• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2749-2763
• /
• 2021

The desirable result of infrared (IR) and visible (VIS) image fusion should have textural details from VIS images and salient targets from IR images. However, detail information in the dark regions of VIS image has low contrast and blurry edges, resulting in performance degradation in image fusion. To resolve the troubles of fuzzy details in dark regions of VIS image fusion, we have proposed a method of reflectance estimation for IR and VIS image fusion. In order to maintain and enhance details in these dark regions, dark region approximation (DRA) is proposed to optimize the Retinex model. With the improved Retinex model based on DRA, quasi-Newton method is adopted to estimate the reflectance of a VIS image. The final fusion outcome is obtained by fusing the DRA-based reflectance of VIS image with IR image. Our method could simultaneously retain the low visibility details in VIS images and the high contrast targets in IR images. Experiment statistic shows that compared to some advanced approaches, the proposed method has superiority on detail preservation and visual quality.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.551-553
• /
• 1999

This paper explores the utility of a new classifier fusion approach to discrimination. Multiple classifier fusion, a popular approach in the field of pattern recognition, uses estimates of each individual classifier's local accuracy on training data sets. In this paper we investigate the effectiveness of fusion methods compared to individual algorithms, including the artificial neural network and k-nearest neighbor techniques. Moreover, we propose an efficient meta-classifier architecture based on an approximation of the posterior Bayes probabilities for learning the oracle.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.335-343
• /
• 2012

This paper presents an target tracking algorithm for fusion of radar and infrared(IR) sensor measurement data. Generally, fusion methods with Kalman filter assume that processing data obtained by radar and IR sensor are synchronized. It has much limitation to apply the fusion methods to real systems. A key point which is taken into account in the proposed algorithm is the fact that two asynchronous dissimilar data are fused by compensating the time difference of the measurements using radar's ranges and track state vectors. The proposed fusion algorithm in the paper is evaluated via a computer simulation with the existing track fusion and measurement fusion methods.

• Journal of Information Processing Systems
• /
• v.12 no.4
• /
• pp.724-740
• /
• 2016

The performance issues of screening large database compounds and multiple query compounds in virtual screening highlight a common concern in Chemoinformatics applications. This study investigates these problems by choosing group fusion as a pilot model and presents efficient parallel solutions in parallel platforms, specifically, the multi-core architecture of CPU and many-core architecture of graphical processing unit (GPU). A study of sequential group fusion and a proposed design of parallel CUDA group fusion are presented in this paper. The design involves solving two important stages of group fusion, namely, similarity search and fusion (MAX rule), while addressing embarrassingly parallel and parallel reduction models. The sequential, optimized sequential and parallel OpenMP of group fusion were implemented and evaluated. The outcome of the analysis from these three different design approaches influenced the design of parallel CUDA version in order to optimize and achieve high computation intensity. The proposed parallel CUDA performed better than sequential and parallel OpenMP in terms of both execution time and speedup. The parallel CUDA was 5-10x faster than sequential and parallel OpenMP as both similarity search and fusion MAX stages had been CUDA-optimized.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1714-1729
• /
• 2018

Change detection of remote sensing images is a profound challenge in the field of remote sensing image analysis. This paper proposes a novel change detection method for bitemporal remote sensing images based on feature fusion and fuzzy c-means (FCM). Different from the state-of-the-art methods that mainly utilize a single image feature for difference image construction, the proposed method investigates the fusion of multiple image features for the task. The subsequent problem is regarded as the difference image classification problem, where a modified fuzzy c-means approach is proposed to analyze the difference image. The proposed method has been validated on real bitemporal remote sensing data sets. Experimental results confirmed the effectiveness of the proposed method.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.423-430
• /
• 2021

Aiming Graph convolutional networks (GCNs) have achieved outstanding performances on skeleton-based action recognition. However, several problems remain in existing GCN-based methods, and the problem of low recognition rate caused by single input data information has not been effectively solved. In this article, we propose a Dual-stream fusion method that combines video data and skeleton data. The two networks respectively identify skeleton data and video data and fuse the probabilities of the two outputs to achieve the effect of information fusion. Experiments on two large dataset, Kinetics and NTU-RGBC+D Human Action Dataset, illustrate that our proposed method achieves state-of-the-art. Compared with the traditional method, the recognition accuracy is improved better.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.2
• /
• pp.45-56
• /
• 2013

The precise identification of vehicle positions, known as the vehicle localization problem, is an important requirement for building intelligent vehicle ad-hoc networks (VANETs). To solve this problem, two categories of solutions are proposed: stand-alone and data fusion approaches. Compared to stand-alone approaches, which use single information including the global positioning system (GPS) and sensor-based navigation systems with differential corrections, data fusion approaches analyze the position information of several vehicles from GPS and sensor-based navigation systems, etc. Therefore, data fusion approaches show high accuracy. With the position information on a set of vehicles in the preprocessing stage, data fusion approaches is used to estimate the precise vehicular location in the local map building stage. This paper proposes an efficient local map building scheme, which increases the accuracy of the estimated vehicle positions via V2V communications. Even under the low ratio of vehicles with communication modules on the road, the proposed local map building scheme showed high accuracy when estimating the vehicle positions. From the experimental results based on the parameters of the practical vehicular environments, the accuracy of the proposed localization system approached the single lane-level.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.2
• /
• pp.147-154
• /
• 2012

In this paper, we revise the JDL data fusion model to have an ability of distributed data fusion(DDF). Data fusion is a function that produces valuable information using data from multiple sources. After the network centric warfare concept was introduced, the data fusion was required to be expanded to DDF. We identify the data transfer and control between nodes is the core function of DDF. The previous data fusion models can not be used for DDF because they don't include that function. Therefore, we revise the previous JDL data fusion model by adding the core function of DDF and propose this new model as a model for DDF. We show that our model is adequate and useful for DDF by using several examples.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2461-2466
• /
• 2003

This paper presents a simple sensor fusion algorithm using neural network for navigation of mobile robots with obstacle avoidance and trap recovery. The multiple sensors input sensor data to the input layer of neural network activating the input nodes. The multiple sensors used include optical encoders, ultrasonic sensors, infrared sensors, a magnetic compass sensor, and GPS sensors. The proposed sensor fusion algorithm is combined with the VFH(Vector Field Histogram) algorithm for obstacle avoidance and AGPM(Adaptive Goal Perturbation Method) which sets adaptive virtual goals to escape trap situations. The experiment results show that the proposed low-level fusion algorithm is effective for real-time navigation of mobile robot.