The paper presents findings from research project Mobis which is aimed at developing a method of assessing safety of unsignalised pedestrian road crossings using video image analysis. Pedestrian and vehicle traffic has been recorded at selected zebra crossing sites in Warsaw and Wrocław, before and after installation of active signage systems SignFlash and Levelite. Speeds of approaching vehicles were measured and drivers’ behaviour was classified using video analysis. The paper presents a comparison of effectiveness of systems such as SignFlash and Levelite based on changes in the mean and standard deviation of vehicle spot speeds as well as changes in speed profiles of vehicles approaching the crossings. Results indicate that both SignFlash and Levelite active signage reduce mean vehicle approach speeds and have a positive impact on drivers’ behaviour.
Polish Sign Language (PJM) is a natural communication system that has been evolving for two centuries. It is at the heart of the identity and culture of the Deaf community in Poland, but it is often marginalized and neglected. It first came under serious linguistic scrutiny not long ago, and more systematic research on it has been initiated in recent years by a team of researchers at the Section for Sign Linguistics at the University of Warsaw.
A variety of algorithms allows gesture recognition in video sequences. Alleviating the need for interpreters is of interest to hearing impaired people, since it allows a great degree of self-sufficiency in communicating their intent to the non-sign language speakers without the need for interpreters. State-of-theart in currently used algorithms in this domain is capable of either real-time recognition of sign language in low resolution videos or non-real-time recognition in high-resolution videos. This paper proposes a novel approach to real-time recognition of fingerspelling alphabet letters of American Sign Language (ASL) in ultra-high-resolution (UHD) video sequences. The proposed approach is based on adaptive Laplacian of Gaussian (LoG) filtering with local extrema detection using Features from Accelerated Segment Test (FAST) algorithm classified by a Convolutional Neural Network (CNN). The recognition rate of our algorithm was verified on real-life data.
The fundamental importance of cartographic signs in traditional maps is unquestionable, although in the case of multimedia maps their key function is not so obvious. Our aim was to search the problem of cartographic signs as a core of multimedia maps prepared by non-cartographer in on-line Map Services. First, pre-established rules for multimedia map designers were prepared emphasizing the key role of the cartographic signs and habits of Web-users. The comparison of projects completed by a group of designers led us to the general conclusion that a cartographic sign should determine the design of a multimedia map in on-line Map Services. Despite the selection of five different map topics, one may list the general characteristics of the maps with a cartographic sign in the core.
For many adaptive noise control systems the Filtered-Reference LMS, known as the FXLMS algorithm is used to update parameters of the control filter. Appropriate adjustment of the step size is then important to guarantee convergence of the algorithm, obtain small excess mean square error, and react with required rate to variation of plant properties or noise nonstationarity. There are several recipes presented in the literature, theoretically derived or of heuristic origin. This paper focuses on a modification of the FXLMS algorithm, were convergence is guaranteed by changing sign of the algorithm steps size, instead of using a model of the secondary path. A TakagiSugeno-Kang fuzzy inference system is proposed to evaluate both the sign and the magnitude of the step size. Simulation experiments are presented to validate the algorithm and compare it to the classical FXLMS algorithm in terms of convergence and noise reduction.