Multi-sensor Data Fusion Approach Research Articles

Assessment of Data Fusion Algorithms for Earth Observation Change Detection Processes.

In this work a parametric multi-sensor Bayesian data fusion approach and a Support Vector Machine (SVM) are used for a Change Detection problem. For this purpose two sets of SPOT5-PAN images have been used, which are in turn used for Change Detection Indices (CDIs) calculation. For minimizing radiometric differences, a methodology based on zonal “invariant features” is suggested. The choice of one or the other CDI for a change detection process is a subjective task as each CDI is probably more or less sensitive to certain types of changes. Likewise, this idea might be employed to create and improve a “change map”, which can be accomplished by means of the CDI’s informational content. For this purpose, information metrics such as the Shannon Entropy and “Specific Information” have been used to weight the changes and no-changes categories contained in a certain CDI and thus introduced in the Bayesian information fusion algorithm. Furthermore, the parameters of the probability density functions (pdf’s) that best fit the involved categories have also been estimated. Conversely, these considerations are not necessary for mapping procedures based on the discriminant functions of a SVM. This work has confirmed the capabilities of probabilistic information fusion procedure under these circumstances.

Integration of full-waveform LiDAR and hyperspectral data to enhance tea and areca classification

Hyperspectral image and full-waveform light detection and ranging (LiDAR) data provide useful spectral and geometric information for classifying land cover. Hyperspectral images contain a large number of bands, thus providing land-cover discrimination. Waveform LiDAR systems record the entire time-varying intensity of a return signal and supply detailed information on geometric distribution of land cover. This study developed an efficient multi-sensor data fusion approach that integrates hyperspectral data and full-waveform LiDAR information on the basis of minimum noise fraction and principal component analysis. Then, support vector machine was used to classify land cover in mountainous areas. Results showed that using multi-sensor fused data achieved better accuracy than using a hyperspectral image alone, with overall accuracy increasing from 83% to 91% using population error matrices, for the test site. The classification accuracies of forest and tea farms exhibited significant improvement when fused data were used. For example, classification results were more complete and compact in tea farms based on fused data. Fused data considered spectral and geometric land-cover information, and increased the discriminability of vegetation classes that provided similar spectral signatures.

Freeway Multisensor Data Fusion Approach Integrating Data from Cellphone Probes and Fixed Sensors

Freeway traffic state information from multiple sources provides sufficient support to the traffic surveillance but also brings challenges. This paper made an investigation into the fusion of a new data combination from cellular handoff probe system and microwave sensors. And a fusion method based on the neural network technique was proposed. To identify the factors influencing the accuracy of fusion results, we analyzed the sensitivity of those factors by changing the inputs of neural-network-based fusion model. The results showed that handoff link length and sample size were identified as the most influential parameters to the precision of fusion. Then, the effectiveness and capability of proposed fusion method under various traffic conditions were evaluated. And a comparative analysis between the proposed method and other fusion approaches was conducted. The results of simulation test and evaluation showed that the fusion method could complement the drawback of each collection method, improve the overall estimation accuracy, adapt to the variable traffic condition (free flow or incident state), suit the fusion of data from cellphone probes and fixed sensors, and outperform other fusion methods.

Monitoring daily evapotranspiration over two California vineyards using Landsat 8 in a multi-sensor data fusion approach

Abstract California's Central Valley grows a significant fraction of grapes used for wine production in the United States. With increasing vineyard acreage, reduced water availability in much of California, and competing water use interests, it is critical to be able to monitor regional water use and evapotranspiration (ET) over large areas, but also in detail at individual field scales to improve water management within these viticulture production systems. This can be achieved by integrating remote sensing data from multiple satellite systems with different spatiotemporal characteristics. In this research, we evaluate the utility of a multi-scale system for monitoring ET as applied over two vineyard sites near Lodi, California during the 2013 growing season, leading into the drought in early 2014. The system employs a multi-sensor satellite data fusion methodology (STARFM: Spatial and Temporal Adaptive Reflective Fusion Model) combined with a multi-scale ET retrieval algorithm based on the Two-Source Energy Balance (TSEB) land-surface representation to compute daily ET at 30 m resolution. In this system, TSEB is run using thermal band imagery from the Geostationary Environmental Operational Satellites (GOES; 4-km spatial resolution, hourly temporal sampling), the Moderate Resolution Imaging Spectroradiometer (MODIS) data (1 km resolution, daily acquisition) and the new Landsat 8 satellite (sharpened to 30 m resolution, ~ 16 day acquisition). Estimates of daily ET generated in two neighboring fields of Pinot noir vines of different age agree with ground-based flux measurements acquired in-field during most of the 2013 season with relative mean absolute errors on the order of 19–23% (root mean square errors of approximately 1 mm d − 1 ), reducing to 14–20% at the weekly timestep relevant for irrigation management (~ 5 mm wk − 1 ). A model overestimation of ET in the early season was detected in the younger vineyard, perhaps relating to an inter-row grass cover crop. Spatial patterns of cumulative ET generally correspond to measured yield maps and indicate areas of variable crop moisture, soil condition, and yield within the vineyards that could require adaptive management. The results suggest that multi-sensor remote sensing observations provide a unique means for monitoring crop water use and soil moisture status at field-scales over extended growing regions, and may have value in supporting operational water management decisions in vineyards and other high value crops.

