Motion is a strong clue for unsupervised grouping of individuals in a crowded environment. We show that collective motion in the crowd can be discovered by temporal analysis of points trajectories. First k-NN graph is constructed to represent the topological structure of point trajectories detected in crowd. Then the data-driven graph segmentation helps to reveal the interaction of individuals even when mixed motion is presented in data. The method was evaluated against the latest state-of-the-art methods and achieved better performance by more than 20 percent.

Abstract. In this paper we focus on appearance features particularly the Local Binary Patterns describing the manual component of Sign Language. We compare the performance of these features with geometric moments describing the trajectory and shape of hands. Since the non-manual component is also very important for sign recognition we localize facial landmarks via Active Shape Model combined with Landmark detector that increases the robustness of model fitting. We test the recognition performance of individual features and their combinations on a database consisting of 11 signers and 23 signs with several repetitions. Local Binary Patterns outperform the geometric moments. When the features are combined we achieve a recognition rate up to 99.75% for signer dependent tests and 57.54% for signer independent tests.

Complex systems composed of many components can operate in an inappropriate way. Information about the system is obtained in time, gradually. The assessment of casualties in such situation has challenged many researchers. The present paper provides a new compact methodology for diagnostics of faults form measurements: Space of measurements is divided into symptoms. Each symptom is able to admit some faults as possible and exclude some as impossible. This concept is based on fuzzy logic approach and provides an efficient alternative to usual probabilistic oriented methodologies. These relations between symptoms and faults are stated in the mapping table as logical rules. The diagnosis information is gathered online and aggregated on the side of symptoms or on the side of faults. This paper provides and compares a set of different methods for transformation of measured information into truth rates for each fault.

No abstract

The characteristics like density of objects, their contrast with respect to surrounding background, their occlusion level and many more describe the context of the scene. The variation of the context represents ambiguous task to be solved by tracker. In this paper we present a new long term tracking framework boosted by context around each tracklet. The framework works by first learning the database of optimal tracker parameters for various context offline. During the testing, the context surrounding each tracklet is extracted and match against database to select best tracker parameters. The tracker parameters are tuned for each tracklet in the scene to highlight its discrimination with respect to surrounding context rather than tuning the parameters for whole scene. The proposed framework is trained on 9 public video sequences and tested on 3 unseen sets. It outperforms the state-of-art pedestrian trackers in scenarios of motion changes, appearance changes and occlusion of objects.