• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.7
• /
• pp.1671-1689
• /
• 2013

The key issue of block-based multi-focus image fusion is to determine the size of the sub-block because different sizes of the sub-block will lead to different fusion effects. To solve this problem, this paper presents a novel genetic algorithm (GA) based multi-focus image fusion method, in which the block size can be automatically found. In our method, the Sum-modified-Laplacian (SML) is selected as an evaluation criterion to measure the clarity of the image sub-block, and the edge information retention is employed to calculate the fitness of each individual. Then, through the selection, crossover and mutation procedures of the GA, we can obtain the optimal solution for the sub-block, which is finally used to fuse the images. Experimental results show that the proposed method outperforms the traditional methods, including the average, gradient pyramid, discrete wavelet transform (DWT), shift invariant DWT (SIDWT) and two existing GA-based methods in terms of both the visual subjective evaluation and the objective evaluation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• pp.800-808
• /
• 2008

This paper presents a localization algorithm of the outdoor wheeled mobile robot using the sensor fusion method based on indirect Kalman filter(IKF). The wheeled mobile robot considered with in this paper is approximated to the two wheeled mobile robot. The mobile robot has the IMU and encoder sensor for inertia positioning system and GPS. Because the IMU and encoder sensor have bias errors, divergence of the estimated position from the measured data can occur when the mobile robot moves for a long time. Because of many natural and artificial conditions (i.e. atmosphere or GPS body itself), GPS has the maximum error about $10{\sim}20m$ when the mobile robot moves for a short time. Thus, the fusion algorithm of IMU, encoder sensor and GPS is needed. For the sensor fusion algorithm, we use IKF that estimates the errors of the position of the mobile robot. IKF proposed in this paper can be used other autonomous agents (i.e. UAV, UGV) because IKF in this paper use the position errors of the mobile robot. We can show the stability of the proposed sensor fusion method, using the fact that the covariance of error state of the IKF is bounded. To evaluate the performance of proposed algorithm, simulation and experimental results of IKF for the position(x-axis position, y-axis position, and yaw angle) of the outdoor wheeled mobile robot are presented.

• Journal of Information Processing Systems
• /
• v.11 no.3
• /
• pp.421-437
• /
• 2015

This paper aims to present a supervised classification algorithm based on data fusion for the segmentation of the textured images. The feature extraction method we used is based on discrete wavelet transform (DWT). In the segmentation stage, the estimated feature vector of each pixel is sent to the support vector machine (SVM) classifier for initial labeling. To obtain a more accurate segmentation result, two strategies based on information fusion were used. We first integrated decision-level fusion strategies by combining decisions made by the SVM classifier within a sliding window. In the second strategy, the fuzzy set theory and rules based on probability theory were used to combine the scores obtained by SVM over a sliding window. Finally, the performance of the proposed segmentation algorithm was demonstrated on a variety of synthetic and real images and showed that the proposed data fusion method improved the classification accuracy compared to applying a SVM classifier. The results revealed that the overall accuracies of SVM classification of textured images is 88%, while our fusion methodology obtained an accuracy of up to 96%, depending on the size of the data base.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4395-4412
• /
• 2020

The multisource image fusion has become an active topic in the last few years owing to its higher segmentation rate. To enhance the accuracy of multimodal pig-body feature segmentation, a multisource image fusion method was employed. Nevertheless, the conventional multisource image fusion methods can not extract superior contrast and abundant details of fused image. To superior segment shape feature and detect temperature feature, a new multisource image fusion method was presented and entitled as NSST-GF-IPCNN. Firstly, the multisource images were resolved into a range of multiscale and multidirectional subbands by Nonsubsampled Shearlet Transform (NSST). Then, to superior describe fine-scale texture and edge information, even-symmetrical Gabor filter and Improved Pulse Coupled Neural Network (IPCNN) were used to fuse low and high-frequency subbands, respectively. Next, the fused coefficients were reconstructed into a fusion image using inverse NSST. Finally, the shape feature was extracted using automatic threshold algorithm and optimized using morphological operation. Nevertheless, the highest temperature of pig-body was gained in view of segmentation results. Experiments revealed that the presented fusion algorithm was able to realize 2.102-4.066% higher average accuracy rate than the traditional algorithms and also enhanced efficiency.

