to automatically detect, conceptualize and recognize objects in 3D scenes in an open-ended manner? (2) How to acquire and use high-level knowledge obtained from the interaction with human users, namely when they provide category labels, in order to improve the system performance? This approach starts with a pre-processing step to remove irrelevant data and prepare a suitable point cloud for the subsequent processing. Clustering is then applied to detect object candidates, and object views are described based on a 3D shape descriptor called spin-image. Finally, a nearest-neighbor classification rule is used to predict the categories of the detected objects. A leave-one-out cross validation algorithm is used to compute precision and recall, in a classical off-line evaluation setting, for different system parameters. Also, an on-line evaluation protocol is used to assess the performance of the system in an open-ended setting. Results show that the proposed system is able to interact with human users, learning new object categories continuously over time.

3D object perception and perceptual learning in the RACE project

This paper describes a 3D object perception and perceptual learning system developed for a complex artificial cognitive agent working in a restaurant scenario. This system, developed within the scope of the European project RACE, integrates detection, tracking, learning and recognition of tabletop objects. Interaction capabilities were also developed to enable a human user to take the role of instructor and teach new object categories. Thus, the system learns in an incremental and open-ended way from user-mediated experiences. Based on the analysis of memory requirements for storing both semantic and perceptual data, a dual memory approach, comprising a semantic memory and a perceptual memory, was adopted. The perceptual memory is the central data structure of the described perception and learning system. The goal of this paper is twofold: on one hand, we provide a thorough description of the developed system, starting with motivations, cognitive considerations and architecture design, then providing details on the developed modules, and finally presenting a detailed evaluation of the system; on the other hand, we emphasize the crucial importance of the Point Cloud Library (PCL) for developing such system.11This paper is a revised and extended version of Oliveira et?al. (2014). We describe an object perception and perceptual learning system.The system is able to detect, track and recognize tabletop objects.The system learns novel object categories in an open-ended fashion.The Point Cloud Library is used in nearly all modules of the system.The system was developed and used in the European project RACE.

Interactive teaching and experience extraction for learning about objects and robot activities

Intelligent service robots should be able to improve their knowledge from accumulated experiences through continuous interaction with the environment, and in particular with humans. A human user may guide the process of experience acquisition, teaching new concepts, or correcting insufficient or erroneous concepts through interaction. This paper reports on work towards interactive learning of objects and robot activities in an incremental and open-ended way. In particular, this paper addresses human-robot interaction and experience gathering. The robots ontology is extended with concepts for representing human-robot interactions as well as the experiences of the robot. The human-robot interaction ontology includes not only instructor teaching activities but also robot activities to support appropriate feedback from the robot. Two simplified interfaces are implemented for the different types of instructions including the teach instruction, which triggers the robot to extract experiences. These experiences, both in the robot activity domain and in the perceptual domain, are extracted and stored in memory, and they are used as input for learning methods. The functionalities described above are completely integrated in a robot architecture, and are demonstrated in a PR2 robot.

A Probabilistic Approach for Color Correction in Image Mosaicking Applications

Image mosaicking applications require both geometrical and photometrical registrations between the images that compose the mosaic. This paper proposes a probabilistic color correction algorithm for correcting the photometrical disparities. First, the image to be color corrected is segmented into several regions using mean shift. Then, connected regions are extracted using a region fusion algorithm. Local joint image histograms of each region are modeled as collections of truncated Gaussians using a maximum likelihood estimation procedure. Then, local color palette mapping functions are computed using these sets of Gaussians. The color correction is performed by applying those functions to all the regions of the image. An extensive comparison with ten other state of the art color correction algorithms is presented, using two different image pair data sets. Results show that the proposed approach obtains the best average scores in both data sets and evaluation metrics and is also the most robust to failures.

ATLASCAR - technologies for a computer assisted driving system on board a common automobile

The future of intelligent vehicles will rely on robust information to allow the proper feedback to the vehicle itself, to issue several kinds of active safety, but before all, to generate information for the driver by calling his or her attention to potential instantaneous or mid-term risks associated with the driving. Before true vehicle autonomy, safety and driver assistance are a priority. Sophisticated sensorial and perceptive mechanisms must be made available for, in a first instance, assisting the driver and, on a latter phase, participate in better autonomy. These mechanisms rely on sensors and algorithms that are mostly available nowadays, but many of them are still unsuited for critical situations. This paper presents a project where engineering and scientific solutions have been devised to settle a full featured real scale platform for the next generation of ITS vehicles that are concerned with the immediate issues of navigation and challenges on the road. The car is now ready and running, and the data gathering has just begun.

Wavelet-Based Visible and Infrared Image Fusion: A Comparative Study.

This paper evaluates different wavelet-based cross-spectral image fusion strategies adopted to merge visible and infrared images. The objective is to find the best setup independently of the evaluation metric used to measure the performance. Quantitative performance results are obtained with state of the art approaches together with adaptations proposed in the current work. The options evaluated in the current work result from the combination of different setups in the wavelet image decomposition stage together with different fusion strategies for the final merging stage that generates the resulting representation. Most of the approaches evaluate results according to the application for which they are intended for. Sometimes a human observer is selected to judge the quality of the obtained results. In the current work, quantitative values are considered in order to find correlations between setups and performance of obtained results; these correlations can be used to define a criteria for selecting the best fusion strategy for a given pair of cross-spectral images. The whole procedure is evaluated with a large set of correctly registered visible and infrared image pairs, including both Near InfraRed (NIR) and Long Wave InfraRed (LWIR).

Multimodal inverse perspective mapping

Over the past years, inverse perspective mapping has been successfully applied to several problems in the field of Intelligent Transportation Systems. In brief, the method consists of mapping images to a new coordinate system where perspective effects are removed. The removal of perspective associated effects facilitates road and obstacle detection and also assists in free space estimation. There is, however, a significant limitation in the inverse perspective mapping: the presence of obstacles on the road disrupts the effectiveness of the mapping. The current paper proposes a robust solution based on the use of multimodal sensor fusion. Data from a laser range finder is fused with images from the cameras, so that the mapping is not computed in the regions where obstacles are present. As shown in the results, this considerably improves the effectiveness of the algorithm and reduces computation time when compared with the classical inverse perspective mapping. Furthermore, the proposed approach is also able to cope with several cameras with different lenses or image resolutions, as well as dynamic viewpoints.

GOOD: A global orthographic object descriptor for 3D object recognition and manipulation

Abstract Object representation is one of the most challenging tasks in robotics because it must provide reliable information in real-time to enable the robot to physically interact with the objects in its environment. To ensure robustness, a global object descriptor must be computed based on a unique and repeatable object reference frame. Moreover, the descriptor should contain enough information enabling to recognize the same or similar objects seen from different perspectives. This paper presents a new object descriptor named Global Orthographic Object Descriptor (GOOD) designed to be robust, descriptive and efficient to compute and use. We propose a novel sign disambiguation method, for computing a unique reference frame from the eigenvectors obtained through Principal Component Analysis of the point cloud of the target object view captured by a 3D sensor. Three principal orthographic projections and their distribution matrices are computed by exploiting the object reference frame. The descriptor is finally obtained by concatenating the distribution matrices in a sequence determined by entropy and variance features of the projections. Experimental results show that the overall classification performance obtained with GOOD is comparable to the best performances obtained with the state-of-the-art descriptors. Concerning memory and computation time, GOOD clearly outperforms the other descriptors. Therefore, GOOD is especially suited for real-time applications. The estimated object’s pose is precise enough for real-time object manipulation tasks.