The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their representation learning capabilities. One of the bottlenecks in training for better representations is the amount of available per-pixel ground truth data that is required for...
Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem as blurs arise not only from multiple object motions but also from camera shake, scene depth variation. To remove these complicated motion blurs, conventional energy optimization based methods rely on simple assumptions such that blur kernel is partially uniform or locally linear. Moreover, recent machine...
This paper presents a novel large-scale dataset and comprehensive baselines for end-to-end pedestrian detection and person recognition in raw video frames. Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification (re-ID) accuracy and assessing the effectiveness of different...
Supervised deep learning often suffers from the lack of sufficient training data. Specifically in the context of monocular depth map prediction, it is barely possible to determine dense ground truth depth images in realistic dynamic outdoor environments. When using LiDAR sensors, for instance, noise is present in the distance measurements, the calibration between sensors cannot be perfect, and the...
Recent advances have enabled oracle classifiers that can classify across many classes and input distributions with high accuracy without retraining. However, these classifiers are relatively heavyweight, so that applying them to classify video is costly. We show that day-to-day video exhibits highly skewed class distributions over the short term, and that these distributions can be classified by much...
Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric...
Person re-identification is an open and challenging problem in computer vision. Existing approaches have concentrated on either designing the best feature representation or learning optimal matching metrics in a static setting where the number of cameras are fixed in a network. Most approaches have neglected the dynamic and open world nature of the re-identification problem, where a new camera may...
Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on the alignment of nearby frames. However, aligning images is a computationally expensive and fragile procedure, and methods...
Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the...
This paper tackles the problem of estimating 3D human poses from given 2D landmarks, which is still an ill-posed problem. The existing works have successfully applied Active Shape Model approach to estimate 3D human poses, but the error is still high. In this paper, we propose an improved method by using the cascade of neural networks to make the estimated shape more alike to the ground truth shape...
A novel dataset for benchmarking image-based localization is presented. With increasing research interests in visual place recognition and localization, several datasets have been published in the past few years. One of the evident limitations of existing datasets is that precise ground truth camera poses of query images are not available in a meaningful 3D metric system. This is in part due to the...
In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs. The architecture is composed of multiple stacked encoder-decoder networks, the core part being an iterative network that is able to improve its own predictions. The network estimates not only depth and motion,...
We explore 3D human pose estimation from a single RGB image. While many approaches try to directly predict 3D pose from image measurements, we explore a simple architecture that reasons through intermediate 2D pose predictions. Our approach is based on two key observations (1) Deep neural nets have revolutionized 2D pose estimation, producing accurate 2D predictions even for poses with self-occlusions...
Re-identification of people in surveillance footage must cope with drastic variations in color, background, viewing angle and a persons pose. Supervised techniques are often the most effective, but require extensive annotation which is infeasible for large camera networks. Unlike previous supervised learning approaches that require hundreds of annotated subjects, we learn a metric using a novel one-shot...
Removing pixel-wise heterogeneous motion blur is challenging due to the ill-posed nature of the problem. The predominant solution is to estimate the blur kernel by adding a prior, but extensive literature on the subject indicates the difficulty in identifying a prior which is suitably informative, and general. Rather than imposing a prior based on theory, we propose instead to learn one from the data...
We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. In common with recent work [10, 14, 16], we use an end-to-end learning approach with view synthesis as the supervisory signal. In contrast to the previous work, our method is completely unsupervised, requiring only monocular video sequences for training. Our...
Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities of corresponding ground truth depth data for training. Just recording quality depth data in a range of environments is a challenging problem. In this paper, we...
Coin recognition is one of the prime important activities for modern banking and currency processing systems in which machine vision is widely used. The technique at the heart of such systems is object recognition in a digital image. Although it has high recognition speed, the traditional method of coin recognition can not recognize the coins with similar sizes. This paper presents a method based...
This paper presents a computer vision-based methodology for human action recognition. First, the shape based pose features are constructed based on area ratios to identify the human silhouette in images. The proposed features are invariance to translation and scaling. Once the human body features are extracted from videos, different human actions are learned individually on the training frames of...
Surveillance systems play a critical role in security and surveillance. A surveillance system with cameras that work in the visible spectrum is sufficient for most cases. However, problems may arise during the night, or in areas with less than ideal illumination conditions. Cameras with thermal infrared technology can be a better option in these situations since they do not rely on illumination to...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.