Marcos Zúñiga

Video-understanding framework for automatic behavior recognition.

We propose an activity-monitoring framework based on a platform called VSIP, enabling behavior recognition in different environments. To allow end-users to actively participate in the development of a new application, VSIP separates algorithms from a priori knowledge. To describe how VSIP works, we present a full description of a system developed with this platform for recognizing behaviors, involving either isolated individuals, groups of people, or crowds, in the context of visual monitoring of metro scenes, using multiple cameras. In this work, we also illustrate the capability of the framework to easily combine and tune various recognition methods dedicated to the visual analysis of specific situations (e.g., mono-/multiactors’ activities, numerical/symbolic actions, or temporal scenarios). We also present other applications, using this framework, in the context of behavior recognition. VSIP has shown a good performance on human behavior recognition for different problems and configurations, being suitable to fulfill a large variety of requirements.

A graph-based immune-inspired constraint satisfaction search

We propose an artificial immune algorithm to solve constraint satisfaction problems (CSPs). Recently, bio-inspired algorithms have been proposed to solve CSPs. They have shown to be efficient in solving hard problem instances. Given that recent publications indicate that immune-inspired algorithms offer advantages to solve complex problems, our main goal is to propose an efficient immune algorithm which can solve CSPs. We have calibrated our algorithm using relevance estimation and value calibration (REVAC), which is a new technique recently introduced to find the parameter values for evolutionary algorithms. The tests were carried out using randomly generated binary constraint satisfaction problems and instances of the three-colouring problem with different constraint networks. The results suggest that the technique may be successfully applied to solve CSPs.

Three-dimensional immersive mixed-reality interface for structural design

A novel three-dimensional interface using immersive augmented reality to perform real-time visual analysis of structural models is presented. The interface integrates and builds on the functionalities of two commercial tools: ‘Leonar3Do’, for visual inspection in a fully three-dimensional immersive environment and ‘SAP 2000’, for structural analysis and simulation. The resulting interface allows the user to visualize the structural design model in three-dimensions, apply forces/loads directly with a three-dimensional physical pointer to indicate their magnitudes and directions and meanwhile observe the behavior of the structure under this action in fully perceived three-dimension. It integrates traditional structural analysis software, three-dimensional viewing and immersive virtual reality environment. The interface facilitates understanding of the different interactions between the structural components, detection of possible structural design weaknesses and improvement of the structural model in order to quickly develop better virtual prototypes.

Hierarchical and incremental event learning approach based on concept formation models

We propose an event learning approach for video, based on concept formation models. This approach incrementally learns on-line a hierarchy of states and event by aggregating the attribute values of tracked objects in the scene. The model can aggregate both numerical and symbolic values. The utilisation of symbolic attributes gives high flexibility to the approach. The approach also proposes the integration of attributes as a doublet value-reliability, for considering the effect in the event learning process of the uncertainty inherited from previous phases of the video analysis process. Simultaneously, the approach recognises the states and events of the tracked objects, giving a multi-level description of the object situation. The approach has been evaluated for an elderly care application and a rat behaviour analysis application. The results show that the approach is capable of learning and recognising meaningful events occurring in the scene, and to build a rich model of the objects behaviour. The results also show that the approach can give a description of the activities of a person (e.g. approaching to a table, crouching), and to detect abnormal events based on the frequency of occurrence.

Uncertainty Control for Reliable Video Understanding on Complex Environments

The most popular applications for video understanding are those related to video-surveillance (e.g. alarms, abnormal behaviours, expected events, access control). Video understanding has several other applications of high impact to the society as medical supervision, traffic control, violent acts detection, crowd behaviour analysis, among many others. We propose a new generic video understanding approach able to extract and learn valuable information from noisy video scenes for real-time applications. This approach comprises motion segmentation, object classification, tracking and event learning phases. This work is focused on building the first fundamental blocks allowing a proper management of uncertainty of data in every phase of the video understanding process. The main contributions of the proposed approach are: (i) a new algorithm for tracking multiple objects in noisy environments, (ii) the utilisation of reliability measures for modelling uncertainty in data and for proper selection of valuable information extracted from noisy data, (iii) the improved capability of tracking to manage multiple visual evidence-target associations, (iv) the combination of 2D image data with 3D information in a dynamics model governed by reliability measures for proper control of uncertainty in data, and (v) a new approach for event recognition through incremental event learning, driven by reliability measures for selecting the most stable and relevant data.

