Paulo G. Costa

A Flow-based Motion Perception Technique for an Autonomous Robot System

Visual motion perception from a moving observer is the most often encountered case in real life situations. It is a complex and challenging problem, although, it can promote the arising of new applications. This article presents an innovative and autonomous robotic system designed for active surveillance and a dense optical flow technique. Several optical flow techniques have been proposed for motion perception however, most of them are too computationally demanding for autonomous mobile systems. The proposed HybridTree method is able to identify the intrinsic nature of the motion by performing two consecutive operations: expectation and sensing. Descriptive properties of the image are retrieved using a tree-based scheme and during the expectation phase. In the sensing operation, the properties of image regions are used by a hybrid and hierarchical optical flow structure to estimate the flow field. The experiments prove that the proposed method extracts reliable visual motion information in a short period of time and is more suitable for applications that do not have specialized computer devices. Therefore, the HybridTree differs from other techniques since it introduces a new perspective for the motion perception computation: high level information about the image sequence is integrated into the estimation of the optical flow. In addition, it meets most of the robotic or surveillance demands and the resulting flow field is less computationally demanding comparatively to other state-of-the-art methods.

Enhancing dynamic videos for surveillance and robotic applications: The robust bilateral and temporal filter

Over the last few decades, surveillance applications have been an extremely useful tool to prevent dangerous situations and to identify abnormal activities. Although, the majority of surveillance videos are often subjected to different noises that corrupt structured patterns and fine edges. This makes the image processing methods even more difficult, for instance, object detection, motion segmentation, tracking, identification and recognition of humans. This paper proposes a novel filtering technique named robust bilateral and temporal (RBLT), which resorts to a spatial and temporal evolution of sequences to conduct the filtering process while preserving relevant image information. A pixel value is estimated using a robust combination of spatial characteristics of the pixels neighborhood and its own temporal evolution. Thus, robust statics concepts and temporal correlation between consecutive images are incorporated together which results in a reliable and configurable filter formulation that makes it possible to reconstruct highly dynamic and degraded image sequences. The filtering is evaluated using qualitative judgments and several assessment metrics, for different Gaussian and Salt-Pepper noise conditions. Extensive experiments considering videos obtained by stationary and non-stationary cameras prove that the proposed technique achieves a good perceptual quality of filtering sequences corrupted with a strong noise component.

Tracking and Identifying in Real Time the Robots of a F-180 Team

This paper describes the method employed to track and identify each robot during a Robocup match. Also, the playing ball is tracked with almost no extra processing effort. To track the robots it is necessary the use of adequate markers so that not only the position is extracted but also the heading. We discuss the difficulties associated with this problem, various possible approaches and justify our solution. The identification is performed thanks to a minimalist bar code placed in each robot. The bar code solves the problem of resolving some ambiguities that can arise in certain configurations. The procedure described can be executed in real time as it was shown in Paris in RoboCup-98.

5dpo-2000 Team Description

This paper describes the 5dpo-2000 team. The paper will be divided into three main sections, corresponding to three main blocks: the Global Level, the Local Level and the Interface Level. These Levels, their subsystems and some implementation details will be described next.

Modeling and Simulation of a Hacked Neato XV-11 Laser Scanner

Laser scanners are widely used in mobile robotics localization systems but, despite the enormous potential of its use, their high price tag is a major drawback, mainly for hobbyist and educational robotics practitioners that usually have a reduced budget. This paper presentes the modeling and simulation of a hacked Neato XV-11 Laser Scanner, having as motivation the fact that it is a very low cost alternative, when compared with the current available laser scanners. The modeling of a hacked Neato XV-11 Laser Scanner allows its realistic simulation and provides valuable information that can promote the development of better designs of robot localization systems based on this sensor. The sensor simulation was developed using SimTwo, which is a realistic simulation software that can support several types of robots.