Data Fusion of Acoustics, Infrared, and Marine Radar for Avian Study

A multisensor data fusion approach via acoustics, infrared camera, and marine radar is proposed and described in the application of avian monitoring. The ultimate scope of avian monitoring is to preserve the population of birds and bats, especially those listed in the endangered list, by observing their activity and behavior over the migration period. With the significant attention toward the construction of off-shore/on-shore wind farms in recent decades, the wind turbines are more threatening the avian life with increasing the risk of birds/bats collision with turbine blades. In order to address this problem, this paper proposes a fuzzy Bayesian-based multisensory data fusion approach to provide the activity information regarding the targets in the application of avian monitoring. The developed technique is used to process the Spring and Fall 2011 migration period.

A ground temperature map of the North Atlantic permafrost region based on remote sensing and reanalysis data

Abstract. Permafrost is a key element of the terrestrial cryosphere which makes mapping and monitoring of its state variables an imperative task. We present a modeling scheme based on remotely sensed land surface temperatures and reanalysis products from which mean annual ground temperatures (MAGT) can be derived at a spatial resolution of 1 km at continental scales. The approach explicitly accounts for the uncertainty due to unknown input parameters and their spatial variability at subgrid scale by delivering a range of MAGTs for each grid cell. This is achieved by a simple equilibrium model with only few input parameters which for each grid cell allows scanning the range of possible results by running many realizations with different parameters. The approach is applied to the unglacierized land areas in the North Atlantic region, an area of more than 5 million km2 ranging from the Ural Mountains in the east to the Canadian Archipelago in the west. A comparison to in situ temperature measurements in 143 boreholes suggests a model accuracy better than 2.5 °C, with 139 considered boreholes within this margin. The statistical approach with a large number of realizations facilitates estimating the probability of permafrost occurrence within a grid cell so that each grid cell can be classified as continuous, discontinuous and sporadic permafrost. At its southern margin in Scandinavia and Russia, the transition zone between permafrost and permafrost-free areas extends over several hundred km width with gradually decreasing permafrost probabilities. The study exemplifies the unexploited potential of remotely sensed data sets in permafrost mapping if they are employed in multi-sensor multi-source data fusion approaches.

Multi sensor data fusion approach for automatic honeycomb detection in concrete

We present a systematic approach for fusion of multi-sensory nondestructive testing data. Our data set consists of impact-echo, ultrasonic pulse echo and ground penetrating radar data collected on a large-scale concrete specimen with built-in honeycombing defects. From each data set, the most significant signatures of honeycombs were extracted in the form of features. We applied two simple data fusion algorithms to the data: Dempster’s rule of combination and the Hadamard product. The performance of the fusion rules versus the single-sensor testing was evaluated. The fusion rules exhibit a slight improvement of false alarm rate over the best single sensor.

Rapid and accurate reverse engineering of geometry based on a multi-sensor system

The reduction of the lead time in measurement and reverse engineering, and the increased requirements in terms of accuracy and flexibility, have resulted in a great deal of research effort aimed at developing and implementing multi-sensor systems. This paper describes an effective competitive approach for using a tactile probe to compensate the data from a laser line scanner to perform accurate reverse engineering of geometric features. With the data acquired using laser scanning, intelligent feature recognition and segmentation algorithms can be exploited to extract the global surface information of the object. The tactile probe is used to re-measure the geometric features with a small number of sampling points and the obtained information can be subsequently used to compensate the point data patches which are measured by laser scanning system. Then, the compensated point data can be exploited for accurate reverse engineering of a CAD model. The limitations of each measurement system are compensated by the other. Experimental results on three parts validate the rapidity and accuracy of this multi-sensor data fusion approach.