Real-time reliability measure-driven multi-hypothesis tracking using 2D and 3D features

We propose a new multi-target tracking approach, which is able to reliably track multiple objects even with poor segmentation results due to noisy environments. The approach takes advantage of a new dual object model combining 2D and 3D features through reliability measures. In order to obtain these 3D features, a new classifier associates an object class label to each moving region (e.g. person, vehicle), a parallelepiped model and visual reliability measures of its attributes. These reliability measures allow to properly weight the contribution of noisy, erroneous or false data in order to better maintain the integrity of the object dynamics model. Then, a new multi-target tracking algorithm uses these object descriptions to generate tracking hypotheses about the objects moving in the scene. This tracking approach is able to manage many-to-many visual target correspondences. For achieving this characteristic, the algorithm takes advantage of 3D models for merging dissociated visual evidence (moving regions) potentially corresponding to the same real object, according to previously obtained information. The tracking approach has been validated using video surveillance benchmarks publicly accessible. The obtained performance is real time and the results are competitive compared with other tracking algorithms, with minimal (or null) reconfiguration effort between different videos.

Incremental Video Event Learning

We propose a new approach for video event learning. The only hypothesis is the availability of tracked object attributes. The approach incrementally aggregates the attributes and reliability information of tracked objects to learn a hierarchy of state and event concepts. Simultaneously, the approach recognises the states and events of the tracked objects. This approach proposes an automatic bridge between the low-level image data and higher level conceptual information. The approach has been evaluated for more than two hours of an elderly care application. The results show the capability of the approach to learn and recognise meaningful events occurring in the scene. Also, the results show the potential of the approach for giving a description of the activities of a person (e.g. approaching to a table, crouching), and to detect abnormal events based on the frequency of occurrence.

Towards an immune system that solves CSP

Constraint satisfaction problems (CSPs) widely occur in artificial intelligence. In the last twenty years, many algorithms and heuristics were developed to solve CSP. Recently, bio-inspired algorithms have been proposed to solve CSP. They have shown to be more efficient than systematic approaches in solving hard instances. Given that recent publications indicate that Immune systems offer advantages to solve complex problems, our aim here is to propose an efficient immune system which can solve CSPs. We propose an immune system which is able to solve hard constraint satisfaction problems. The tests were carried out using random generated binary constraint satisfaction problems on the transition phase.

A Computer Application for Drone Parametrization: Developing Solution for Drone Manufacturing

In this article, a solution for parametrization of drone parts by following a structured approach is proposed. Through this research, the authors attempt to contribute with a solution for those users that can have a 3D printer, but not necessarily have the specific knowledge to create appropriate parts for their drone or related modifications. A master 3D model has been created, which can be modified through a simple user interface, allowing to modify the general 3D model. The solution aims to manufacture the master model according to different drone sizes.

Enhancing creativity for development of automation solutions using OTSM-TRIZ: A systematic case study in agronomic industry

The article describes a method to stimulate users’ creativity within constraint-based scenarios and OTSM-TRIZ, which allows to define the problems and partial solutions to be solved during the design process in an appropriate manner. The proposed method aims to overcome constraints and problems defined within product development and related organization resources. Indeed, if these constraints are not properly taken into account, the risk of generating unsuccessful and even ineffective solutions can be high. In this work, a method has been defined, based on the OTSM-TRIZ theory: it guides the users toward the problem solution through a mapping of both the problem to solve and the relationships existing among the problems and constraints. A step-by-step approach is used to describe and propose a systematic structure, allowing to link the conceptual solution with specific solution criteria in the automation field. The validation of the proposed method corresponds to a real case study, that is, the necessity of increasing the productivity of an operational plant for the palletizing process has been selected to discuss the method implementation. Finally, the results of the case study were considered successful, because it was not necessary to introduce high investments for solution development and implementation.