Recommender systems usually propose items to single users. However, in some domains like Mobile IPTV or Satellite Systems it might be impossible to generate a program schedule for each user, because of bandwidth limit...
详细信息
Recommender systems usually propose items to single users. However, in some domains like Mobile IPTV or Satellite Systems it might be impossible to generate a program schedule for each user, because of bandwidth limitations. A few approaches were proposed to generate group recommendations. However, these approaches take into account that groups of users already exist and no recommender system is able to detect intrinsic users communities. This paper describes an algorithm that detects groups of users whose preferences are similar and predicts recommendations for such groups. Groups of different granularities are generated through a modularity-based Community detection algorithm, making it possible for a content provider to explore the trade off between the level of personalization of the recommendations and the number of channels. Experimental results show that the quality of group recommendations increases linearly with the number of groups created.
In this paper, we propose a vision based monitoring system for passenger's safety in railway platform. The detection algorithm of the proposed system exploits stereo vision algorithm to improve system detection pe...
详细信息
ISBN:
(纸本)9781424424900
In this paper, we propose a vision based monitoring system for passenger's safety in railway platform. The detection algorithm of the proposed system exploits stereo vision algorithm to improve system detection performance because railway platform has various illumination conditions due to train arrival and departure in the scene. The vision based monitoring system detects possible accidents, such as a fallen passenger on the track, getting stuck between the train doors, and so on, and informs operators about the accident with alarm in order to promptly make a deal with the emergency. In the paper, the system configuration, detection process and test result of detection performance are presented.
Recent years HOG algorithm has been used to recognize objects in images, with complex content, with a very high success rate. Hardware implementation of this algorithm is very important because of the fact that it can...
详细信息
Recent years HOG algorithm has been used to recognize objects in images, with complex content, with a very high success rate. Hardware implementation of this algorithm is very important because of the fact that it can be used in many object recognition applications. In this work HOG algorithm is implemented on FPGA to recognize different geometrical figures with a very high success rate. Objects vertical and horizontal edges have been sharpened using edge detection algorithms to calculate magnitude and angle of the local gradients. Obtained result are used to construct the histograms of gradient orientation. It is observed that each constructed histogram have distinctive features for every object. Rule based classifiers has been used to implement a successful real time object recognition approach on embedded system.
This paper describes a sensorless position and speed detection algorithm designed for permanent magnet linear synchronous motor (PMLSM) drive. Measured line currents and terminal voltages are used to estimate the flux...
详细信息
This paper describes a sensorless position and speed detection algorithm designed for permanent magnet linear synchronous motor (PMLSM) drive. Measured line currents and terminal voltages are used to estimate the flux of the α-β axis in stator frame, integrating the back electromotive force (EMF). Position and speed signals are derived from angle of the flux linkage and its change rate. A new improved integrator is presented and analyzed for compensate DC offsets and drift, which invariably exist in any practical implementation based on combination of low-pass filter, highpass filter and PI regulator. Experimental results are presented to show the realization of the objectives.
Image matching is usually used in tire disfigurement recognition. Traditional template matching methods such as the NC and the SSDA have high matching precision, but the calculating is hard and time consuming. The fas...
详细信息
Image matching is usually used in tire disfigurement recognition. Traditional template matching methods such as the NC and the SSDA have high matching precision, but the calculating is hard and time consuming. The fast template matching algorithm based on the projection and the KMP algorithm has been proposed. Firstly, the feature string is gotten by projecting the image followed by matching it to get the approximate matching results. Secondly, the NC method is used to validate the approximate matching results. The algorithm has been used in the tire disfigurement recognition based on image matching and proven to be efficient.
Eye tracking is the focus problem in the researching domain of human-machine interaction and computer vision in recent years. The method of using a single eye location and detection algorithm has poor real-time perfor...
