Search results for "Video Analysis"
showing 10 items of 11 documents
“Is there any sugar in bread?” A qualitative video analysis of student activating learning tasks in Home Economics
2021
The Norwegian Food and Health (FH) school subject aims to develop students' ability to understand the association between diet and health. Research on FH in Norway indicates that the main focus today is on cooking and the development of practical cooking skills, leaving little emphasis on activities related to the more theoretical aspects of the curriculum. To increase students’ knowledge and skills regarding nutrition and health, we aimed to evaluate three newly developed student-activating learning tasks. Three 6th grade FH classes in Southern Norway participated. Audio and video recording of the learning tasks were used to evaluate the activities. Also, data from focus group discussions …
Decoding Children's Social Behavior
2013
We introduce a new problem domain for activity recognition: the analysis of children's social and communicative behaviors based on video and audio data. We specifically target interactions between children aged 1-2 years and an adult. Such interactions arise naturally in the diagnosis and treatment of developmental disorders such as autism. We introduce a new publicly-available dataset containing over 160 sessions of a 3-5 minute child-adult interaction. In each session, the adult examiner followed a semi-structured play interaction protocol which was designed to elicit a broad range of social behaviors. We identify the key technical challenges in analyzing these behaviors, and describe met…
A video-based real-time vehicle counting system using adaptive background method
2008
International audience; This paper presents a video-based solution for real time vehicle detection and counting system, using a surveillance camera mounted on a relatively high place to acquire the traffic video stream.The two main methods applied in this system are: the adaptive background estimation and the Gaussian shadow elimination. The former allows a robust moving detection especially in complex scenes. The latter is based on color space HSV, which is able to deal with different size and intensity shadows. After these two operations, it obtains an image with moving vehicle extracted, and then operation counting is effected by a method called virtual detector.
Facilitating socio-cognitive and socio-emotional monitoring in collaborative learning with a regulation macro script – an exploratory study
2017
This study examines student teachers’ collaborative learning by focusing on socio-cognitive and socio-emotional monitoring processes during more and less active script discussions as well as the near transfer of monitoring activities in the subsequent task work. The participants of this study were teacher education students whose collaborative learning was supported with a designed regulation macro script during a six weeks environmental science course. The script divided the group work into three phases, namely: the orientation phase, intermediate phase, and reflection phase. The script was put in use by prompting questions that were delivered to the students on tablets. Question prompts i…
Toward an Integrated System for Surveillance and Behaviour Analysis of Groups and People
2013
Security and INTelligence SYStem is an Italian research project which aims to create an integrated system for the analysis of multi-modal data sources (text, images, video, audio), to assist operators in homeland security applications. Within this project the Scientific Research Unit of the University of Palermo is responsible of the image and video analysis activity. The SRU of Palermo developed a web service based architecture that provides image and video analysis capabilities to the integrated analysis system. The developed architecture uses both state of the art techniques, adapted to cope with the particular problem at hand, and new algorithms to provide the following services: image …
Automatic Video Database Indexing and Retrieval
1997
The increasing development of advanced multimedia applications requires new technologies for organizing and retrieving by content databases of still digital images or digital video sequences. To this aim image and image sequence contents must be described and adequately coded. In this paper we describe a system allowing content-based annotation and querying in video databases. No user action is required during the database population step. The system automatically splits a video into a sequence of shots, extracts a few representative frames (said r-frames) from each shot and computes r-frame descriptors based on color, texture and motion. Queries based on one or more features are possible. …
Two View Line-Based Motion and Structure Estimation for Planar Scenes
2012
We present an algorithm for reconstruction of piece-wise planar scenes from only two views and based on minimum line correspondences. We first recover camera rotation by matching vanishing points based on the methods already exist in the literature and then recover the camera translation by searching among a family of hypothesized planes passing through one line. Unlike algorithms based on line segments, the presented algorithm does not require an overlap between two line segments or more that one line correspon- dence across more than two views to recover the translation and achieves the goal by exploiting photometric constraints of the surface around the line. Experimental results on real…
Urban Traffic Analysis through an UAV
2014
Abstract In order to realize a precise and accurate traffic study, a method to evaluate the real traffic flow conditions in urban areas based on videos acquired by an UAV, Unmanned Aerial Vehicle, is proposed. In this way it does not require additional equipment to earth and, not being invasive, does not influence the driver behavior. This paper presents the results obtained in terms of vehicular traffic flow along a way in the city of Palermo. The results have been compared to experiments using macroscopic simulation models and the eventually differences have been discussed.
S-pot - A benchmark in spotting signs within continuous signing
2014
In this paper we present S-pot, a benchmark setting for evaluating the performance of automatic spotting of signs in continuous sign language videos. The benchmark includes 5539 video files of Finnish Sign Language, ground truth sign spotting results, a tool for assessing the spottings against the ground truth, and a repository for storing information on the results. In addition we will make our sign detection system and results made with it publicly available as a baseline for comparison and further developments. peerReviewed
Gap acceptance analysis in an urban intersection through a video acquired by an UAV
2014
Purpose of this paper is to apply a methodology previously developed to achieve an accurate measurements of the real traffic condition thought the use of a video acquired by an UAV (Unmanned Aerial Vehicle) and a probe vehicle equipped with a differential GPS. The used methodology is not invasive and thus, it doesn't influence the driver behavior. The used equipment must not be compared to the traditional techniques of traffic flow but it can be used for particular situations in which the installation of fixed detectors is not economic. In particular, we have analyzed the gap acceptance for an urban intersection between a main road with dual carriageway and two lanes in one direction, that …