Genetics Based Compact Fuzzy System for Visual Sensor Network

As a component of Wireless Sensor Network(WSN),Visual-WSN(VWSN)utilizes cameras to obtain relevant data including visual recordings and static images.Data from the camera is sent to energy efficient sink to extract key-information out of it.VWSN applications range from health care monitoring to military surveillance.In a network with VWSN,there are multiple challenges to move high volume data from a source location to a target and the key challenges include energy,memory and I/O resources.In this case,Mobile Sinks(MS)can be employed for data collection which not only collects information from particular chosen nodes called Cluster Head(CH),it also collects data from nearby nodes as well.The innovation of our work is to intelligently decide on a particular node as CH whose selection criteria would directly have an impact on QoS parameters of the system.However,making an appropriate choice during CH selection is a daunting task as the dynamic and mobile nature of MSs has to be taken into account.We propose Genetic Machine Learning based Fuzzy system for clustering which has the potential to simulate human cognitive behavior to observe,learn and understand things from manual perspective.Proposed architecture is designed based on Mamdani’s fuzzy model.Following parameters are derived based on the model residual energy,node centrality,distance between the sink and current position,node centrality,node density,node history,and mobility of sink as input variables for decision making in CH selection.The inputs received have a direct impact on the Fuzzy logic rules mechanism which in turn affects the accuracy of VWSN.The proposed work creates a mechanism to learn the fuzzy rules using Genetic Algorithm(GA)and to optimize the fuzzy rules base in order to eliminate irrelevant and repetitive rules.Genetic algorithmbased machine learning optimizes the interpretability aspect of fuzzy system.Simulation results are obtained using MATLAB.The result shows that the classification accuracy increase along with minimizing fuzzy rules count and thus it can be inferred that the suggested methodology has a better protracted lifetime in contrast with Low Energy Adaptive Clustering Hierarchy(LEACH)and LEACHExpected Residual Energy(LEACH-ERE).

Specific-Scene Oriented Pedestrian Detection in Visual Sensor Network

Pedestrian detection is one of the most important problems in the visual sensor network. Considering that the visual sensors have limited cap ability, we propose a pedestrian detection method with low energy consumption. Our method contains two parts: one is an Enhanced Self-Organizing Background Subtraction (ESOBS) based foreground segmentation module to obtain active areas in the observed region from the visual sensors; the other is an appearance model based detection module to detect the pedestrians from the foreground areas. Moreover, we create our own large pedestrian dataset according to the specific scene in the visual sensor network. Numerous experiments are conducted in both indoor and outdoor specific scenes. The experimental results show that our method is effective.

Vision-based detection of weld pool width in TIG welding of copper-clad aluminum cable

In order to realize automatic control of the width of weld pool, a visual sensor system for the width of weld pool detection is developed. By initiative arc light, the image of copper plate weld pool is taken back of the torch through the process of weakening and filtering arc light. In order to decrease the time of processing video signals, analog circuit is applied in the processing where video signals is magnified, trimmed and processed into binary on the datum of dynamic average value, therefore the waveform of video signals of weld pool is obtained. The method that is used for detecting the width of weld pool is established. Results show that the vision sensing method for real-time detecting weld pool width to copper-clad aluminum wire TIG welding is feasible. The response cycle of this system is no more than 50 ms, and the testing precision is less than 0. 1 mm.

Weld pool image sensor for pulsed MIG welding

Visual image sensor is developed to detect the weld pool images in pulsed MIG welding. An exposure controller, which is composed of the modules of the voltage transforming, the exposure parameters presetting, the complex programmable logic device （CPLD） based logic controlling, exposure signal processing, the arc state detecting, the mechanical iris driving and so on, is designed at first. Then, a visual image sensor consists of an ordinary CCD camera, optical system and exposure controller is established. The exposure synchronic control logic is described with very-high-speed integrated circuit hardware description language （VHDL） and programmed with CPLD , to detect weld pool images at the stage of base current in pulsed MIG welding. Finally, both bead on plate welding and V groove filled welding are carried out, clear and consistent weld pool images are acquired.

A New Calibration Method for an Inertial and Visual Sensing System

The relative pose between inertial and visual sensors equipped in autonomous robots is calibrated in two steps. In the first step, the sensing system is moved along a line, the orientations in the relative pose are computed from at least five corresponding points in the two images captured before and after the movement. In the second step, the translation parameters in the relative pose are obtained with at least two corresponding points in the two images captured before and after one step motion. Experiments are conducted to verify the effectiveness of the proposed method.

Efective Object Identification and Association by Varying Coverage Through RFID Power Control

This paper presents an effective power scheduling strategy for energy efficient multiple objects identification and association. The proposed method can be utilized in many heterogeneous surveillance systems with visual sensors and RFID （radio-frequency identification） readers where energy efficiency as well as association rate are critical Multiple objects positions and trajectory estimates are used to decide the power level of RFID readers. Several key parameters including the time windows and the distance separations are defined in the method in order to minimize the effects of RFID coverage uncertainty. The power cost model is defined and incorporated into the method to minimize energy consumption and to maximize association performance. The proposed method computes the power cost using the range of the outermost position for possible single association and group associations at every sampling time. An RFID reader is activated with the proper coverage range when the power cost for the current time is lower than the power cost for the next time sample. The simplicity of the power cost model relieves the problematic combinatorial comparisons in multiple object cases. The performance comparison simulation with the minimum and maximum energy consumption shows that the proposed method achieves fast single associations with less energy consumption. Finally, the realistic comparison simulation with the fixed range RFID readers demonstrates that the proposed method outperforms the fixed ranges in terms of single association rate and energy consumption.

Low-Cost Approach for Improving Video Transmission Efficiency in WVSN

The wireless visual sensor network(WVSN)as a new emerged intelligent visual system,has been applied in many video monitoring sites.However,there is still great challenge because of the limited wireless network bandwidth.To resolve the problem,we propose a real-time dynamic texture approach which can detect and reduce the temporal redundancy during many successive image frames.Firstly,an adaptively learning background model is improved to discover successive similar image frames from the inputting video sequence.Then,the dynamic texture model based on the singular value decomposition is adopted to distinguish foreground and background element dynamics.Furthermore,a background discarding strategy based on visual motion coherence is proposed to determine whether each image frame is streamed or not.To evaluate the trade-off performance of the proposed method,it is tested on the CDW-2014 dataset,which can accurately detect the first foreground frame when the moving objects of interest appear in the field of view in the most tested dynamic scenes,and the misdetection rate of the undetected foreground frames is near to zero.Compared to the original stream,it can reduce the occupied bandwidth a lot and its computational cost is relatively lower than the state-of-the-art methods.