• Journal of Korea Multimedia Society
• /
• v.15 no.3
• /
• pp.291-298
• /
• 2012

In automatic target recognition(ATR) systems, target extraction techniques are very important because ATR performance depends on segmentation result. So, this paper proposes a multi-sensor image fusion method based on adaptive weights. To incorporate the FLIR image and CCD image, we used information such as the bi-modality, distance and texture. A weight of the FLIR image is derived from the bi-modality and distance measure. For the weight of CCD image, the information that the target's texture is more uniform than the background region is used. The proposed algorithm is applied to many images and its performance is compared with the segmentation result using the single image. Experimental results show that the proposed method has the accurate extraction performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.422-424
• /
• 2021

In this paper, it leads the approach of fusing multiple RGB cameras for visual objects recognition based on deep learning with convolution neural network and 3D Light Detection and Ranging (LiDAR) to observe the environment and match into a 3D world in estimating the distance and position in a form of point cloud map. The goal of perception in multiple cameras are to extract the crucial static and dynamic objects around the autonomous vehicle, especially the blind spot which assists the AV to navigate according to the goal. Numerous cameras with object detection might tend slow-going the computer process in real-time. The computer vision convolution neural network algorithm to use for eradicating this problem use must suitable also to the capacity of the hardware. The localization of classified detected objects comes from the bases of a 3D point cloud environment. But first, the LiDAR point cloud data undergo parsing, and the used algorithm is based on the 3D Euclidean clustering method which gives an accurate on localizing the objects. We evaluated the method using our dataset that comes from VLP-16 and multiple cameras and the results show the completion of the method and multi-sensor fusion strategy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.3
• /
• pp.125-132
• /
• 2017

Even after applying an image registration, Very High Resolution (VHR) multi-temporal images acquired from different optical satellite sensors such as IKONOS, QuickBird, and Kompsat-2 show a local misalignment due to dissimilarities in sensor properties and acquisition conditions. As the local misalignment, also referred to as Registration Noise (RN), is likely to have a negative impact on multi-temporal information extraction, detecting and reducing the RN can improve the multi-temporal image processing performance. In this paper, an approach to fine registration between VHR multi-temporal images by considering local distribution of RN is proposed. Since the dominant RN mainly exists along boundaries of objects, we use edge information in high frequency regions to identify it. In order to validate the proposed approach, datasets are built from VHR multi-temporal images acquired by optical satellite sensors. Both qualitative and quantitative assessments confirm the effectiveness of the proposed RN-based fine registration approach compared to the manual registration.

• Journal of Advanced Navigation Technology
• /
• v.21 no.3
• /
• pp.251-257
• /
• 2017

Recently, hybrid positioning system combining GPS, vision sensor, and inertial sensor has drawn many attentions to estimate accurate vehicle positions. Since accurate multi-sensor fusion requires efficient time synchronization, this paper proposes an efficient method to obtain time synchronized measurements of vision sensor, inertial sensor, and OBD device based on GPS time information. In the proposed method, the time and position information is obtained by the GPS receiver, the attitude information is obtained by the inertial sensor, and the speed information is obtained by the OBD device. The obtained time, position, speed, and attitude information is converted to the color information. The color information is inserted to several corner pixels of the corresponding image frame. An experiment was performed with real measurements to evaluate the feasibility of the proposed method.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.505-508
• /
• 2005

Wavelet scheme can be applied to the various remote sensing problems: conventional multi-resolution image analysis, compression of large image sets, fusion of heterogeneous sensor image and segmentation of features. In this study, we attempted wavelet-based filtering and its analysis. Traditionally, statistical methods and adaptive filter are used to manipulate noises in the image processing procedure. While we tried to filter random noise from optical image and radar image using Discrete Wavelet Transform (DW1) and Stationary Wavelet Transform (SW1) and compared with existing methods such as median filter and adaptive filter. In result, SWT preserved boundaries and reduced noises most effectively. If appropriate thresholds are used, wavelet filtering will be applied to detect road boundaries, buildings, cars and other complex features from high-resolution imagery in an urban environment as well as noise filtering

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.3
• /
• pp.95-103
• /
• 1998

This paper deals with a problem occuring in recognition of tactile images due to the effects of imposed force at a me urement moment. Tactile image of a contact surface, used for recognition of the surface type, varies depending on the forces imposed so that a false recognition may result in. This paper fuzzifies two parameters of the contour of a tactile image with the membership function formed by considering the imposed force. Two fuzzifed paramenters are fused by the average Minkowski's dist; lnce. The proposed algorithm was implemented on the multisensor system cnmposed of an optical tact le sensor and a 6 axes forceltorque sensor. By the experiments, the proposed algorithm has shown average recognition ratio greater than 869% over all imposed force ranges and object models which is about 14% enhancement comparing to the case where only the contour information is used. The pro- ~oseda lgorithm can be used for end-effectors manipulating a deformable or fragile objects or for recognition of 3D objects by implementing on multi-fingered robot hand.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.550-558
• /
• 2013

The infrared and visible images are represented by different information due to the different wavelength of the light. The infrared image has thermal information and the visible image has texture information. Desirable results are obtained by fusing infrared and visible information. To enhance a visible image, we extract a weight map from a visible image using saturation, brightness. After that, the weight map is adjusted using thermal information in the infrared image. Finally, an enhanced image is resulted from combining an infrared image and a visible image. Our experiment results show that our proposed algorithm is working well to enhance the smoke in the original image.

• Journal of the Korea Convergence Society
• /
• v.7 no.1
• /
• pp.9-15
• /
• 2016

In this paper, we describe the design of a high speed data acquisition system(DAS) with STM32 processor based on Cortex-M4. The system is used for the sensor devices to collect raw data on production lines at factory and send them to the servo computer in real time. The system is designed for multi functions with universal asynchronous receiver and transmitter(UART), analog to digital converter(ADC), digital to analog converter(DAC), and general purpose input output(GPIO). those are well tested for various data acquisition and high speed motor control in real time.

• ETRI Journal
• /
• v.30 no.1
• /
• pp.59-67
• /
• 2008

The necessity for the precise time synchronization of measurement data from multiple sensors is widely recognized in the field of global positioning system/inertial navigation system (GPS/INS) integration. Having precise time synchronization is critical for achieving high data fusion performance. The limitations and advantages of various time synchronization scenarios and existing solutions are investigated in this paper. A criterion for evaluating synchronization accuracy requirements is derived on the basis of a comparison of the Kalman filter innovation series and the platform dynamics. An innovative time synchronization solution using a counter and two latching registers is proposed. The proposed solution has been implemented with off-the-shelf components and tested. The resolution and accuracy analysis shows that the proposed solution can achieve a time synchronization accuracy of 0.1 ms if INS can provide a hard-wired timing signal. A synchronization accuracy of 2 ms was achieved when the test system was used to synchronize a low-grade micro-electromechanical inertial measurement unit (IMU), which has only an RS-232 data output interface.