• 전자공학회논문지 IE
• /
• v.43 no.3
• /
• pp.13-21
• /
• 2006

Ryu et al. proposed a multiple target angle tracking algorithm using the angular measurement obtained from the signal subspace estimated by the output of sensor array. Ryu's algorithm has good features that it has no data association problem and simple structure. But its performance is seriously degraded in the low signal-to-noise ratio, and it uses the angular measurement obtained from the signal subspace of sampling time, even though the signal subspace is continuously updated by the output of sensor array. For improving the tracking performance of Ryu's algorithm, a measurement fusion method is derived based on ML(Maximum Likelihood) in this paper, and it admits us to use the angular measurements obtained form the adjacent signal subspaces as well as the signal subspace of sampling time. The new target angle tracking algorithm is proposed using the derived measurement fusion method. The proposed algorithm has a better tracking performance than that of Ryu's algorithm and it sustains the good features of Ryu's algorithm.

• Korean Journal of Remote Sensing
• /
• v.26 no.5
• /
• pp.581-591
• /
• 2010

In this paper, we proposed a new wavelet-based image fusion algorithm, which has advantages in both frequency and spatial domains for signal analysis. The developed algorithm compares the ratio of SAR image signal to optical image signal and assigns the SAR image signal to the fused image if the ratio is larger than a predefined threshold value. If the ratio is smaller than the threshold value, the fused image signal is determined by a weighted sum of optical and SAR image signal. The fusion rules consider the ratio of SAR image signal to optical image signal, image gradient and local variance of each image signal. We evaluated the proposed algorithm using Ikonos and TerraSAR-X satellite images. The proposed method showed better performance than the conventional methods which take only relatively strong SAR image signals in the fused image, in terms of entropy, image clarity, spatial frequency and speckle index.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.5
• /
• pp.291-299
• /
• 2005

An obstacle avoidance algorithm for a network-based autonomous mobile robot is proposed in this paper. The obstacle avoidance algorithm is based on the VFH(Vector Field Histogram) algorithm and two delay compensation methods with the VFH algorithm are proposed for a network-based robot with distributed environmental sensors, mobile actuators, and the VFH controller. Firstly, the environmental sensor information is compensated by prospection with acquired environmental sensor information, measured network delays, and the kinematic model of the robot. The compensated environmental sensor information is used for building polar histogram with the VFH algorithm. Secondly, a sensor fusion algorithm for localization of the robot is proposed to compensate the delay of odometry sensor information and the delay of environmental sensor information. Through some simulation tests, the performance enhancement of the proposed algorithm in the viewpoint of efficient path generation and accurate goal positioning is shown here.

• The Journal of Korea Robotics Society
• /
• v.4 no.4
• /
• pp.298-304
• /
• 2009

This paper describes an algorithm that improves 3D reconstruction result using a multi-sensor fusion disparity map. We can project LRF (Laser Range Finder) 3D points onto image pixel coordinatesusing extrinsic calibration matrixes of a camera-LRF (${\Phi}$, ${\Delta}$) and a camera calibration matrix (K). The LRF disparity map can be generated by interpolating projected LRF points. In the stereo reconstruction, we can compensate invalid points caused by repeated pattern and textureless region using the LRF disparity map. The result disparity map of compensation process is the multi-sensor fusion disparity map. We can refine the multi-sensor 3D reconstruction based on stereo vision and LRF using the multi-sensor fusion disparity map. The refinement algorithm of multi-sensor based 3D reconstruction is specified in four subsections dealing with virtual LRF stereo image generation, LRF disparity map generation, multi-sensor fusion disparity map generation, and 3D reconstruction process. It has been tested by synchronized stereo image pair and LRF 3D scan data.

• 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 the Korean Society for Precision Engineering
• /
• v.20 no.11
• /
• pp.79-90
• /
• 2003

In this paper, we propose a multisensor-based navigation algorithm for a mobile robot, which is intelligently searching the goal location in unknown dynamic environments using multi-ultrasonic sensor. Instead of using “sensor fusion” method which generates the trajectory of a robot based upon the environment model and sensory data, “command fusion” method by fuzzy inference is used to govern the robot motions. The major factors for robot navigation are represented as a cost function. Using the data of the robot states and the environment, the weight value of each factor using fuzzy inference is determined for an optimal trajectory in dynamic environments. For the evaluation of the proposed algorithm, we performed simulations in PC as well as experiments with IRL-2002. The results show that the proposed algorithm is apt to identify obstacles in unknown environments to guide the robot to the goal location safely.