Roberto M. Cesar-Jr

Visual rhythm-based plankton detection method for ballast water quality assessment

The ballast water transported by commercial ships is one of the major un-natural means of species dispersal in aquatic ecosystems. An important technological challenge for monitoring ballast water standards concerns the establishment of analytical techniques that generate reliable results on organisms concentration, size and viability quickly and without the need for intensive manual work of specialists. Moreover, an automatic monitoring system must be able to store and analyze possibly large databases (hours of videos acquired with high frame rate and high resolution digital cameras). In the present paper, a new image analysis method for ballast water monitoring is presented. The main objective was to detect and count planktonic microorganisms using the Visual Rhythm of the video records during ballast water discharges. The results prove the efficacy of the proposed approach in the analysis of long movie sequences.

Exploring structure for long-term tracking of multiple objects in sports videos

Abstract In this paper, we propose a novel approach for exploiting structural relations to track multiple objects that may undergo long-term occlusion and abrupt motion. We use a model-free approach that relies only on annotations given in the first frame of the video to track all the objects online, i.e. without knowledge from future frames. We initialize a probabilistic Attributed Relational Graph (ARG) from the first frame, which is incrementally updated along the video. Instead of using the structural information only to evaluate the scene, the proposed approach considers it to generate new tracking hypotheses. In this way, our method is capable of generating relevant object candidates that are used to improve or recover the track of lost objects. The proposed method is evaluated on several videos of table tennis, volleyball, and on the ACASVA dataset. The results show that our approach is very robust, flexible and able to outperform other state-of-the-art methods in sports videos that present structural patterns.

Towards a quantitative academic internationalization assessment of Brazilian research groups

This paper introduces a new computational method to automatically estimate the International Publication Ratio (IPR) based on the analysis of bibliographical productions of Brazilian research groups, a task that would be too difficult (in many cases, impossible) to be performed manually. The proposed method explores the DOI number to identify the countries of every co-author who participated in each publication. Considering the bibliometric data from the Brazilian Lattes platform we show that is possible to make a good estimation of the IPR for research groups. Calculating the IPR is important in order to make a quantitative evaluation of the science progress and to establish a comparison between the academic institutions or knowledge areas. The experiments considering research groups, belonging to the 100 more collaborative researchers of five Brazilian major knowledge areas, confirm that the our proposal leads to an effective way to infer the IPR.

Using Text Similarity to Detect Social Interactions not Captured by Formal Reply Mechanisms

In modeling social interaction online, it is important to understand when people are reacting to each other. Many systems have explicit indicators of replies, such as threading in discussion forums or replies and retweets in Twitter. However, it is likely these explicit indicators capture only part of peoples reactions to each other, thus, computational social science approaches that use them to infer relationships or influence are likely to miss the mark. This paper explores the problem of detecting non-explicit responses, presenting a new approach that uses tf-idf similarity between a users own tweets and recent tweets by people they follow. Based on a months worth of posting data from 449 ego networks in Twitter, this method demonstrates that it is likely that at least 11% of reactions are not captured by the explicit reply and retweet mechanisms. Further, these uncaptured reactions are not evenly distributed between users: some users, who create replies and retweets without using the official interface mechanisms, are much more responsive to followees than they appear. This suggests that detecting non-explicit responses is an important consideration in mitigating biases and building more accurate models when using these markers to study social interaction and information diffusion.

Motion Estimation from RGB-D Images Using Graph Homomorphism

We present an approach for motion estimation from videos captured by depth-sensing cameras. Our method uses the technique of graph matching to find groups of pixels that move to the same direction in subsequent frames. In order to choose the best matching for each patch, we minimize a cost function that accounts for distances on RGB and XYZ spaces. Our application runs at real-time rates for low resolution images and has shown to be a convenient framework to deal with input data generated by the new depth-sensing devices. The results show clearly the advantage obtained in the use of RGB-D images over RGB images.