详细信息
Eye tracking is the focus problem in the researching domain of human-machine interaction and computer vision in recent years. The method of using a single eye location and detection algorithm has poor real-time performance. So a new eye tracking method is proposed in this paper. This method combines the location and detection algorithm with the grey prediction for eye tracking. The GM(1,1) model is used to predict the position of moving eye in the next frame, and then this position is taken as the reference point for the searching region of eye. The efficiency of eye tracking is improved in this way. Experimental results for image sequence of eye maneuvering show that the grey prediction model GM(1,1) can track eye region robustly and correctly because it doesnpsilat assume the moving law in advance, and weaken the effect of random disturbances by results of accumulated generating operation to explore the law of eye motion.
This paper presents a lecture video structuring and analysis scheme to provide students an efficient way to access the lecture content. Instead of using color-based or histogram-based methodologies, we propose a new e...
详细信息
This paper presents a lecture video structuring and analysis scheme to provide students an efficient way to access the lecture content. Instead of using color-based or histogram-based methodologies, we propose a new edge-based shot boundary detection algorithm to accurately rebuild the slide structure. The proposed approach can successfully resist the unwanted influences induced from the variant illumination condition and occlusions. Besides, original slide content can be extracted excluding any obstruction by using human removing techniques. Furthermore, the teaching focus is analyzed so that this system becomes more useful for learning.
Thermography, or thermal visualization is a type of infrared visualization. Thermographic cameras are used in many heavy factories like metal recycling factories, wafer production factories and etc for monitoring the ...
详细信息
Thermography, or thermal visualization is a type of infrared visualization. Thermographic cameras are used in many heavy factories like metal recycling factories, wafer production factories and etc for monitoring the temperature conditions of the machines. Besides, thermographic camera can be used to detect trespassers in environment with poor lighting condition, whereby, the conventional digital cameras are less applicable in. In this paper, we proposed two simple and fast detection algorithms into a cost effective thermal imaging surveillance system. This surveillance system not only used in monitoring the functioning of different machinery and electrical equipments in a factory site, it can also used for detecting the trespassers in poor lighting condition. Experimental results show that the proposed surveillance system achieves high accuracy in monitoring machines conditions and detecting trespassers.
In this paper, mobile lane departure warning systems (M-LDWS) are addressed. The proposed lane departure warning (LDW) detection algorithm has been successfully implemented on handheld devices with their build-in came...
详细信息
In this paper, mobile lane departure warning systems (M-LDWS) are addressed. The proposed lane departure warning (LDW) detection algorithm has been successfully implemented on handheld devices with their build-in cameras. The users as long as download LDW program to their own mobile phones and the driving safety service will be enabled. M-LDWS is settled behind the windshield and the driver will be alerted when his car departs from the host lane. M-LDWS detects lane boundaries ahead the host vehicle and estimates the position within the host lane by the captured real-time image. It is qualified to be applied on highways, expressways and urban roadways in Taiwan. It also has been successfully verified in sunny, cloudy and rainy conditions for day and night. M-LDWS will be a novel killer application in consumer devices for driving assistance systems.
Due to the capacity achievable, Multiple-Input Multiple-Output (MIMO) systems witnessed more interest in recent years. Several data detection algorithms are available for MIMO systems, especially the tree-search ones ...
详细信息
ISBN:
(纸本)9781424443970;9781424443987
Due to the capacity achievable, Multiple-Input Multiple-Output (MIMO) systems witnessed more interest in recent years. Several data detection algorithms are available for MIMO systems, especially the tree-search ones which offer lower complexity comparing to the ML receiver. In this paper, we are interested in one of tree-search algorithms, which is the Stack decoder. Nevertheless, the stack decoder is only proposed to decode MIMO systems employing finite constellations, as the QAM (Quadrature Amplitude Modulation). In this work, we introduce a new Stack decoder capable of decoding lattice and we call it the M-Stack decoder. The principle idea behind it is to generate M nodes at each tree-level and so to reduce the infinite alphabet of the lattice to only M components at each step. Then, we propose to adapt it to decode QAM constellations. This one is compared to the known QRD-Stack algorithm. While both visit the same number of nodes, the proposed M-Stack algorithm offers lower computational complexity and it is much faster than the QRD-Stack one.
暂无评论