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.
Recent ground-breaking works have shown that deep neural networks can be trained end-to-end to regress dense disparity maps directly from image pairs. Computer generated imagery is deployed to gather the large data corpus required to train such networks, an additional fine-tuning allowing to adapt the model to work well also on real and possibly diverse environments. Yet, besides a few public datasets...
Domain adaption (DA) allows machine learning methods trained on data sampled from one distribution to be applied to data sampled from another. It is thus of great practical importance to the application of such methods. Despite the fact that tensor representations are widely used in Computer Vision to capture multi-linear relationships that affect the data, most existing DA methods are applicable...
While fine-grained object recognition is an important problem in computer vision, current models are unlikely to accurately classify objects in the wild. These fully supervised models need additional annotated images to classify objects in every new scenario, a task that is infeasible. However, sources such as e-commerce websites and field guides provide annotated images for many classes. In this...
Traditional matrix factorization methods approximate high dimensional data with a low dimensional subspace. This imposes constraints on the matrix elements which allow for estimation of missing entries. A lower rank provides stronger constraints and makes estimation of the missing entries less ambiguous at the cost of measurement fit. In this paper we propose a new factorization model that further...
This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic. It is therefore applicable without any modifications to a wide range of computer vision problems such as image classification, object detection and image segmentation...
Foreground detection is the classical computer vision task of segmenting out motion information from a particular scene. Foreground detection using Gaussian Mixture Models (GMM) is the famous choice. Since first time proposed, many researchers tried to improve GMM. This paper focuses on the comparative evaluation of three most famous improvements in the algorithm. The improved methods are compared...
In tracking, one of the major challenges comes from handling appearance variations caused by changes in scale, pose, illumination and occlusion. In this paper, we propose a novel Bayesian Hierarchical Appearance Model (BHAM) for robust object tracking. Our idea is to model the appearance of a target as a combination of multiple appearance models, each covering the target appearance changes under a...
A method to detect objects in television images offered by the authors is considered. The basis of the method makes an adaptive technique to evaluate the background with static accumulation of information about the location of detected objects in clusters. The method has been confirmed while controlling slots of parking.
Fire detection system in the surveillance system monitors the indoor environment and issues alarm as part of the early warning mechanism with ultimate goal to provide an alarm at early stage before the fire become uncontrollable. Conventional fire detection systems suffer from the transparent delay from the fire to the sensor which is looking at a point. The reliability of the fire detection system...
Understanding the activities of human from videos is demanding task in Computer Vision. Identifying the actions being accomplished by the human in the video sequence automatically and tagging their actions is the prime functionality of intelligent video systems. The goal of activity recognition is to identify the actions and objectives of one or more objects from a series of examination on the action...
Particle filter is a widely used framework for object tracking, but it is vulnerable when its observation model is based on visual appearance. In this paper, we propose a modified particle filtering that makes use of foreground regions and their pixel-based confidences that are likely to be foreground; the foreground regions are used for preventing generations of particle in the background and the...
This paper describes a method of cross-domain object categorization, using the concept of domain adaptation. Here, a classifier is trained using samples from the source/auxiliary domain and performance is observed on a set of test samples taken from a different domain, termed as the target domain. To overcome the difference between the two domains, we aim to find a sequence of optimally weighted sub-spaces,...
This paper is concerned with the detection of moving objects using a pan-tilt camera and a background subtraction algorithm. Traditionally, motion compensation is performed on the current image to align its pixels with their background models in previous frames. Pixel misalignment however can occur during motion compensation. Although this problem can be alleviated by using pixel motion such as the...
In this paper, we present a novel generalized Segment-Forest Model (SFM) to segment an object as well as label all the object's semantic parts simultaneously. Segment-Forest is composed by various generated segment trees that act directly on super pixels. Unlike recent works, SFM does not need the prior information like skeleton to capture the core structure of an object, but actively learns the structure...
We propose a new approach that integrates object tracking with object segmentation in a closed loop. The EM-like algorithm for color-histogram-based object tracking is modified to deal with the appearance models of the object and background represented by the Gaussian mixture models which are more efficient in RGB color space. It provides a rough object spatial model to guide segmentation. A five-layer...
The vehicle detection is extremely important for the traffic parameter extraction and analysis in traffic scenes. In order to detect moving vehicle quickly, this paper proposes a samples-based adaptive segmentation detection algorithm. First, select the first frame as a reference frame, use a random policy to select values to build a samples-based estimation of the background. Second, we adopt different...
Moving object segmentation is an essential process for many computer vision algorithms. Many different methods have been proposed over the recent years but expert can be confused about their benefits and limitations. In this paper, review and comparative studyof various moving object segmentation approachesis presented in terms of qualitative and quantitative performances with the aim of pointing...
We present an extension to the Hierarchical Dirichlet Process (HDP), which allows for the inclusion of supervision. Our model marries the non-parametric benefits of HDP with those of Supervised Latent Dirichlet Allocation (SLDA) to enable learning the topic space directly from data while simultaneously including the labels within the model. The proposed model is learned using variational inference...
In this paper, we firstly propose a novel robust scale estimator called AIKOSE. It can estimate the scale of inlier noises by adaptively selecting the optimal value of K in the IKOSE scale estimator. Moreover, based on AIKOSE, we propose a novel robust estimator called AMSAC, which can fit a model without requiring a manually tuned threshold. In the experiments, we demonstrate the performance of AMSAC...
This paper proposes a new articulated human motion tracking and pose estimation algorithm using an improved silhouette extraction method with view adaptive fusion. It is developed around the baseline algorithm in HumanEva, which uses the Annealed Particle Filter (APF). Shadow detection and removal and a level-set method are employed to achieve better silhouette extraction. An adaptive view fusion...
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.