Thomas Mauthner

Graz University of Technology | TU Graz · Institute for Computer Graphics and Vision

We present a novel approach for spatiotemporal saliency detection by optimizing a unified criterion of color contrast, motion contrast, appearance and background cues. To this end, we first abstract the video by temporal superpixels. Second, we propose a novel graph structure exploiting the saliency cues to assign the edge weights. The salient segm...

The Thermal Infrared Visual Object Tracking challenge 2016, VOT-TIR2016, aims at comparing short-term single-object visual track-ers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2016 is the second benchmark on short-term tracking in TIR sequences. Results of 24 track-ers are presente...

The Thermal Infrared Visual Object Tracking challenge 2016, VOT-TIR2016, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2016 is the second benchmark on short-term tracking in TIR sequences. Results of 24 trackers are presented....

The Visual Object Tracking challenge VOT2016 aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 70 trackers are presented, with a large number of trackers being published at major computer vision conferences and journals in the recent years. The number of tested state-of-...

We introduce a novel approach to recognizing facial expressions over a large range of head poses. Like previous approaches, we map the features extracted from the input image to the corresponding features of the face with the same facial expression but seen in a frontal view. This allows us to collect all training data into a common referential and...

Multi-view facial expression recognition (MFER) is an active research topic in facial analysis. In fact, not only the accuracy but also time complexity is desirable for real applications. In this paper, we introduce a new fast and robust approach for recognizing facial expressions in arbitrary views. Our approach relies on learning linear regressio...

In this work, we address the problem of model-free online object tracking based on color representations. According to the findings of recent benchmark evaluations, such trackers often tend to drift towards regions which exhibit similar appearance compared to the object of interest. To overcome this limitation, we propose an efficient discriminativ...

We present a novel video saliency detection method for supporting human activity recognition and weakly supervised training of activity detection algorithms. Recent research has emphasized the need for analyzing salient information in videos for minimizing dataset bias or to supervise weakly labeled training of activity detectors. In contrast to pr...

Activity recognition in sport is an attractive field for computer vision research. Game, player and team analysis are of great interest and research topics within this field emerge with the goal of automated analysis. As the execution of same activities differs between players and activities cannot be modeled by local description alone, additional...

Dataset can be found at: http://lrs.icg.tugraz.at/download.php#vb14

The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not ap-ply pre-learned models of object appearance. Results of 38 trackers are presented. The number of tested trackers makes VOT 2014 the largest benchmark on short-term tracking to date. For each participating tracker, a short de...

The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 38 trackers are presented. The number of tested trackers makes VOT 2014 the largest benchmark on short-term tracking to date. For each participating tracker, a short des...

Robust multi-object tracking-by-detection requires the correct assignment of noisy detection results to object trajectories. We address this problem by proposing an online approach based on the observation that object detectors primarily fail if objects are significantly occluded. In contrast to most existing work, we only rely on geometric informa...

Activity recognition in sport is an attractive field for computer vision research. Game, player and team analysis are of great interest and research topics within this field emerge with the goal of automated analysis. The very specific underlying rules of sports can be used as prior knowledge for the recognition task and present a constrained envir...

Performance in team sports crucially depends on the knowledge about the own and the opponents strengths and weaknesses. Since the analysis of single actions only provides restricted information on the game process, the analysis of sequential actions is from great importance to understand team tactics. In this paper, we introduce a novel method to a...

Combining foreground images from multiple views by projecting them onto a common ground-plane has been recently applied within many multi-object tracking approaches. These planar projections introduce severe artifacts and constrain most approaches to objects moving on a common 2D ground-plane. To overcome these limitations, we introduce the concept...

In this paper, we focus on human activity detection, which solves detection, tracking, and recognition jointly. Existing approaches typically use off-the-shelf approaches for detection and tracking, ignoring naturally given prior knowledge. Hence, in this work we present a novel strategy for learning activity specific motion models by feature-to-te...

Pan-Tilt-Zoom (PTZ) cameras are widely used in video surveillance tasks. In particular, they can be used in combination with static cameras to provide high resolution imagery of interesting events in a scene on demand. Nevertheless, PTZ cameras only provide a single trajectory at a time. Hence, engineering algorithms for common computer vision task...

