13 research outputs found
Development of site-specific non-intrusive load monitoring for maximum demand control
No full textDemand-side load management (DSM) requires greater role-play by endusers. To lower the investment for this load management concept, nonintrusive load management (NILM) was introduced as the solution. However, most of the mathematical techniques used in NILM are complex. This may hinder users from actively take part in the energy management effort. This paper explores the possibilities of applying change point detection techniques with help of differentiation and application of filters. These filters were selected strictly based on site-specific conditions. As part of the NILM implementation, a new and practical technique was developed for this paper. It was found that the developed technique, despite its simplicity it can identify the electrical equipment which added the significant load demand. The performance of the technique was found to be satisfactory as compared to results reported by other researchers
A comparative study using different classifiers for face verification
No full textFace recognition, verification and identification are often confused. Face recognition is a general topic that includes both face identification and face verification (also called authentication). On one hand, face verification is concerned with validating a claimed identity based on the image of a face, and either accepting or rejecting the identity claim (one-to-one matching)
Performance evaluation of face verification: a comparative study on different classifiers
No full textThe task offace verification is to verify the identity or decide whether the a priori user is an impostor or not from the known a priori identity of the user. The paper presents the performance evaluation carried out using different classifiers for face verification. The paper initially describes the approaches used for the face representation. and classification of face verification system. It then evaluates the performance of the system by applying three types of classifier: template-based matching, artificial neural network classifier. and Bayesian classifier based on AT & T and local face daJasets. The measures used for performance evaluation are the false acceptance rate (FAR) and false rejection rate (FAR). Based on the experimental results, the artificial neural network classifier provides promising results for face verification with FAR of 4.44% and FRR 4.50% using AT&T face daJaset, and FAR of 3.88 and FRR 4.00 % using local face dataset
Human motion detection and classification
No full textHuman Motion Detection is one of the most challenging problems in computer vision due to the huge quantity of possible cases. The number of postures depends on the degree of freedom of the human body (i.e. the articulations such as shoulders or knees). Moreover, the morphology of the person (height, corpulence, etc) influences the perception of the posture.vFurthermore, clothes can also give different types of appearances for the same postur
Evaluation of the IEEE 802.11p-based TDMA MAC method for road side-to-vehicle communications
No full textWireless vehicular communications (WVC) has been identified as a key technology for intelligent transportation systems (ITS) for a few years ago. IEEE 802.11p is the proposed standard for physical and MAC layer of WVC devices. The main objective of the standard is to change the frame format and increase delay spread tolerance introduced by vehicle mobility, in which the channel bandwidth is scaled from 20 MHz i.e.802.11a to 10 MHz i.e. 802.11p. This paper proposes TDMA technique with fixed time slots and guard band
between slots to ensure interoperability between wireless devices communicate in rapidly changing environment where transactions must be completed in small timeframe. The new TDMA sub-layer is proposed to be on-top of the conventional 802.11p MAC. The simulation results present the performance analysis and validate the efficiency of the proposed scheme
Intelligent auto tracking in 3D space by image processing
No full textA robotic vision system has been designed and analyzed for real time tracking of maneuvering objects. Passive detection using live TV images provides the tracking signals derived from the video data. The calibration and orientation of two cameras is done by a bundle adjustment technique. The target location algorithm determines the centroid coordinates of the target in the image plane and relates it to the aim point in the object plane. The stereoscopic images provide the information, from which the range, r of the object can be determined. The azimuth, thetas and elevation, phi of the target with respect to a certain origin are determined by correlating the x-y displacements of the centroid in the image plane with the angular displacement of the target in the object plane. The servo drive signals for both the robot motion and the angular positioning of the cameras are derived from the image processing algorithm that keeps the centroid of the target image in the center of the frame and the target in line with the axis of the optical system. Hence, the spherical coordinates of the target are defined and updated with every TV frame. The time development of the centroid in successive TV frames represents the real time trajectory of the target path. A non-linear prediction technique keeps the target within the aim zone of the tracking system. In order to minimize the image processing time, i.e. kept within the demand of real time operation, one TV frame time, an image segmentation process is made to subtract nearly all redundant background details
