The objective of this work is recognition and spatiotemporal localization of two-person interactions in video. Our approach is person-centric. As a first stage we track all upper bodies and heads in a video using a tracking-by-detection approach that combines detections with KLT tracking and clique partitioning, together with occlusion detection, to yield robust person tracks. We develop local descriptors of activity based on the head orientation (estimated using a set of pose-specific classifiers) and the local spatiotemporal region around them, together with global descriptors that encode the relative positions of people as a function of interaction type. Learning and inference on the model uses a structured output SVM which combines the local and global descriptors in a principled manner. Inference using the model yields information about which pairs of people are interacting, their interaction class, and their head orientation (which is also treated as a variable, enabling mistakes in the classifier to be corrected using global context). We show that inference can be carried out with polynomial complexity in the number of people, and describe an efficient algorithm for this. The method is evaluated on a new dataset comprising 300 video clips acquired from 23 different TV shows and on the benchmark UT--Interaction dataset.

This paper describes a general continuous-time framework for visual-inertial simultaneous localization and mapping and calibration. We show how to use a spline parameterization that closely matches the torque-minimal motion of the sensor. Compared to traditional discrete-time solutions, the continuous-time formulation is particularly useful for solving problems with high-frame rate sensors and multiple unsynchronized devices. We demonstrate the applicability of the method for multi-sensor visual-inertial SLAM and calibration by accurately establishing the relative pose and internal parameters of multiple unsynchronized devices. We also show the advantages of the approach through evaluation and uniform treatment of both global and rolling shutter cameras within visual and visual-inertial SLAM systems.

No abstract

In this paper we address the problem of recognising interactions between two people in realistic scenarios for video retrieval purposes. We develop a per-person descriptor that uses attention (head orientation) and the local spatial and temporal context in a neighbourhood of each detected person. Using head orientation mitigates camera view ambiguities, while the local context, comprised of histograms of gradients and motion, aims to capture cues such as hand and arm movement. We also employ structured learning to capture spatial relationships between interacting individuals.We train an initial set of one-vs-the-rest linear SVM classifiers, one for each interaction, using this descriptor. Noting that people generally face each other while interacting, we learn a structured SVM that combines head orientation and the relative location of people in a frame to improve upon the initial classification obtained with our descriptor. To test the efficacy of our method, we have created a new dataset of realistic human interactions comprised of clips extracted from TV shows, which represents a very difficult challenge. Our experiments show that using structured learning improves the retrieval results compared to using the interaction classifiers independently.

One of the challenges found in recent methods for action recognition has been to classify ambiguous actions successfully . In the case of methods that use spatio-temporal features this phenomenon is observed when two actions generate similar feature types. Ideally, a probabilistic classification method would be based on a model of the full joint distribution of features, but this is computationally intractable. In this paper we propose using an approximation of the full joint via first order dependencies between feature types using so-called Chow-Liu trees. We obtain promising results and achieve an improvement in the classification accuracy over naive Bayes and other simple classifiers. Our implementation of the method makes use of a binary descriptor for a video analogous to one previously used in location recognition for mobile robots. Because of the simplicity of the algorithm, once the offline learning phase is over, real-time action recognition is possible and we present an adaptation of this method that works in real-time.