E-Nose and e-Tongue combination for improved recognition of fruit juice samples

There are many important challenges related to food security analysis by application of chemical and electrochemical sensors. One critical parameter is the development of reliable tools, capable of performing an overall sensory analysis. In these systems, as much information as possible is required in relation to smell, taste and colour. Here, we investigated the possibility of using a multisensor data fusion approach, which combines an e-Nose and an e-Tongue, adept in generating combined aroma and taste profiles. In order to shed light on this concept, classification of various Tunisian fruit juices using a low-level of abstraction data fusion technique was attempted. Five tin oxide-based Taguchi Gas Sensors were applied in the e-Nose instrument and the e-Tongue was designed using six potentiometric sensors. Four different commercial brands along with eleven fruit juice varieties were characterised using the e-Nose and the e-Tongue as individual techniques, followed by a combination of the two together. Applying Principal Component Analysis (PCA) separately on the respective e-Nose and e-Tongue data, only few distinct groups were discriminated. However, by employing the low-level of abstraction data fusion technique, very impressive findings were achieved. The Fuzzy ARTMAP neural network reached a 100% success rate in the recognition of the eleven-fruit juices. Therefore, data fusion approach can successfully merge individual data from multiple origins to draw the right conclusions that are more fruitful when compared to the original single data. Hence, this work has demonstrated that data fusion strategy used to combine e-Nose and e-Tongue signals led to a system of complementary and comprehensive information of the fruit juices which outperformed the performance of each instrument when applied separately.

Multisensor Data Fusion for Water Quality Evaluation Using Dempster-Shafer Evidence Theory

A multisensor data fusion approach for water quality evaluation using Dempster-Shafer evidence theory is presented. To evaluate water quality, each sensor measurement is considered as a piece of evidence. Based on the water quality parameters measured by sensor node, the mass function of water quality class is calculated. Evidence from each sensor is given a reliability discounting and then combined with the others by D-S rule. According to the decision rule which uses the fusion mass function values, the class of water quality can be determined. Finally, experiments are given to demonstrate that the proposed approach can evaluate water quality from uncertain sensor data and improve evaluation performance.

Sensor Fusion on Structural Monitoring Data Analysis: Application to a Cable-Stayed Bridge

This paper illustrates an application of Bayesian logic to monitoring data analysis and structural condition state inference. The case study is a 260 m long cable-stayed bridge spanning the Adige River 10 km north of the town of Trento, Italy. This is a statically indeterminate structure, having a composite steel-concrete deck, supported by 12 stay cables. Structural redundancy, possible relaxation losses and an as-built condition differing from design, suggest that long-term load redistribution between cables can be expected. To monitor load redistribution, the owner decided to install a monitoring system which combines built-on-site elasto-magnetic and fiber-optic sensors. In this note, we discuss a rational way to improve the accuracy of the load estimate from the EM sensors taking advantage of the FOS information. More specifically, we use a multi-sensor Bayesian data fusion approach which combines the information from the two sensing systems with the prior knowledge, including design information and the outcomes of laboratory calibration. Using the data acquired to date, we demonstrate that combining the two measurements allows a more accurate estimate of the cable load, to better than 50 kN.

Distributed multisensor data fusion based on kalman filtering and the parallel implementation

The purpose of data fusion is to produce an improved model or estimate of a system from a set of independent data sources. Various multisensor data fusion approaches exist, in which Kalman filtering is important. In this paper, a fusion algorithm based on multisensor systems is discussed and a distributed multisensor data fusion algorithm based on Kalman filtering presented. The algorithm has been implemented on cluster-based high performance computers. Experimental results show that the method produces precise estimation in considerably reduced execution time.

A FAULT TOLERANT MULTI-SENSOR NAVIGATION SYSTEM FOR AN UNMANNED SURFACE VEHICLE

This paper describes the development of an intelligent multi-sensor data fusion (MSDF) system with fault tolerance for an unmanned surface vehicle (USV). A fuzzy logic adaptive federated Kalman filter (FLA-FKF) algorithm is developed. In this novel MSDF approach, fuzzy logic techniques are implemented to adjust the measurement noise covariance matrix (R) to fit the actual statistics of the noise profile present in the incoming measured data using a covariance matching method. Also the information feedback factors employed in the FLA-FKF are tuned based on the accuracy of each sensor. Simulation results demonstrate the algorithm's capability under different types of sensor fault.

Some remarks on Kalman filters for the multisensor fusion

Abstract Multisensor data fusion has found widespread application in industry and commerce. The purpose of data fusion is to produce an improved model or estimate of a system from a set of independent data sources. There are various multisensor data fusion approaches, of which Kalman filtering is one of the most significant. Methods for Kalman filter based data fusion includes measurement fusion and state fusion. This paper gives first a simple a review of both measurement fusion and state fusion, and secondly proposes two new methods of state fusion based on fusion procedures at the prediction and update level, respectively, of the Kalman filter. The theoretical derivation for these algorithms are derived. To illustrate their application, a simple example is performed to evaluate the proposed methods and compare their performance with the conventional state fusion method and measurement fusion methods.