Recently, several approaches have been introduced for incorporating the information from multiple cameras to increase the robustness of tracking. This allows to handle problems of mutually occluding objects - a reasonable scenario for many tasks such as visual surveillance or sports analysis. However, these methods often ignore problems such as ina...

In action recognition recently prototype-based classification methods became popular. However, such methods, even showing competitive classification results, are often limited due to too simple and thus insufficient representations and require a long-term analysis. To compensate these problems we propose to use more sophisticated features and an ef...

Recently descriptors based on Histograms of Oriented Gradients (HOG) and Local Binary Patterns (LBP) have shown excellent results in object detection considering the precision as well as the recall. However, since these descriptors are based on high dimensional representations such approaches suffer from enormous memory and runtime requirements. Th...

Computer vision-based interfaces to games hold the promise of rich natural interaction and thus a more realistic gaming experience. Therefore, the video games industry started to develop and market computer vision-based games recently with great success. Due to limited computational resources, they employ mostly simple algorithms such as background...

Position determination of game analysts is often performed by subjective visual estimation. The aim of this study was to evaluate human position estimations for setting actions in beach volleyball. Subjects were asked to assign the athlete's position to one of five cells representing the court. Position estimations from seven beach volleyball exper...

We present a human action recognition system suitable for very short sequences. In particular, we estimate Histograms of Oriented Gradients (HOGs) for the current frame as well as the corresponding dense flow field estimated from two frames. The thus obtained descriptors are then efficiently represented by the coefficients of a Nonnegative Matrix F...

In this paper we present an efficient technique to obtain accurate semantic classification on the pixel level capable of integrating various modalities, such as color, edge responses, and height information. We propose a novel feature representation based on Sigma Points computations that enables a simple application of powerful covariance descript...

Tracking is usually interpreted as finding an object in single consecutive frames. Regularization is done by enforcing temporal smoothness of appearance, shape and motion. We propose a tracker, by interpreting the task of tracking as segmentation of a volume in 3D. Inherently temporal and spatial regularization is unified in a single regularization...

In this paper, we present an efficient system for action recognition from very short sequences. For action recognition typically appearance and/or motion information of an action is analyzed using a large number of frames. This is a limitation if very fast actions (e.g., in sport analysis) have to be analyzed. To overcome this limitation, we propos...

In this paper, we present an efficient system for action recognition from very short sequences. For action recogni-tion typically appearance and/or motion information of an action is analyzed using a large number of frames, which is often not sufficient, if very fast actions (e.g., in sport anal-ysis) have to be analyzed. To overcome this limitatio...

This paper introduces a hierarchical approach for multi-component tracking, where the object-to-be-tracked is modeled as a group of spatial related parts. We propose to use a robust particle filtering framework for tracking the individual components and outline how the spatial coherency between the parts can be efficiently integrated by analyzing a...

This paper describes a combination of an automated image acquisition method and a probabilistic tracking method for analysis of the 3D microstructure of a sheet of paper. A prototype which combines microtomy and light microscopy enables efficient and fully automated digitization of paper samples in high resolution. A particle filter based tracking...

This paper proposes an efficient approach for semantic image classification by inte- grating additional contextual constraints such as class co-occurrences into a randomized forest classification framework. The randomized forest classifier performs an initial yet local classification on the pixel level by using powerful covariance matrix based de-...

This paper proposes a new method for interest region matching in omnidirectional images, which uses vir-tual perspective camera planes. Perspective views are gen-erated for each detected region depending on the region properties. This removes the distortions from the omnidirec-tional imaging device and enables the use of state-of-the-art wide-basel...

This work proposes an efficient approximation of a covariance based feature representation for track-ing. In contrast to approximated similarity measurements such as Foerstner metric between second order moments, we propose to approximate single distributions by specified sampling. We derive a efficient and discriminative feature representation tha...

This paper deals with the task of tracking several similar looking athletes during a competition, using only a single camera. Due to the wide range of possible motions, non-rigid shape changes and mutual occlusions the tracking situations can become quite complex. We propose a novel method to use a high dimensional motion model for a particle filte...

This paper aims at successful tracking of beach volleyball athletes during competition using only a single camera. Due to the wide range of possible motions and non-rigid shape changes, the tracking task becomes quite complex. We propose a novel method based on integral histograms, to use a high dimensional model for a particle filter without drast...