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 order to solve the problem of traffic accidents that caused by drivers and passengers open the door abruptly, this paper proposes a door open alarm (DOA) system that uses the camera as the sensor, and applies two analog cameras that set at the both side view mirrors to get the video information. This paper is based on image processing to develop the algorithm and has been implemented on Renesas...
In this paper, we propose an image transformation method for correcting projective distortion which commonly occurs in surveillance camera systems. The method geometrically transforms a planar image into an equirectangular image using a spherical image sensor model. The transformation makes objects standing perpendicular to the ground to appear vertically in the image and also makes objects at the...
In this paper, the problem of queue in convenient stores is considered. We propose a low cost automatic queue length monitoring system by using an Internet-of-Things (IoT) platform. This system can detect the length of queue and the number of people that enqueue and leave the queue. If the length of queue is critical, the system will alert to staff via LINE Notify. Experimental results indicate that...
A Surveillance cameras are installed in facilities and urban areas for the purpose of monitoring intruders, and objects equipped with a moving object detection function also exist. In addition, due to recent improvements in camera technology, prices have declined, individuals can own surveillance cameras and install them at home. In this way, since the surveillance camera is installed in various places...
In this paper we make improvement to fisheye camera calibration methods. Chessboard corners are used to calculate the relation between 2D image points and 3D world points. In addition, we perform a weighted joint residual refinement. With our fisheye camera calibration method, we can attain better camera parameters and produce a more accurate fisheye undistortion image. Experiment results shows that...
This paper presented an implementation of indoor environmental data collection with the localization module. Since where the environmental data is collected can be known, the distribution of the environmental data in an indoor environment would be presented. The small and light weight sensors are employed here and equipped on a mobile platform such that the mobile platform can freely cruise in the...
This paper proposes a new spatio-temporal appearance feature named Phasic Maximal and Local Maximal Occurrence (PM-LOMO) representation for video-based person re-identification. To perform temporal alignment of the sequence, we selected the optimal period of walking cycle and divide frames into several phases based on the extreme points of the sequence's Flow Energy Profile (FEP). To describe the...
Automatic and accurate human upper-body detection and orientation estimation have great practical value in several computer vision applications. Most previous works on human upper-body orientation estimation assume that the human upper-body region is already detected and aligned. However, this is not the case in many real-world scenarios. Additional human detector is essential which is usually much...
Photos crowdsourced from mobile devices can be used in many applications such as disaster recovery to obtain information about a target area. However, such applications often have resource constraints in terms of bandwidth, storage, and processing capability, which limit the number of photos that can be crowdsourced. Thus, it is a challenge to use the limited resources to crowdsource photos that best...
Keeping students attentive during lectures may significantly improve learning outcomes. Traditional methods of attention estimation cannot offer a real-time feedback to the teacher. We present a technical concept of student attention monitoring during a lecture. The system utilizes a set of cameras providing tracking of the behavior of individual students in the classroom. The monitoring system is...
This study addresses issues of vehicular mobility scenario generation using the framework called En Route. By applying the framework to planet scale imagery dataset (traffic cameras) we were able to model the traffic demand of a large scale urban scenario (city of London) by means of origin/destination matrix and trips starting within 30 minutes. Along the way, we investigate the relationship of traffic...
Vehicular mobility scenarios are utilized to study vehicular networks and transportation systems. However, the generation of vehicular simulation scenarios at scale poses several research challenges. Large-scale vehicular datasets (in geographic coverage and time span) are not easily or publicly available, which hinders the generation of data-driven scenarios. In this paper, we introduce a systematic...
Traditional, the hardcopy of cadastral map is an important historical evidence for the land parcels information in the Land Office. However, the paper is not easy to save and the size of the scanner is not large enough for digital storage either. In this study, multi-view image processing technology is applied to create a true ortho-photo of cadastral map for solving the storage problem.
In this paper, we present an improved motion estimation method by adding extra information for binocular visual odometry (VO) which is especially suited for improving high-speed pose change estimation. The extra information is obtained by structured object detecting, taking lane line detection as an example. We can get an accurate position information by calculating the interval of each dotted lane...
The rapid-bubble-growth instability at the onset of flow boiling was studied experimentally in a single, 500 pm-diameter borosilicate glass microchannel subjected to a uniform heat flux of 41.9 kW/m2. Fluid was driven through the microchannel in an open-loop test facility by maintaining a constant pressure difference between a pressurized upstream reservoir and the ambient. Simultaneous measurement...
Flexible electronics provide new design options not afforded by rigid electronics in a variety of applications including wearable electronics, robotics and automotive systems. However, the processes for the manufacturing of complex electronic assemblies using fine-pitch components are not as well developed as those for rigid electronics. The lack of structural rigidity of flexible printed circuit...
The increasing age of infrastructure such as bridges or tall buildings requires a significant effort to be performed with respect to inspection such that damage being considered critical can be recognized early in advance and a respective infrastructure management can be performed. Many countries take the advantage of advance in Unmanned Aerial Vehicle technologies and applied for mostly aerial mapping...
The feature of central projection will result the pixels offset for UAV aerial photos. This problem can be solved by way of correcting relief displacement of DEM that was constructed by dense point cloud. During the image processing procedure, the creation of dense point cloud spent the most time. By cutting the image into blocks to reduce the creating time of high dense point cloud is the main issue...
Image stitching technique is to integrate multiple images with overlapping regions into a complete image with a wide viewing angle, less distortion, and no obvious suture. Image stitching could be used for global positioning and robot autonomous navigation without changing the hardware. SIFT feature and SURF feature are the classical algorithm in the image stitching. But they have the long time-consuming...
Various coordinate systems of cadastral map are not very easy to be unified in Taiwan area due to temporal-spatial limitation of these maps. Therefore, the urban planning map, topographic map and other base map cannot integrate into geographic information system (GIS) for additional value-added applications. Cadastral map is directly related to the people's property, it is essential to develop “three...
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.