Abstract: Deep video action recognition models have been highly successful in recent years but require large quantities of manually-annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic training data for video action recognition, as synthetic data have been successfully used to supervise models for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation, physics models and other components of modern game engines. With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. PHAV contains a total of 39,982 videos, with more than 1000 examples for each of 35 action categories. Our video generation approach is not limited to existing motion capture sequences: 14 of these 35 categories are procedurally-defined synthetic actions. In addition, each video is represented with 6 different data modalities, including RGB, optical flow and pixel-level semantic labels. These modalities are generated almost simultaneously using the Multiple Render Targets feature of modern GPUs. In order to leverage PHAV, we introduce a deep multi-task (i.e. that considers action classes from multiple datasets) representation learning architecture that is able to simultaneously learn from synthetic and real video datasets, even when their action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance. Our approach also significantly outperforms video representations produced by fine-tuning state-of-the-art unsupervised generative models of videos.

Abstract: Video alignment is important in different areas of computer vision such as wide baseline matching, action recognition, change detection, video copy detection and frame dropping prevention. Current video alignment methods usually deal with a relatively simple case of fixed or rigidly attached cameras or simultaneous acquisition. Therefore, in this paper we propose a joint video alignment for bringing two video sequences into a spatio-temporal alignment. Specifically, the novelty of the paper is to formulate the video alignment to fold the spatial and temporal alignment into a single alignment framework. This simultaneously satisfies a frame-correspondence and frame-alignment similarity; exploiting the knowledge among neighbor frames by a standard pairwise Markov random field (MRF). This new formulation is able to handle the alignment of sequences recorded at different times by independent moving cameras that follows a similar trajectory, and also generalizes the particular cases that of fixed geometric transformation and/or linear temporal mapping. We conduct experiments on different scenarios such as sequences recorded simultaneously or by moving cameras to validate the robustness of the proposed approach. The proposed method provides the highest video alignment accuracy compared to the state-of-the-art methods on sequences recorded from vehicles driving along the same track at different times.

Abstract: In this paper, we investigate the problem of visual odometry for ground vehicles based on the simultaneous utilization of multispectral cameras. It encompasses a stereo rig composed of an optical (visible) and thermal sensors. The novelty resides in the localization of the cameras as a stereo setup rather
than two monocular cameras of different spectrums. To the best of our knowledge, this is the first time such task is attempted. Log-Gabor wavelets at different orientations and scales are used to extract interest points from both images. These are then described using a combination of frequency and spatial information within the local neighborhood. Matches between the pairs of multimodal images are computed using the cosine similarity function based
on the descriptors. Pyramidal Lucas–Kanade tracker is also introduced to tackle temporal feature matching within challenging sequences of the data sets. The vehicle egomotion is computed from the triangulated 3-D points corresponding to the matched features. A windowed version of bundle adjustment incorporating
Gauss–Newton optimization is utilized for motion estimation. An outlier removal scheme is also included within the framework to deal with outliers. Multispectral data sets were generated and used as test bed. They correspond to real outdoor scenarios captured using our multimodal setup. Finally, detailed results validating the proposed strategy are illustrated.