Evaluation of Depth Sensors for Robotic Applications

The sensors that acquire 3D data play an important role in many applications. In addition, they have been used in the robotic field for several purposes, for instance, enhancing the navigation of mobile robots, object detection, scene reconstruction, 3D inspection of parts and others. Moreover, a significant amount of devices with distinct cost, accuracy and features have been released in the recent years which increases the difficulty of comparing each sensor in a proper manner or choosing the most suitable device for a specific task and operation field. This paper compares the Kinect v1, Kinect v2, Structure Sensor and Mesa Imaging SR4000. The noise of each sensor is characterized for different distances and considering objects with different colors. Therefore, this paper proposes a simple but quantitative benchmark for evaluating 3D devices that characterizes the most relevant features for the robotic field and in accordance with different type of operations.

Robust Robot Localization Based on the Perfect Match Algorithm

Self-localization of a robot in an indoor plant is one of the most important requirement in mobile robotics. This paper addresses the application and improvement of a well known localization algorithm used in Robocup Midsize league competition in real service and industrial robots. This new robust approach is based on modeling the quality of several measures and minimizing the maching error. The presented innovative work applies the robotic football knowledge to other fields with high accuracy. Real and simulated results allow to validate the proposed methodology.

An architecture for visual motion perception of a surveillance-based autonomous robot

This research presents an innovative mobile robotic system designed for active surveillance operations. This mobile robot moves along a rail and is equipped with a monocular camera. Thus, it enhances the surveillance capability when compared to conventional systems (mainly composed by multiple static cameras). In addition, the paper proposes a technique for multi-object tracking called MTMP (Multi-Tracking of Motion Profiles). The MTMP resorts to a formulation based on the Kalman filter and tracks several moving objects using motion profiles. A motion profile is characterized by the dominant flow vector and is computed using the optical flow signature with removal of outliers. A similarity measure based on the Mahalanobis distance is used by the MTMP for associating the moving objects over frames. The experiments conducted in realistic environments have proved that the static perception mode of the proposed robot is able to detect and track multiple moving objects in a short period of time and without using specialized computers. In addition, the MTMP exhibits a good computational performance since it takes less than 5 milliseconds to compute. Therefore, results show that the estimation of motion profiles is suitable for analyzing motion on image sequences.

Unsupervised flow-based motion analysis for an autonomous moving system ☆

Abstract This article discusses the motion analysis based on dense optical flow fields and for a new generation of robotic moving systems with real-time constraints. It focuses on a surveillance scenario where an especially designed autonomous mobile robot uses a monocular camera for perceiving motion in the environment. The computational resources and the processing-time are two of the most critical aspects in robotics and therefore, two non-parametric techniques are proposed, namely, the Hybrid Hierarchical Optical Flow Segmentation and the Hybrid Density-Based Optical Flow Segmentation. Both methods are able to extract the moving objects by performing two consecutive operations: refining and collecting. During the refining phase, the flow field is decomposed in a set of clusters and based on descriptive motion properties. These properties are used in the collecting stage by a hierarchical or density-based scheme to merge the set of clusters that represent different motion models. In addition, a model selection method is introduced. This novel method analyzes the flow field and estimates the number of distinct moving objects using a Bayesian formulation. The research evaluates the performance achieved by the methods in a realistic surveillance situation. The experiments conducted proved that the proposed methods extract reliable motion information in real-time and without using specialized computers. Moreover, the resulting segmentation is less computationally demanding compared to other recent methods and therefore, they are suitable for most of the robotic or surveillance applications.

Self localization of an autonomous robot: using an EKF to merge odometry and vision based landmarks

Localization is essential to modern autonomous robots in order to enable effective completion of complex tasks over possibly large distances in low structured environments. In this paper, a extended Kalman filter is used in order to implement self-localization. This is done by merging odometry and localization information, when available. The used landmarks are colored poles that can be recognized while the robot moves around performing normal tasks. This paper models measurements with very different characteristics in distance and angle to markers and shows results of the self-localization method. Results of simulations and real robot tests are shown