Continuous localization and mapping of a pan–tilt–zoom camera for wide area tracking

Pan–tilt–zoom (PTZ) cameras are well suited for object identification and recognition in far-field scenes. However, the effective use of PTZ cameras is complicated by the fact that a continuous online camera calibration is needed and the absolute pan, tilt and zoom values provided by the camera actuators cannot be used because they are not synchronized with the video stream. So, accurate calibration must be directly extracted from the visual content of the frames. Moreover, the large and abrupt scale changes, the scene background changes due to the camera operation and the need of camera motion compensation make target tracking with these cameras extremely challenging. In this paper, we present a solution that provides continuous online calibration of PTZ cameras which is robust to rapid camera motion, changes of the environment due to varying illumination or moving objects. The approach also scales beyond thousands of scene landmarks extracted with the SURF keypoint detector. The method directly derives the relationship between the position of a target in the ground plane and the corresponding scale and position in the image and allows real-time tracking of multiple targets with high and stable degree of accuracy even at far distances and any zoom level.     

Virtual wiper — removal of adherent noises from images of dynamic scenes by using a pan–tilt camera

In this paper, we propose a new method that can remove noises from images of dynamic scenes that can cause viewing problems. One of the thorny problems in outdoor surveillance by a camera is that adherent noises such as waterdrops or mud blobs on the protecting glass surface lens disturb the view from the camera. Therefore, we propose a method for removing adherent noises from images of dynamic scenes taken by changing the direction of a pan–tilt camera, which is often used for surveillance. Our method is based on the comparison of two images — a reference image and a second image taken by a different camera angle. The latter image is transformed by a projective transformation and subtracted from the reference image to extract the regions of adherent noises and moving objects. The regions of adherent noises in the reference image are identified by examining the shapes and distances of regions existing in the subtracted image. Finally, regions of adherent noises can be eliminated by merging two images. Experimental results show the effectiveness of our proposed method.     

Fuzzy fault tree analysis based on T–S model with application to INS/GPS navigation system

A novel fault tree analysis (FTA) technique based on the Takagi and Sugeno (T–S) model is proposed in this paper. In the proposed technique, referred to as the TS-FTA, the events in the conventional FTA can be expressed in terms of fuzzy possibilities, and the gates that represent the relations among the top event and the primary events are replaced by T–S fuzzy gates derived from the T–S model. The magnitudes of the faults in the system are expressed in term of fuzzy variables. Since the proposed TS-FTA is derived from fuzzy logic and the T–S model, it can readily handle fuzzy information and uncertainties in the relationships among events. Therefore, the TS-FTA is suitable for systems where exact information on the fault probabilities of the components and the failure mechanisms are not available. The proposed TS-FTA is applied to analyze the reliability of an Inertial Navigation System and Global Position System (INS/GPS) integrated navigation system.     

Structure and stability analysis of a Takagi–Sugeno fuzzy PI controller with application to tissue hyperthermia therapy

 In this paper, we first reveal the analytical structure of a simple Takagi–Sugeno (TS) fuzzy PI controller relative to the linear PI controller. The fuzzy controller consists of two linear input fuzzy sets, four TS fuzzy rules with linear consequent, Zadeh fuzzy logic AND and the centroid defuzzifier. We prove that the fuzzy controller is actually a nonlinear PI controller with the gains changing with process output. Utilizing the well-known small Gain Theorem in control theory, we then derive sufficient conditions for global stability of the fuzzy control systems involving the TS fuzzy PI controller. Finally, as an application demonstration, we apply the fuzzy PI controller to control issue temperature, in computer simulation, during hyperthermia therapy. The relationship between heat energy and tissue temperature is represented by a linear time-varying model with a time delay. The sufficient conditions for global stability are used to design a stable fuzzy control system. Our simulation results show that the fuzzy PI control system achieves satisfactory temperature control performance. The control system is robust and stable even when the model parameters are changed suddenly and significantly.     

An optimised product-unit neural network with a novel PSO–BP hybrid training algorithm: Applications to load–deformation analysis of axially loaded piles

In general, neural network training is a nonlinear multivariate optimisation problem. Unlike previous studies, in the present study, particle swarm optimisation (PSO) and back-propagation (BP) algorithms were coupled to develop a robust hybrid training algorithm with both local and global search capabilities. To demonstrate the capacity of the proposed model, we applied the model to the predictions of the load–deformation behaviour of axially loaded piles. This is a soil–structure interaction problem, involving a complex mechanism of load transfer from the pile to the supporting geologic medium. A database of full scale pile loading tests is used to train and validate the product-unit network. The results show that the proposed hybrid learning algorithm simulates the load–deformation curve of axially loaded piles more accurately than other BP, PSO, and existing PSO–BP hybrid methods. The network developed using the proposed algorithm also turns out to be more accurate than hyperbolic and $t?z$ models.     

Time-series analysis of chlorophyll-a,sea surface temperature,and sea surface height anomalies during 2003–2014 with special reference to El Niño,La Niña,and Indian Ocean Dipole (IOD) Years

The present study was carried out to find the variability of chlorophyll-a (chl-a) concentration, sea surface temperature (SST), and sea surface height anomalies (SSHa) during 2003–2014, covering the Bay of Bengal (BoB) and Arabian Sea (AS) waters. These parameters were linked with El Niño, La Niña, and Indian Ocean Dipole (IOD) years. The observed results during 2003–2014 were evaluated and it was found that the monthly mean value for 12-year data ranged as follows: chl-a (0.11–0.46 mg m^?3), SST (27–31 °C), and SSHa (?0.2 to 20 cm). The annual mean range of chl-a for 12-year data was 0.1–0.23 mg m^?3, the SST range was 27–28 °C, and the SSHa range was 2.14–13.91 cm. It has been observed that with the SST range of 27–28 °C and the SSHa range of 7–9 cm, the chl-a concentration enhanced to 0.20–0.23 mg m^?3. With a higher SST range of 28–29 °C and with a positive SSHa range of 11–14 cm, the chl-a concentration appeared to be low (0.17–0.18 mgm^?3). During normal years, SSHa was positive with the >5 to <10 cm range during the months of April–June, which coincided with an increase in SST, >2 to <4 °C. During the normal years, SSHa (>?0.2 to a concentration (>0.3 to <0.5 mg m^?3) was noticed during December–February in the BoB and AS. Compared to the BoB chl-a range (<0.4 mg m^?3), a high chl-a concentration was observed in AS (>0.4 mg m^?3). However, during the phenomenon years, the study area had experienced low chl-a (<0.2 mg m^?3), high SST (>5 °C), and more positive SSHa (>10 to <20 cm) during January–March and October–December in AS and BoB. The present study infers that a positive IOD leads to low chl-a concentration (<2 mg m^?3) and low primary productivity in AS. El Niño caused the down-welling process, it results in a low chl-a concentration (<1 mg m^?3) in BoB and AS. La Niña caused the upwelling process, and it results in a high chl-a concentration (>2.0 mg m^?3) in BoB and AS. In the recent past years (2003–2014), the intensity and frequency of El Niño, La Niña, and IOD have been increasing, evidenced with few studies, and have impacts on the Indian Ocean climate. Therefore, the influences of the relative changes of these phenomena on the BoB and AS need to be understood for productivity assessment and ocean state monitoring.