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 propose a simple and effective solution to the important and challenging problem of across-camera person re-identification. We focus on the common case in video surveillance where multiple images or video frames are available for each person. Instead of exploring new features, the proposed approach aims at making a better use of such images/frames. It builds a collaborative representation...
The objective of human re-identification is to recognize a specific individual on different locations and to determine whether an individual has already appeared. This is especially in multi-camera networks with non-overlapping fields of view of interest. However, this is still an unsolved computer vision task due to several challenges, e.g. significant changes of appearance of humans as well as different...
In recent years, a large amount of research efforts have been spent in the tracking human targets using one or more visual sensors (cameras) in both indoor and outdoor security and surveillance environments such as airports, metro stations, etc. However, in majority, the problem of associating a reliable identification signature to a detected target when in motion, has often been complicated due to...
There are several methods used to measure human height; it includes contact and non-contact measurements. In this research, we develop a fixed laser point triangular distance measurement (FLPTDM) method to construct a non-contact human height measurement scheme. In our scheme, a laser beam was used for signal emission, and a digital camera was used as the signal detection. We calculate the distance...
In many application cases, 2D human postures display haven't been able to meet people's requirements which is failure to show human motions comprehensive, image and vivid. However, 3D human Postures display could restore and show human motions well, which is convenient for people to observe and learn human motions. This paper presents a method to recognize 3D human postures by using Microsoft Kinect...
We describe our experience with the Muithu sports notational analysis system, a novel digital information system in the popular sports domain. The system integrates real-time coach notations with related video sequences, and is configured with small, off-the-shelf and cheap components. Muithu requires little or no human post-processing, which is in strong contrast to state of the art resource-intensive...
Visual detection based sense and avoid problem is more and more important nowadays as UAVs are getting closer to entering remotely piloted or autonomously into the airspace. It is critical to gain as much information as possible from the silhouettes of the distant aircrafts. In our paper, we investigate the reachable accuracy of the orientation information of remote planes under different geometrical...
As a certain case in the domain of human actions, hand gestures can be expressed by the motion of user's hand to provide nature interaction in many applications. In this paper we proposed a real-time hand gesture recognition system based on robust hand tracking from depth image sequences. Using hidden markov models (HMM) with varying states, gesture models are trained online along with user's feedback,...
A new method is proposed for using a combination of measurements from a laser range finder and a depth camera in a data fusion process that benefits from each modality's strong side. The combination leads to a significantly improved performance of the human detection and tracking in comparison with what is achievable from the singular modalities. The useful information from both laser and depth camera...
Wide area monitoring for community and city can be a very challenging engineering task due to its scale and heterogeneity in sensor, algorithm, and visualization levels. Multi-modal cameras and algorithms have to be fused into compact presentation for a single operator to actively and effectively respond to anomaly events and jeopardy. This paper presents a distributed and scalable video surveillance...
Kinect, as a 3D digital capturing device, can collect the RGB and depth information of human activities rapidly. We study fusing the depth and RGB information for activity recognition. We introduce histogram color-based image thresholding to detect skin on human body, and use a GMM model to segment human hand areas. We design a new local descriptor, called a 3D Motion Scale-Invariant Feature Transform...
In intelligent buildings, practical sensing systems designed to gather indoor occupancy information play an indispensable role in improving occupant comfort and energy efficiency by optimizing control strategies of HVAC (Heating, Ventilation and Air Conditioning) system and lighting system. In this paper we propose a novel method for occupant detection based on video surveillances now widely used...
In this paper we propose an approach to recognize human actions using depth images. Here, we capture the motion dynamics of the object from the depth difference image and average depth image. The features from the space-time depth difference images are obtained from hierarchical division of the silhouette bounding box. We also make use of motion history images to represent the temporal information...
Is low-cost tracking precise enough for recognition of pointing actions? We investigate the quality of the human body tracking available with a Kinect camera by comparing it to a state-of-the-art motion capture system. The application is action recognition with parametric hidden Markov Models (PHMMs) for programming industrial robots. The data from the Kinect is overall more noisy and potentially...
In this paper, we present Roman Tutor, an intelligent tutoring simulator to train astronauts on manipulating the SSRMS, an articulated robot arm deployed on the International Space Station. Roman Tutor incorporates a model of the system operations curriculum, a kinematic simulation of the robotics equipment and the ISS, a high performance path planner and an automatic task demonstration generator...
Social network analysis is a popular topic in social science. However, it needs a lot of human labor to get the information in psychological analysis. In this paper, we propose a multi-camera based evaluation system which can automatically track and recognize the human activities in an environment, and then build the corresponding social network and personality graphs. The proposed system contains...
As we move along the scale of adjustable autonomy for the control of robots from direct teleoperation at one extreme to full automation at the other, several opportunities for improvement in control quality, user feedback and machine learning suggest themselves. We describe three experiments, in telerobotics, the provision of situational awareness, and the acquisition of knowledge for automation from...
Computer vision is a field that includes methods for acquiring, processing, analyzing and understanding images. In the embedded world, computer vision applications have to fight with limited processing power and limited resources to achieve optimized algorithms and high performance. This paper presents work on implementing a human tracking system on both Intel based PC platform and embedded systems...
Among 2D-to-3D image conversion methods, those involving human operators have been most successful but also time-consuming and costly. Automatic methods, that typically make use of a deterministic 3D scene model, have not yet achieved the same level of quality as they often rely on assumptions that are easily violated in practice. In this paper, we adopt the radically different approach of “learning”...
One challenge when tracking objects is to adapt the object representation depending on the scene context to account for changes in illumination, coloring, scaling, etc. Here, we present a solution that is based on our earlier approach for object tracking using particle filters and component-based descriptors. We extend the approach to deal with changing backgrounds by using a quick training phase...
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.