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.
This paper deals with the selection of relevant motion from multi-object movement. The proposed method is based on a multi-scale approach using features extracted from optical flow and global rarity quantification to compute bottom-up saliency maps. It shows good results from four objects to dense crowds with increasing performance. The results are convincing on synthetic videos, simple real video...
Training home robots to behave like human can help people with their daily chores and repetitive tasks. In this paper, we present Imirok, a system to remotely control robotic arms by user motion using low-cost, off-the-shelf mobile devices and webcam. The motion tracking algorithm detects user motion in real time, without classifier training or predefined action sets. Experimental results show that...
Real-time feature extraction is a key component for any action recognition system that claims to be truly real-time. In this paper we present a conceptually simple and computationally efficient method for real-time human activity recognition based on simple statistical features. Such features are very cheap to compute and form a relatively low dimensional feature space in which classification can...
In the process of traffic video segmentation, the moving shadows have always been wrongly detected as foreground, which will in turn affect the latter processes of detection, analysis and tracing. We propose a method of moving shadow detection based on local texture features integrated with linear characteristics. Firstly, an adaptive background model was built on the basis of RGB color information,...
An improved moving object segmentation approach which extracted motion field from H.264 compressed domain is proposed. Pre-treatments such as vector median filtering and forward block vector accumulation are used to obtain more obvious motion field. Then mix and hierarchical clustering algorithm based on improved k-means and EM is exploited to segment the moving on the macro-block level and on the...
Mobile robots are widely used for computation-intensive tasks such as surveillance, moving object recognition and tracking. Existing studies perform the computation entirely on robot processors or on dedicated servers. The robot processors are limited by their computation capability; real-time performance may not be achieved. Even though servers can perform tasks faster, the communication time between...
In this paper we present a novel system for real-time, six degree of freedom visual simultaneous localization and mapping using a stereo camera as the only sensor. The system makes extensive use of parallelism both on the graphics processor and through multiple CPU threads. Working together these threads achieve real-time feature tracking, visual odometry, loop detection and global map correction...
The paper presents a new tracking scheme based on the object-strips color (OSC) feature. Firstly, the images captured by the camera are transformed into a format which is suitable for object tracking. Secondly, background subtraction method is used to detect the moving object. Then the OSC feature is represented by dividing the detected object into several strips and integrating the mean hue of each...
Modern surveillance systems are becoming highly automated in terms of scene understanding and event detection capabilities, and most existing methods rely on track-and motion-based features for event classification and anomaly detection. However, trajectory-based methods fail in public scenarios due to frequently loosing the object tracks, while the capabilities of motion-based methods are limited...
Human activity recognition has become very popular in the field of computer vision. In this paper, we present a simple, robust and computationally efficient algorithm, architecture and implementation to recognise and classify human activities in real-time using very few training data. We employ a spatio-temporal representation of human activities by combining trajectory information and invariant spatial...
We present a method that unifies tracking and video content recognition with applications to Mobile Augmented Reality (MAR). We introduce the Radial Gradient Transform (RGT) and an approximate RGT, yielding the Rotation-Invariant, Fast Feature (RIFF) descriptor. We demonstrate that RIFF is fast enough for real-time tracking, while robust enough for large scale retrieval tasks. At 26× the speed, our...
This paper deals with the real-time estimations of the rigid motion and three-dimensional structure of a scene from one or stereo moving camera. The method is based on an Extended Kalman Filter (EKF) that permits to obtain an executable real-time implementation. The extensions of an existent single camera solution and the new formulation of the stereo case is explained. Synthetic and real data experiments...
This paper proposes a method to detect speed variation of a moving human target, based on polar projection feature. Through even-grid-polar mapping, two polar projection feature images, namely r-projection and q-projection, are obtained respectively. It is found that the frequency of double-peak in q-projection feature image series in a motion cycle is sensitive to speed variation and can be utilized...
In many cases, visual tracking is based on detecting, describing, and then matching local features. A variety of algorithms for these steps have been proposed and used in tracking systems, leading to an increased need for independent comparisons. However, existing evaluations are geared towards object recognition and image retrieval, and their results have limited validity for real-time visual tracking...
This paper will present an obstacle detection approach that relies on the three-dimensional information from stereo vision. Concerning real-time response of the system and high accuracy of the reconstructed points, instead of the traditional stereo matching, a new way that combines three-dimensional features with wavelet-based hierarchical technique is proposed to decrease the computational cost and...
Driving assistance systems provide either safety or comfort functions. Such systems must evaluate the state of the world and take necessary actions. A preliminary step for evaluating the state of the world is to detect, track and classify scene objects. The classification step becomes especially important in complex urban traffic scenarios. In such scenarios the sensors of choice are vision based,...
The problem of eye gaze tracking has been researched and developed for a long time. Most of them use intrusive techniques to estimate the gaze of a person. This paper presents a non-intrusive approach for eye gaze tracker in real time with a simple camera. To track the eye gaze we have to deal with three principle problems: detecting the eye, tracking the eye and detecting the gaze of the eye on the...
Indoor and outdoor real-time monitoring of scenes has become a hot topic for decades. This paper analyzes the median filter and its shortcomings and proposes a modified detection method for moving objects with complex background. Using the method based on decision-making data gives the weights of a consecutive sequence of frames to calculate the weighted average of the corresponding values of pixel...
When broadcasting sports events it is useful to be able to place virtual 3D annotations on the ground, to indicate things such as world record lines and distances. This requires the camera pose to be estimated in real time, so that the graphics can be rendered to match the camera view. Whilst camera calibration data can be obtained by using sensors on the camera mount and lens, such sensors can be...
We describe a novel markerless camera tracking approach and user interaction methodology for augmented reality (AR) on unprepared tabletop environments. We propose a real-time system architecture that combines two types of feature tracking. Distinctive image features of the scene are detected and tracked frame-to-frame by computing optical flow. In order to achieve real-time performance, multiple...
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.