Mario Fernando Montenegro Campos

STOP: Space-Time Occupancy Patterns for 3D Action Recognition from Depth Map Sequences

This paper presents Space-Time Occupancy Patterns (STOP), a new visual representation for 3D action recognition from sequences of depth maps. In this new representation, space and time axes are divided into multiple segments to define a 4D grid for each depth map sequence. The advantage of STOP is that it preserves spatial and temporal contextual information between space-time cells while being flexible enough to accommodate intra-action variations. Our visual representation is validated with experiments on a public 3D human action dataset. For the challenging cross-subject test, we significantly improved the recognition accuracy from the previously reported 74.7% to 84.8%. Furthermore, we present an automatic segmentation and time alignment method for online recognition of depth sequences.

Dynamic role assignment for cooperative robots

Proposes a methodology for coordinating multi-robot teams in the execution of cooperative tasks. It is based on a dynamic role-assignment mechanism in which the robots assume and exchange roles during cooperation. We model the role assignment under a hybrid systems framework, using a hybrid automaton to represent roles, transitions and controllers. Using a multi-robot simulator, the methodology is demonstrated in a cooperative transportation task, in which a group of robots must find and cooperatively transport several objects scattered in the environment.

Decentralized Algorithms for Multi-Robot Manipulation via Caging

In this paper we address the problem of transporting objects with multiple mobile robots using the concept of “object closure”. In contrast to other manipulation techniques that are typically derived from form or force closure constraints, object closure requires the less stringent condition that the object be trapped or caged by the robots. Our basic goal in this paper is to develop decentralized control policies for a group of robots to move toward a goal position while maintaining a condition of object closure. We present experimental results that show polygonal mobile robots controlled using visual feedback, transporting a convex polygonal object in an obstacle free environment toward a prescribed goal.

A Paradigm for Dynamic Coordination of Multiple Robots

In this paper, we present a paradigm for coordinating multiple robots in the execution of cooperative tasks. The basic idea in the paper is to assign to each robot in the team, a role that determines its actions during the cooperation. The robots dynamically assume and exchange roles in a synchronized manner in order to perform the task successfully, adapting to unexpected events in the environment. We model this mechanism using a hybrid systems framework and apply it in different cooperative tasks: cooperative manipulation and cooperative search and transportation. Simulations and real experiments demonstrating the effectiveness of the proposed paradigm are presented.

Real-Time Gesture Recognition from Depth Data through Key Poses Learning and Decision Forests

Human gesture recognition is a challenging task with many applications. The popularization of real time depth sensors even diversifies potential applications to end-user natural user interface (NUI). The quality of such NUI highly depends on the robustness and execution speed of the gesture recognition. This work introduces a method for real-time gesture recognition from a noisy skeleton stream, such as the ones extracted from Kinect depth sensors. Each pose is described using a tailored angular representation of the skeleton joints. Those descriptors serve to identify key poses through a multi-class classifier derived from Support Vector learning machines. The gesture is labeled on-the-fly from the key pose sequence through a decision forest, that naturally performs the gesture time warping and avoids the requirement for an initial or neutral pose. The proposed method runs in real time and shows robustness in several experiments.

Transmission Estimation in Underwater Single Images

This paper proposes a methodology to estimate the transmission in underwater environments which consists on an adaptation of the Dark Channel Prior (DCP), a statistical prior based on properties of images obtained in outdoor natural scenes. Our methodology, called Underwater DCP (UDCP), basically considers that the blue and green color channels are the underwater visual information source, which enables a significant improvement over existing methods based in DCP. This is shown through a comparative study with state of the art techniques, we present a detailed analysis of our technique which shows its applicability and limitations in images acquired from real and simulated scenes.

Particle Filter-Based Predictive Tracking for Robust Fish Counting

In this paper we study the use of computer vision techniques for for underwater visual tracking and counting of fishes in vivo. The methodology is based on the application of a Bayesian filtering technique that enables tracking of objects whose number may vary over time. Unlike existing fish-counting methods, this approach provides adequate means for the acquisition of relevant information about characteristics of different fish species such as swimming ability, time of migration and peak flow rates. The system is also able to estimate fish trajectories over time, which can be further used to study their behaviors when swimming in regions of interest. Our experiments demonstrate that the proposed method can operate reliably under severe environmental changes (e.g. variations in water turbidity) and handle problems such as occlusions or large inter-frame motions. The proposed approach was successfully validated with real-world video streams, achieving overall accuracy as high as 81%.

Decentralized Algorithms for Multirobot Manipulation via Caging

This paper addresses the problem of transporting objects with multiple mobile robots using the concept of object closure. In contrast to other manipulation techniques that are typically derived from form or force closure constraints, object closure requires the less stringent condition that the object be trapped or caged by the robots. Our basic goal in this paper is to develop decentralized control policies for a group of robots to achieve a condition of object closure, and then, move toward a goal position while maintaining this condition. We present experimental results that show car-like robots controlled using visual feedback, transporting an object in an obstacle free environment toward a prescribed goal.

Cooperative Transport of Planar Objects by Multiple Mobile Robots Using Object Closure

This paper addresses the problem of transporting objects by multiple mobile robots using the concept of object closure. In contrast to other manipulation techniques that are typically derived from form or force closure constraints, object closure requires the less stringent condition that the object be trapped or caged by the robots. We present experimental results that show car-like robots controlled using visual feedback, transporting an object in an obstacle free environment toward a prescribed goal.

Coordination of multiple mobile robots in an object carrying task using implicit communication

Addresses the problem of coordinating multiple mobile robots in a tightly coupled task by means of implicit communication. This approach allows the development of controllers that do not depend on any explicit data flow between the robots, thus relying only on local sensor information. A box-carrying task is used to validate the proposed methodology both in simulation and in real-world experiments. Results show that implicit communication can be used together or replacing explicit communication for the cooperative box carrying task, making the system more robust to faulty communication environments.