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.
We present a novel and configurable synthetic data generator for evolving region trajectories that emulates certain characteristics of a given input dataset, such as the spatial position, velocity, lifespan, and geometry shape and size. This tool aims to facilitate faster prototyping and evaluation of new spatiotemporal data mining algorithms that operate on a specific type of trajectory data, of...
ORB-SLAM2 is one of the better-known open source SLAM implementations available. However, the dependence of visual features causes it to fail in featureless environments. With the present work, we propose a new technique to improve visual odometry results given by ORB-SLAM2 using a tightly Sensor Fusion approach to integrate camera and odometer data. In this work, we use odometer readings to improve...
In this paper, based on quaternion and Euler angles, an attitude control algorithm is proposed for pitching and rolling of quadrotor aircraft. In addition, the target tracking algorithm of quadrotor aircraft is designed by using the collected video information and color feature recognition. The system is based on the homemade quadrotor aircraft, using gyroscope, accelerometer as the original measurement...
Urbanization is accelerating worldwide, giving rise to serious traffic problems. Traffic wave, known as stop-and go traffic or phantom intersection, is one of the most significant traffic oscillation patterns studied in Traffic Engineering. Usually these studies are numerical experiments that investigate specific places, such as a crossroad or a highway section, and their findings cannot, therefore,...
In this work we propose novel joint and sequential multimodal approaches for the task of single channel audio source separation in videos. This is done within the popular non-negative matrix factorization framework using information about the sounding object's motion. Specifically, we present methods that utilize non-negative least squares formulation to couple motion and audio information. The proposed...
We introduce a general framework for visual forecasting, which directly imitates visual sequences without additional supervision. As a result, our model can be applied at several semantic levels and does not require any domain knowledge or handcrafted features. We achieve this by formulating visual forecasting as an inverse reinforcement learning (IRL) problem, and directly imitate the dynamics in...
This paper incorporates sampling-based global path planning with model predictive image-based visual servoing (IBVS) for quadrotor unmanned aerial vehicles (UAVs) equipped with a fixed camera. The proposed method produces safe control inputs of quadrotor in obstacle environment by taking image feature kinematics into account. Firstly, we utilize a sampling-based algorithm for optimal path planning,...
Mobile robotics became an important knowledge area. Led by the technological advances, the life spectancy increases, rising the senior citizens ratio. At the same hand, the cities growth turn on a more intense and dangerous traffic. Autonomous mobile robots can help in these situations, but still have a jeopardized application. In this sense, this work presents a contribution to development of nonholonomic...
We propose a visual SLAM (Simultaneous Localization And Mapping) system able to perform robustly in populated environments. The image stream from a moving RGB-D camera is the only input to the system. The computed map in real-time is composed of two layers: 1) The unpopulated geometrical layer, which describes the geometry of the bare scene as an occupancy grid where pieces of information corresponding...
The unified program architecture of real time vision system (VS) with several fields of view construction is described. The offered architecture provides both onboard and stationary usage. In case of stationary usage, it provides determination of location and trajectory of objects movement in the ordered system of co-ordinates. Principles of open architecture, componential technology and use of standard...
We consider scenarios in which we wish to perform joint scene understanding, object tracking, activity recognition, and other tasks in scenarios in which multiple people are wearing body-worn cameras while a third-person static camera also captures the scene. To do this, we need to establish person-level correspondences across first-and third-person videos, which is challenging because the camera...
This paper presents a method to predict the future movements (location and gaze direction) of basketball players as a whole from their first person videos. The predicted behaviors reflect an individual physical space that affords to take the next actions while conforming to social behaviors by engaging to joint attention. Our key innovation is to use the 3D reconstruction of multiple first person...
360° Video requires human viewers to actively control where to look while watching the video. Although it provides a more immersive experience of the visual content, it also introduces additional burden for viewers, awkward interfaces to navigate the video lead to suboptimal viewing experiences. Virtual cinematography is an appealing direction to remedy these problems, but conventional methods...
In recent years, both online retail and video hosting service have been exponentially grown. In this paper, a novel deep neural network, called AsymNet, is proposed to explore a new cross-domain task, Video2Shop, targeting for matching clothes appeared in videos to the exactly same items in online shops. For the image side, well-established methods are used to detect and extract features for clothing...
For survival, a living agent (e.g., human in Fig. 1(a)) must have the ability to assess risk (1) by temporally anticipating accidents before they occur (Fig. 1(b)), and (2) by spatially localizing risky regions (Fig. 1(c)) in the environment to move away from threats. In this paper, we take an agent-centric approach to study the accident anticipation and risky region localization tasks. We propose...
We develop predictive models of pedestrian dynamics by encoding the coupled nature of multi-pedestrian interaction using game theory and deep learning-based visual analysis to estimate person-specific behavior parameters. We focus on predictive models since they are important for developing interactive autonomous systems (e.g., autonomous cars, home robots, smart homes) that can understand different...
Riffling the pages of a book, perhaps in the search for a specific image, is an example of Rapid Serial Visual Presentation (RSVP). Even at a pace of 10 images per second, successful search is often possible. Interest in RSVP arises because a digital embodiment of RSVP has many applications.There are many possible 'modes' of RSVP. However, a mode can be especially helpful if, after the appearance...
The analysis of incidents is important for preventing collisions between moving objects. However, it requires that many cases of incidents be collected as target data. The purpose of this study was to develop a method that supports the collection of many cases of anomalous (near-miss) approach from massive movement data. To achieve this, a relative superposition method is proposed. Relative superposition...
We previously proposed a bicycle rider behavior visualization method using a probe bicycle equipped with an accurate speed sensor, a rotary encoder to measure handle angle, and a sensor to detect tilt of the bicycle body. However, the probe bicycle is expensive and inhibits wide use of this visualization method. To resolve this problem, we employ a smartphone as the sensor device. This newly proposed...
Eye movement reflects the shift of overt visual attention. Eye movement trajectories from a group of observers can be expressed by a representative scanpath. The representative scan-path can work as a baseline for studies on scanpath prediction as well as provide useful knowledge about group behavior in psychological studies. In this paper, we propose a new framework to summarize a representative...
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.