• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1633-1649
• /
• 2017

In remote sensing image processing, the traditional fusion algorithm is based on the Intensity-Hue-Saturation (IHS) transformation. This method does not take into account the texture or spectrum information, spatial resolution and statistical information of the photos adequately, which leads to spectrum distortion of the image. Although traditional solutions in such application combine manifold methods, the fusion procedure is rather complicated and not suitable for practical operation. In this paper, an improved IHS transformation fusion algorithm based on the local variance weighting scheme is proposed for remote sensing images. In our proposal, firstly, the local variance of the SPOT (which comes from French "Systeme Probatoire d'Observation dela Tarre" and means "earth observing system") image is calculated by using different sliding windows. The optimal window size is then selected with the images being normalized with the optimal window local variance. Secondly, the power exponent is chosen as the mapping function, and the local variance is used to obtain the weight of the I component and match SPOT images. Then we obtain the I' component with the weight, the I component and the matched SPOT images. Finally, the final fusion image is obtained by the inverse Intensity-Hue-Saturation transformation of the I', H and S components. The proposed algorithm has been tested and compared with some other image fusion methods well known in the literature. Simulation result indicates that the proposed algorithm could obtain a superior fused image based on quantitative fusion evaluation indices.

• Journal of Astronomy and Space Sciences
• /
• v.20 no.4
• /
• pp.359-364
• /
• 2003

In this paper, we present multi-sensor data fusion for telematics application. Successful telematics can be realized through the integration of navigation and spatial information. The well-determined acquisition of vehicle's position plays a vital role in application service. The development of GPS is used to provide the navigation data, but the performance is limited in areas where poor satellite visibility environment exists. Hence, multi-sensor fusion including IMU (Inertial Measurement Unit), GPS(Global Positioning System), and DMI (Distance Measurement Indicator) is required to provide the vehicle's position to service provider and driver behind the wheel. The multi-sensor fusion is implemented via algorithm based on Kalman filtering technique. Navigation accuracy can be enhanced using this filtering approach. For the verification of fusion approach, land vehicle test was performed and the results were discussed. Results showed that the horizontal position errors were suppressed around 1 meter level accuracy under simulated non-GPS availability environment. Under normal GPS environment, the horizontal position errors were under 40㎝ in curve trajectory and 27㎝ in linear trajectory, which are definitely depending on vehicular dynamics.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.462-475
• /
• 2022

Although researchers have proposed numerous techniques for speech emotion recognition, its performance remains unsatisfactory in many application scenarios. In this study, we propose a speech emotion recognition model based on a genetic algorithm (GA)-decision tree (DT) fusion of deep and acoustic features. To more comprehensively express speech emotional information, first, frame-level deep and acoustic features are extracted from a speech signal. Next, five kinds of statistic variables of these features are calculated to obtain utterance-level features. The Fisher feature selection criterion is employed to select high-performance features, removing redundant information. In the feature fusion stage, the GA is is used to adaptively search for the best feature fusion weight. Finally, using the fused feature, the proposed speech emotion recognition model based on a DT support vector machine model is realized. Experimental results on the Berlin speech emotion database and the Chinese emotion speech database indicate that the proposed model outperforms an average weight fusion method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.9
• /
• pp.863-870
• /
• 2012

This paper presents a track-to-tack information fusion algorithm using tracks of 2D and 3D radars. Before track fusion, it is needed to match the dimension of the tracks, as the tracks generated by 2D and 3D radars have different dimensions. This paper suggests how the 2D tracks are converted to the 3D tracks for track fusion. Through simulation studies, we can verify that the performance of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.3
• /
• pp.539-557
• /
• 2013

A novel multifocus image fusion algorithm based on NSCT is proposed in this paper. In order to not only attain the image focusing properties and more visual information in the fused image, but also sensitive to the human visual perception, a local multidirection variance (LEOV) fusion rule is proposed for lowpass subband coefficient. In order to introduce more visual saliency, a modified local contrast is defined. In addition, according to the feature of distribution of highpass subband coefficients, a direction vector is proposed to constrain the modified local contrast and construct the new fusion rule for highpass subband coefficients selection The NSCT is a flexible multiscale, multidirection, and shift-invariant tool for image decomposition, which can be implemented via the atrous algorithm. The proposed fusion algorithm based on NSCT not only can prevent artifacts and erroneous from introducing into the fused image, but also can eliminate 'block effect' and 'frequency aliasing' phenomenon. Experimental results show that the proposed method achieved better fusion results than wavelet-based and CT-based fusion method in contrast and clarity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1516-1539
• /
• 2022

This article shows a set of physical information fusion IoT systems that we designed for smart buildings. Its essence is a computer system that combines physical quantities in buildings with quantitative analysis and control. In the part of the Internet of Things, its mechanism is controlled by a monitoring system based on sensor networks and computer-based algorithms. Based on the design idea of the agent, we have realized human-machine interaction (HMI) and machine-machine interaction (MMI). Among them, HMI is realized through human-machine interaction, while MMI is realized through embedded computing, sensors, controllers, and execution. Device and wireless communication network. This article mainly focuses on the function of wireless sensor networks and MMI in environmental monitoring. This function plays a fundamental role in building security, environmental control, HVAC, and other smart building control systems. The article not only discusses various network applications and their implementation based on agent design but also demonstrates our collaborative information fusion strategy. This strategy can provide a stable incentive method for the system through collaborative information fusion when the sensor system is unstable in the physical measurements, thereby preventing system jitter and unstable response caused by uncertain disturbances and environmental factors. This article also gives the results of the system test. The results show that through the CPS interaction of HMI and MMI, the intelligent building IoT system can achieve comprehensive monitoring, thereby providing support and expansion for advanced automation management.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.496-498
• /
• 2023

Brain tumor segmentation problem has challenges in the tumor diversity of location, imbalance, and morphology. Attention mechanisms have recently been used widely to tackle medical segmentation problems efficiently by focusing on essential regions. In contrast, the fusion approaches enhance performance by merging mutual benefits from many models. In this study, we proposed a 3D dual fusion attention network to combine the advantages of fusion approaches and attention mechanisms by residual self-attention and local blocks. Compared to fusion approaches and related works, our proposed method has shown promising results on the BraTS 2018 dataset.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.5
• /
• pp.847-851
• /
• 2006

This paper presents a technology of information fusion between radar and electronic intelligence system. Radar can get range and direction information of targets and electronic intelligence system can get direction and electromagnetic information of targets which can be fused and identified together. We designed an information fusion unit in which information data is able to be added and compared and designed a display unit in which a fused information is totally displayed.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.3
• /
• pp.368-375
• /
• 2003

Data fusion approach is investigated to avoid suction in the left ventricular assist system (LVAS) using a nonpulsatile pump. LVAS requires careful control of pump speed to support the heart while preventing suction in the left ventricle and providing proper cardiac output at adequate perfusion pressure to the body. Since the implanted sensors are usually unreliable for long-term use, a sensorless approach is adopted to detect suction. The pump model is developed to provide the load coefficient as a necessary signal to the data fusion system without the implanted sensors. The load coefficient of the pump mimics the pulsatility property of the actual pump flow and provides more comparable information than the pump flow after suction occurs. Four signals are generated from the load coefficient as inputs to the data fusion system for suction detection and a neural fuzzy method is implemented to construct the data fusion system. The data fusion approach has a good ability to classify suction status and it can also be used to design a controller for LVAS.