When given a single frame of the video, humans can not only interpret the content of the scene, but also they are able to forecast the near future. This ability is mostly driven by their rich prior knowledge about the visual world, both in terms of (i) the dynamics of moving agents, as well as (ii) the semantic of the scene. In this work we exploit the interplay between these two key elements to predict scenespecific motion patterns. First, we extract patch descriptors encoding the probability of moving to the adjacent patches, and the probability of being in that particular patch or changing behavior. Then, we introduce a Dynamic Bayesian Network which exploits this scene specific knowledge for trajectory prediction. Experimental results demonstrate that our method is able to accurately predict trajectories and transfer predictions to a novel scene characterized by similar elements.

Matching cross-view images is challenging because the appearance and viewpoints are significantly different. While low-level features based on gradient orientations or filter responses can drastically vary with such changes in viewpoint, semantic information of images however shows an invariant characteristic in this respect. Consequently, semantically labeled regions can be used for performing cross-view matching.In this paper, we therefore explore this idea and propose an automatic method for detecting and representing the semantic information of an RGB image with the goal of performing cross-view matching with a (non-RGB) geographic information system (GIS). A segmented image forms the input to our system with segments assigned to semantic concepts such as traffic signs, lakes, roads, foliage, etc. We design a descriptor to robustly capture both, the presence of semantic concepts and the spatial layout of those segments. Pairwise distances between the descriptors extracted from the GIS map and the query image are then used to generate a shortlist of the most promising locations with similar semantic concepts in a consistent spatial layout. An experimental evaluation with challenging query images and a large urban area shows promising results.

Human ability to foresee the near future plays a key role in everyone's life to prevent potentially dangerous situations. To be able to make predictions is crucial when people have to interact with the surrounding environment. Modeling such capability can lead to the design of automated warning systems and provide moving robots with an intelligent way of interaction with changing situation.

AimsTo evaluate whether quantification of the extent of scarred left ventricular (LV) tissue by speckle-tracking strain echo (2DSE) can predict response to cardiac resynchronization therapy (CRT) in patients with ischaemic dilated cardiomyopathy (DCM). Methods and resultsForty-five patients (58.3 + 8.3 years; 24 males) with ischaemic DCM scheduled for CRT, and 25 controls were studied. A week before implantation all the patients underwent standard Doppler echo, 2DSE, and contrast-enhanced magnetic resonance (MR). Clinical and echocardiographic evaluation was repeated 6 months after CRT. The patients were considered as responders to CRT if LV end-systolic volume decreased by 15%. In DCM patients, LV ejection fraction was 29.2 + 5.1%. By evaluating the 765 segments with MR, subendocardial infarct was identified in 17.0% and transmural infarct in 18.3%. With 2DSE, the average global longitudinal strain (GLS) was 223.1 + 3.6% in controls and 215.1 + 5.1% in DCM (P ¼ 0.001). GLS showed a close correlation with total scar burden using MR (r ¼ 0.64, P , 0.001). At follow-up, patients were subdivided into responders (n ¼ 30; 66.7%) and non-responders (n ¼ 15; 33.3%) to CRT. GLS was significantly different in non-responders than in responders (GLS: 210.4 + 5.1 in nonresponders vs. 218.4 + 14% in responders, P , 0.001). In a multivariable analysis, GLS (P , 0.0001) and radial intraventricular dyssynchrony (P , 0.001) were powerful independent determinants of response to CRT. ConclusionGLS is strongly associated with total scar burden assessed by MR, and is an excellent independent predictor of response to CRT.--