We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individually, we show how to learn to do all three in a unified manner while preserving end-toend differentiability. We then demonstrate that our Deep pipeline outperforms state-of-the-art methods on a number of benchmark datasets, without the need of retraining.

The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 38 trackers are presented. The number of tested trackers makes VOT 2014 the largest benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the appendix. Features of the VOT2014 challenge that go beyond its VOT2013 predecessor are introduced: (i) a new VOT2014 dataset with full annotation of targets by rotated bounding boxes and per-frame attribute, (ii) extensions of the VOT2013 evaluation methodology, (iii) a new unit for tracking speed assessment less dependent on the hardware and (iv) the VOT2014 evaluation toolkit that significantly speeds up execution of experiments. The dataset, the evaluation kit as well as the results are publicly available at the challenge website (http://​votchallenge.​net)

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outliers, while simultaneously using them to recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than directly on the image, and is thus simple and small. We introduce a novel normalization technique, called Context Normalization, which allows us to process each data point separately while embedding global information in it, and also makes the network invariant to the order of the correspondences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data.

We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive. We first identify good keypoint candidates in multiple training images taken from the same viewpoint. We then train a regressor to predict a score map whose maxima are those points so that they can be found by simple non-maximum suppression. As there are no standard datasets to test the influence of these kinds of changes, we created our own, which we will make publicly available. We will show that our method significantly outperforms the state-of-the-art methods in such challenging conditions, while still achieving state-of-the-art performance on the untrained standard Oxford dataset

No abstract

No abstract

Detecting moving objects on mobile cameras in real-time is a challenging problem due to the computational limits and the motions of the camera. In this paper, we propose a method for moving object detection on non-stationary cameras running within 5.8 milliseconds (ms) on a PC, and real-time on mobile devices. To achieve real time capability with satisfying performance, the proposed method models the background through dual-mode single Gaussian model (SGM) with age and compensates the motion of the camera by mixing neighboring models. Modeling through dual-mode SGM prevents the background model from being contaminated by foreground pixels, while still allowing the model to be able to adapt to changes of the background. Mixing neighboring models reduces the errors arising from motion compensation and their influences are further reduced by keeping the age of the model. Also, to decrease computation load, the proposed method applies one dualmode SGM to multiple pixels without performance degradation. Experimental results show the computational lightness and the real-time capability of our method on a smart phone with robust detection performances.

The Canada-France Imaging Survey (CFIS) will consist of deep, high-resolution r-band imaging over ~5000 square degrees of the sky, representing a first-rate opportunity to identify recently-merged galaxies. Due to the large number of galaxies in CFIS, we investigate the use of a convolutional neural network (CNN) for automated merger classification. Training samples of post-merger and isolated galaxy images are generated from the IllustrisTNG simulation processed with the observational realism code RealSim. The CNN’s overall classification accuracy is 88 percent, remaining stable over a wide range of intrinsic and environmental parameters. We generate a mock galaxy survey from IllustrisTNG in order to explore the expected purity of post-merger samples identified by the CNN. Despite the CNN’s good performance in training, the intrinsic rarity of post-mergers leads to a sample that is only ~6 percent pure when the default decision threshold is used. We investigate trade-offs in purity and completeness with a variable decision threshold and find that we recover the statistical distribution of merger-induced star formation rate enhancements. Finally, the performance of the CNN is compared with both traditional automated methods and human classifiers. The CNN is shown to outperform Gini-M20 and asymmetry methods by an order of magnitude in post-merger sample purity on the mock survey data. Although the CNN outperforms the human classifiers on sample completeness, the purity of the post-merger sample identified by humans is frequently higher, indicating that a hybrid approach to classifications may be an effective solution to merger classifications in large surveys.