Abstract: Human multi-limb segmentation in RGB images has attracted a lot of interest in the research community because of the huge amount of possible applications in fields like Human-Computer Interaction, Surveillance, eHealth, or Gaming. Nevertheless, human multi-limb segmentation is a very hard task because of the changes in appearance produced by different points of view, clothing, lighting conditions, occlusions, and number of articulations of the human body. Furthermore, this huge pose variability makes the availability of large annotated datasets difficult. In this paper, we introduce the HuPBA8k+ dataset. The dataset contains more than 8000 labeled frames at pixel precision, including more than 120000 manually labeled samples of 14 different limbs. For completeness, the dataset is also labeled at frame-level with action annotations drawn from an 11 action dictionary which includes both single person actions and person-person interactive actions. Furthermore, we also propose a two-stage approach for the segmentation of human limbs. In a first stage, human limbs are trained using cascades of classifiers to be split in a tree-structure way, which is included in an Error-Correcting Output Codes (ECOC) framework to define a body-like probability map. This map is used to obtain a binary mask of the subject by means of GMM color modelling and GraphCuts theory. In a second stage, we embed a similar tree-structure in an ECOC framework to build a more accurate set of limb-like probability maps within the segmented user mask, that are fed to a multi-label GraphCut procedure to obtain final multi-limb segmentation. The methodology is tested on the novel HuPBA8k+ dataset, showing performance improvements in comparison to state-of-the-art approaches. In addition, a baseline of standard action recognition methods for the 11 actions categories of the novel dataset is also provided.

Abstract: The visual analysis of humans from images is an important topic of interest due to its relevance to many computer vision applications like pedestrian detection, monitoring and surveillance, human-computer interaction, e-health or content-based image retrieval, among others.
In this dissertation we are interested in learning different visual representations of the human body that are helpful for the visual analysis of humans in images and video sequences. To that end, we analyze both RGB and depth image modalities and address the problem from three different research lines, at different levels of abstraction; from pixels to gestures: human segmentation, human pose estimation and gesture recognition.
First, we show how binary segmentation (object vs. background) of the human body in image sequences is helpful to remove all the background clutter present in the scene. The presented method, based on Graph cuts optimization, enforces spatio-temporal consistency of the produced segmentation masks among consecutive frames. Secondly, we present a framework for multi-label segmentation for obtaining much more detailed segmentation masks: instead of just obtaining a binary representation separating the human body from the background, finer segmentation masks can be obtained separating the different body parts.
At a higher level of abstraction, we aim for a simpler yet descriptive representation of the human body. Human pose estimation methods usually rely on skeletal models of the human body, formed by segments (or rectangles) that represent the body limbs, appropriately connected following the kinematic constraints of the human body. In practice, such skeletal models must fulfill some constraints in order to allow for efficient inference, while actually limiting the expressiveness of the model. In order to cope with this, we introduce a top-down approach for predicting the position of the body parts in the model, using a mid-level part representation based on Poselets.
Finally, we propose a framework for gesture recognition based on the bag of visual words framework. We leverage the benefits of RGB and depth image modalities by combining modality-specific visual vocabularies in a late fusion fashion. A new rotation-variant depth descriptor is presented, yielding better results than other state-of-the-art descriptors. Moreover, spatio-temporal pyramids are used to encode rough spatial and temporal structure. In addition, we present a probabilistic reformulation of Dynamic Time Warping for gesture segmentation in video sequences. A Gaussian-based probabilistic model of a gesture is learnt, implicitly encoding possible deformations in both spatial and time domains.

Abstract: In order to increase the classification performance obtained using Error-Correcting Output Codes designs (ECOC), introducing weights in the decoding phase of the ECOC has attracted a lot of interest. In this work, we present a method for ECOC designs that focuses on increasing hypothesis margin on the data samples given a base classifier. While achieving this, we implicitly reward the base classifiers with high performance, whereas punish those with low performance. The resulting objective function is of the fractional programming type and we deal with this problem through the Dinkelbach’s Algorithm. The conducted tests over well known UCI datasets show that the presented method is superior to the unweighted decoding and that it outperforms the results of the state-of-the-art weighted decoding methods in most of the performed experiments.

Abstract: In this work we present a comprehensive computational framework to help in the clinical assessment of cancer response from a pair of time consecutive oncological PET-CT scans. In this scenario, the design and implementation of a supervised machine learning system to predict and quantify cancer progression or response conditions by introducing a novel feature set that models the underlying clinical context is described. Performance results in 100 clinical cases (corresponding to 200 whole body PET-CT scans) in comparing expert-based visual analysis and classifier decision making show up to 70% accuracy within a completely automatic pipeline and 90% accuracy when providing the system with expert-guided PET tumor segmentation masks.

Abstract: The performance of different action recognition techniques has recently been studied by several computer vision researchers. However, the potential improvement in classification through classifier fusion by ensemble-based methods has remained unattended. In this work, we evaluate the performance of an ensemble of action learning techniques, each performing the recognition task from a different perspective.
The underlying idea is that instead of aiming a very sophisticated and powerful representation/learning technique, we can learn action categories using a set of relatively simple and diverse classifiers, each trained with different feature set. In addition, combining the outputs of several learners can reduce the risk of an unfortunate selection of a learner on an unseen action recognition scenario.
This leads to having a more robust and general-applicable framework. In order to improve the recognition performance, a powerful combination strategy is utilized based on the Dempster-Shafer theory, which can effectively make use
of diversity of base learners trained on different sources of information. The recognition results of the individual classifiers are compared with those obtained from fusing the classifiers’ output, showing enhanced performance of the proposed methodology.