• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.3
• /
• pp.229-235
• /
• 2011

To make a robust object tracking and identifying system for an intelligent robot and/or home system, heterogeneous sensor fusion between visible ray system and infrared ray system is proposed. The proposed system separates the object by combining the ROI (Region of Interest) estimated from two different images based on a heterogeneous sensor that consolidates the ordinary CCD camera and the IR (Infrared) camera. Human's body and face are detected in both images by using different algorithms, such as histogram, optical-flow, skin-color model and Haar model. Also the pose of human body is estimated from the result of body detection in IR image by using PCA algorithm along with AdaBoost algorithm. Then, the results from each detection algorithm are fused to extract the best detection result. To verify the heterogeneous sensor fusion system, few experiments were done in various environments. From the experimental results, the system seems to have good tracking and identification performance regardless of the environmental changes. The application area of the proposed system is not limited to robot or home system but the surveillance system and military system.

• Journal of IKEEE
• /
• v.19 no.2
• /
• pp.142-147
• /
• 2015

In this paper, a Kalman filter-based sensor fusion filter that measures posture by calibrating and combining information obtained from acceleration and gyro sensors was proposed. Recent advancements in sensor network technology have required sensor fusion technology. In the proposed approach, the nonlinear system model of the filter is converted to a linear system model through a Jacobian matrix operation, and the measurement value predicted via Euler integration. The proposed filter was implemented at an operating frequency of 74 MHz using a Virtex-6 FPGA Board from Xilinx Inc. Further, the accuracy and reliability of the measured posture were validated by comparing the values obtained using the implemented filters with those from existing filters.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.7-13
• /
• 2021

This paper presents an vulnerable road user (VRU) classification and tracking algorithm using vision and LiDAR sensor fusion method for urban autonomous driving. The classification and tracking for vulnerable road users such as pedestrian, bicycle, and motorcycle are essential for autonomous driving in complex urban environments. In this paper, a real-time object image detection algorithm called Yolo and object tracking algorithm from LiDAR point cloud are fused in the high level. The proposed algorithm consists of four parts. First, the object bounding boxes on the pixel coordinate, which is obtained from YOLO, are transformed into the local coordinate of subject vehicle using the homography matrix. Second, a LiDAR point cloud is clustered based on Euclidean distance and the clusters are associated using GNN. In addition, the states of clusters including position, heading angle, velocity and acceleration information are estimated using geometric model free approach (GMFA) in real-time. Finally, the each LiDAR track is matched with a vision track using angle information of transformed vision track and assigned a classification id. The proposed fusion algorithm is evaluated via real vehicle test in the urban environment.

• Journal of the Korean Vacuum Society
• /
• v.19 no.1
• /
• pp.72-80
• /
• 2010

It is very important to predict and analyze the change of voltage and current distribution of current strap, abnormal voltage distribution of transmission line and resonance phenomenon by coupling between current straps for more stable operation of ICRF system. In this study, to understand those phenomena by coupling, 8-port coupled transmission line model is completed by appling S-parameter measured in the prototype KSTAR ICRF antenna to the model. The determined self-inductance, mutual-inductance and capacitance of antenna straps are shown to be lower than that calculated from 2D approximate model due to finite length of strap. The coupled transmission line model of current strap will be utilized to the operation of ICRF system of KSTAR in the future.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.238-245
• /
• 2024

In this paper, we propose a framework for improving the performance of semantic segmentation of agricultural multispectral image using feature fusion techniques. Most of the semantic segmentation models being studied in the field of smart farms are trained on RGB images and focus on increasing the depth and complexity of the model to improve performance. In this study, we go beyond the conventional approach and optimize and design a model with multispectral and attention mechanisms. The proposed method fuses features from multiple channels collected from a UAV along with a single RGB image to increase feature extraction performance and recognize complementary features to increase the learning effect. We study the model structure to focus on feature fusion and compare its performance with other models by experimenting with favorable channels and combinations for crop images. The experimental results show that the model combining RGB and NDVI performs better than combinations with other channels.

• Journal of Korean Neurosurgical Society
• /
• v.59 no.2
• /
• pp.91-97
• /
• 2016

Objective : To investigate the biomechanical effects of a newly proposed Interspinous Process Compressor (IPC) and compare with pedicle screw fixation at surgical and adjacent levels of lumbar spine. Methods : A three dimensional finite element model of intact lumbar spine was constructed and two spinal fusion models using pedicle screw fixation system and a new type of interspinous devices, IPC, were developed. The biomechanical effects such as range of motion (ROM) and facet contact force were analyzed at surgical level (L3/4) and adjacent levels (L2/3, L4/5). In addition, the stress in adjacent intervertebral discs (D2, D4) was investigated. Results : The entire results show biomechanical parameters such as ROM, facet contact force, and stress in adjacent intervertebral discs were similar between PLIF and IPC models in all motions based on the assumption that the implants were perfectly fused with the spine. Conclusion : The newly proposed fusion device, IPC, had similar fusion effect at surgical level, and biomechanical effects at adjacent levels were also similar with those of pedicle screw fixation system. However, for clinical applications, real fusion effect between spinous process and hooks, duration of fusion, and influence on spinous process need to be investigated through clinical study.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.635-644
• /
• 2020

