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.
In this paper we explore ways to address the issue of dataset bias in person re-identification by using data augmentation to increase the variability of the available datasets, and we introduce a novel data augmentation method for re-identification based on changing the image background. We show that use of data augmentation can improve the cross-dataset generalisation of convolutional network based...
Person re-identification is an important computer vision task with many applications in areas such as surveillance or multimedia. Approaches relying on handcrafted image features struggle with many factors (e.g. lighting, camera angle) which lead to a large variety in visual appearance for the same individual. Features based on semantic attributes of a person's appearance can help with some of these...
In addition to the traditional video surveillance, various audio processing techniques can also be added to the existing CCTV cameras. They can be used as additional features to help in analyzing the scene better and autonomously detecting violence or any unwanted activity in the scene. For this purpose, a deep learning based scream sound detection approach is proposed in this paper. MFCC features...
We propose a novel approach to segment hand regions in egocentric video that requires no manual labeling of training samples. The user wearing a head-mounted camera is prompted to perform a simple gesture during an initial calibration step. A combination of color and motion analysis that exploits knowledge of the expected gesture is applied on the calibration video frames to automatically label hand...
Considering the enormous creation rate of usergenerated videos on websites like YouTube, there is an immediate need for automatic categorization, recognition and analysis of videos. To develop algorithms for analyzing user-generated videos, unconstrained and representative datasets are of great significance. For this purpose, we collected a dataset of Sports Videos in the Wild (SVW), consisting of...
The tracking of moving points in image sequences requires unique features that can be easily distinguished. However, traditional feature descriptors are of high dimension, leading to larger storage requirement and slower computation. In this paper, Principal Component Analysis (PCA) is applied to the 64-Dimension (D) Speeded Up Robust Features (SURF) descriptor to reduce the descriptor dimensionality...
In a teleoperated system, misalignment between the master and slave manipulators can result from clutching, errors in the kinematic model, and/or sensor errors. This study examines the effects of type and magnitude of misalignment on the performance of the teleoperator. We first characterized the magnitude and direction of orientation misalignment created when clutching and unclutching during use...
Human tracking across multiple cameras is highly demanded for large scale video surveillance. To successfully track human across multiple uncalibrated cameras that have no overlapping field of views, a system to train more reliable camera link models is proposed in this paper. We employ a novel approach of combining multiple camera links and building bidirectional transition time distribution in the...
Today's mobile devices are likely to store various kinds of personal information, making it important to authenticate mobile device users. Since various types of mobile devices now have cameras, there has been growing interest in authentication based on images of the areas surrounding the eye due to the case of combing with iris and periocular from an image. We propose a method for authenticating...
This paper proposes a video anomaly detection method based on wake motion descriptors. The method analyses the motion characteristics of the video data, on a video volumeby- video volume basis, by computing the wake left behind by moving objects in the scene. It then probabilistically identifies those never previously seen motion patterns in order to detect anomalies. The method also considers the...
This paper proposes a novel people counting method based on head detection and tracking to evaluate the number of people who move under an over-head camera. There are four main parts in the proposed method: foreground extraction, head detection, head tracking, and crossing-line judgment. The proposed method first utilizes an effective foreground extraction method to obtain foreground regions of moving...
This paper addresses two contributions for improving the accuracy and speed of preceding car detection systems. First, it proposes a feature description using Scalable Histogram of Oriented Gradient (SHOG) to solve scale problem of car region on the image. Without resizing the images to a fixed size, it is capable to extract a high-discriminated features with on the same feature space. Second, instead...
An electric wheelchair is basically acknowledged for mobility improvement in disability patients. In some cases, their hand could not well function. They may tire easy before reaching to the desired destination. Furthermore, the safety is the most concerned issue for wheelchair control in disability patients. Therefore, this work tries to develop the prototype of the automated navigation system that...
We propose an algorithm that uses pressure image data to detect a person's sleeping posture and identifies different body limbs. Our algorithm can be used in monitoring bed-bound patients and assessing the risk of pressure ulceration. We used a GMM-based clustering approach for concurrent posture classification and limb identification. Our proposed technique, applied on 9 healthy subjects instructed...
This paper presents a method of interaction and orientation that can be implemented in welding simulator and will be used for basic welding training. In welding process there are many factors that can affect the welding results. One of them is the orientation angle and interaction distance between plate and torch. Therefore, a method to find an angle and a distance between plate and welding torch...
In the automotive industry the issue of safety remains a major priority. This aspect is not focused just on the driver but also on the other participants of the traffic like the pedestrians. This paper describes a pedestrian detection system where three different classification methods are used for detecting pedestrians with a far infrared camera. The three methods are tested and compared on variable...
Light field photography provides a revolutionary possibility to reconstruct well-focused iris region from a 4D light-field image. However, such a “shoot and refocus” scheme is time-consuming in practice because it commonly needs to render an image sequence for finding the optimally refocused frame. This paper presents an efficient auto-refocusing iris imaging solution for lenselet-based light-field...
Human action recognition based on the depth maps is an important yet challenging task. In this paper, a new framework based on the 3D motion trail model (3DMTM) and Pyramid Histograms of Oriented Gradient (PHOG) is proposed to recognize human actions from sequences of depth maps. Specifically, a discriminative descriptor called 3DMTM-PHOG is proposed for depth-based human action recognition. The 3DMTM...
Social attention behavior offers vital cues towards inferring one's personality traits from interactive settings such as round-table meetings and cocktail parties. Head orientation is typically employed as a proxy for determining the social attention direction when faces are captured at low-resolution. Recently, multi-task learning has been proposed to robustly compute head pose under perspective...
Conventional supervised object recognition methods have been investigated for many years. Despite their successes, there are still two suffering limitations: (1) various information of an object is represented by artificial features only derived from RGB images, (2) lots of manually labeled data is required by supervised learning. To address those limitations, we propose a new semi-supervised learning...
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.