Object recognition, detection and instance segmentation based on DL (Deep Learning) have being used in various practices, and mainly optical images are used as training data for DL models. The major objective of this paper is object segmentation and building detection by utilizing multimodal datasets as well as optical images for training Detectron2 model that is one of the improved R-CNN (Region-based Convolutional Neural Network). For the implementation, infrared aerial images, LiDAR data, and edges from the images, and Haralick features, that are representing statistical texture information, from LiDAR (Light Detection And Ranging) data were generated. The performance of the DL models depends on not only on the amount and characteristics of the training data, but also on the fusion method especially for the multimodal data. The results of segmenting objects and detecting buildings by applying hybrid fusion - which is a mixed method of early fusion and late fusion - results in a 32.65% improvement in building detection rate compared to training by optical image only. The experiments demonstrated complementary effect of the training multimodal data having unique characteristics and fusion strategy.

• Journal of Yeungnam Medical Science
• /
• v.24 no.2
• /
• pp.262-274
• /
• 2007

Purpose : Bone morphogenetic proteins (BMPs) play an important role in the formation of cartilage and bone, as well as regulating the growth of chondroblasts and osteoblasts. In this study, we investigated whether recombinant human BMP adenoviruses are available for ex vivo gene therapy, using human fibroblasts and human bone marrow stromal cells in an animal spinal fusion model. Materials and Methods : Human fibroblasts and human bone marrow stromal cells were transduced with recombinant BMP-2 adenovirus (AdBMP-2) or recombinant BMP-7 adenovirus (AdBMP-7), referred to as AdBMP-7/BMSC, AdBMP-2/BMSC, AdBMP-7/HuFb, and AdBMP-2/HuFb. We showed that each cell secreted active BMPs by alkaline phosphatase staining. Since AdBMP-2 or AdBMP-7 tranducing cells were injected into the paravertebral muscle of athymic nude mice, at 4 weeks and 7 weeks, we confirmed that new bone formation occurred by induction of spinal fusion on radiographs and histochemical staining. Results : In the region where the AdBMP-7/BMSC was injected, new bone formation was observed in all cases and spinal fusion was induced in two of these. AdBMP-2/BMSC induced bone formation and spinal fusion occurred among one of five. However, in the region where AdBMP/HuFb was injected, neither bone formation nor spinal fusion was observed. Conclusion : The osteoinductivity of AdBMP-7 was superior to that of AdBMP-2. In addition, the human bone marrow stromal cells were more efficient than the human fibroblasts for bone formation and spinal fusion. Therefore, the results of this study suggest that AdBMP-7/BMSC would be the most useful approach to ex vivo gene therapy for an animal spinal fusion model.

• Journal of Korean Neurosurgical Society
• /
• v.46 no.4
• /
• pp.397-402
• /
• 2009

Objective : In this study, the authors assessed the ability of rat bone marrow derived mesenchymal stem cells (BMDMSCs), in the presence of a growth factor, fibroblast growth factor-4 (FGF-4) and hydroxyapatite, to act as a scaffold for posterolateral spinal fusion in a rat model. Methods : Using a rat posterolateral spine fusion model. the experimental study comprised 3 groups. Group 1 was composed of 6 animals that were implanted with 0.08 gram hydroxyapatite only. Group 2 was composed of 6 animals that were implanted with 0.08 gram hydroxyapatite containing $1{\times}10^6/60{\mu}L$ rat of BMDMSCs. Group 3 was composed of 6 animals that were implanted with 0.08 gram hydroxyapatite containing $1{\times}10^6/60{\mu}L$ of rat BMDMSCs and FGF-4 $1{\mu}G$ to induce the bony differentiation of the BMDMSCs. Rats were assessed using radiographs obtained at 4, 6, and 8 weeks postoperatively. After sacrifice, spines were explanted and assessed by manual palpation, high-resolution microcomputerized tomography, and histological analysis. Results : Radiographic, high-resolution microcomputerized tomographic, and manual palpation revealed spinal fusion in five rats (83%) in Group 2 at 8 weeks. However, in Group 1, three (60%) rats developed fusion at L4-L5 by radiography and two (40%) by manual palpation in radiographic examination. In addition, in Group 3, bone fusion was observed in only 50% of rats by manual palpation and radiographic examination at this time. Conclusion : The present study demonstrates that 0.08 gram of hydroxyapatite with $1{\times}10^6/60{\mu}L$ rat of BMDMSCs induced bone fusion. FGF4, added to differentiate primitive $1{\times}10^6/60{\mu}L$ rat of BMDMSCs did not induce fusion. Based on histologic data, FGF-4 appears to induce fibrotic change rather than differentiation to bone by $1{\times}10^6/60{\mu}L$ rat of BMDMSCs.

• International journal of advanced smart convergence
• /
• v.4 no.2
• /
• pp.20-28
• /
• 2015

In this paper, we propose an effective tracking algorithm with an appearance model based on features extracted from a video frame with posture variation and camera view point adaptation by employing the non-adaptive random projections that preserve the structure of the image feature space of objects. The existing online tracking algorithms update models with features from recent video frames and the numerous issues remain to be addressed despite on the improvement in tracking. The data-dependent adaptive appearance models often encounter the drift problems because the online algorithms does not get the required amount of data for online learning. So, we propose an effective tracking algorithm with an appearance model based on features extracted from a video frame.