• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.55-61
• /
• 2019

In this paper, if images are acquired in all-time situations through various sensors (EO/IR, SAR, GMTI, LiDAR) used for defense purposes, the images can be analyzed and expressed in augmented reality(AR). Various algorithms are used to process images with augmented reality, and depending on the situation, it is necessary to decide which algorithms to select and use. Through the performance comparison (error rate, processing time, accuracy) of SIFT, SURF, ORB, and BRISK, the representative augmented reality algorithm, it is analyzed and proposed which augmented reality algorithm is effective to use under various situations in the defense field.

• Agricultural and Biosystems Engineering
• /
• v.3 no.1
• /
• pp.18-28
• /
• 2002

Neural network based models were developed and evaluated for predicting corn yield from aerial images based on 1998 and 1994 image data. The model used images in multi-spectral bands such as R, G, B, and IR (Red, Green, Blue and Infrared). The inputs to the neural network consisted of mean and standard deviation of multispectral bands of the aerial images. Performances of several neural network architectures using back-propagation with momentum were compared. The maximum yield prediction accuracy obtained was 97.81%. The BPNN model prediction accuracy could be enhanced by using more number of observations to the model, other data transformation techniques, or by performing optical calibration of the aerial image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.252-255
• /
• 2010

In this thesis, it suggests large scale interactive display system which is able to various touch interaction and bases on infrared LED BAR and using 3D. Interaction layer formed on space from screen which is able to feel 3D using suggested IR LED BAR. It gets the image in real time what is composed in interaction section using infrared camera with band pass filter. The image finds touch interaction coordinate through image processing module and saves as packet. It send packet to server through network data communication. It analyze packet by metaphor analysis module and save as metaphor event and send it to contents. On contents, it practices to metaphor event result in real time so it makes use touch interaction in stereopsis. According to this process, it does not need touch the screen at firsthand but it is possible system and touch interaction so touch interaction is possible while use 3D.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.901-906
• /
• 2007

Algorithms of path planning and obstacle avoidance are essential to autonomous mobile robots that are working in unknown environments in the real time. This paper presents a new navigation algorithm for an autonomous mobile robot with vision and IR sensors using fuzzy rules. Temporary targets are set up by distance variation method and then the algorithms of trajectory planning and obstacle avoidance are designed using fuzzy rules. In this approach, several digital image processing technique is employed to detect edge of obstacles and the distances between the mobile robot and the obstacles are measured. An autonomous mobile robot with single vision and IR sensors is built up for experiments. We also show that the autonomous mobile robot with the proposed algorithm is navigating very well in complex unknown environments.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.493-505
• /
• 2023

Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.122-127
• /
• 2016

This paper propose implementation method of SoC system for efficient depth image segmentation. SoC systems are combined platform in the form of the Software and Hardware IP. In order to perform effectively, the user to determine the operation of the configuration of each part. In this paper, we implemented a segmentation of depth images taken by the infrared sensor at APU of SoC system. The proposed method efficiently implements high performance and low power in SoC system. Proposed method that using software parts of SoC system is capable to use at several depth image processing systems.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.4
• /
• pp.138-144
• /
• 2007

This paper introduces the design techniques of an IR module using the 2-D array un-cooled type infrared detector which is applied to the individual combat weapon. Considering the size and weight of the hand carried weapon system, we used a very small-sized detector and applied an adaptive temperature control algorithm so that the operation consumed with low power can be possible. We applied the AR(Auto Regressive) filter to improve the signal-to-noise ratio in a thermal image processing step. We also applied the plateau equalization and boundary enhancement techniques to improve the visibility for human visual system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1464-1480
• /
• 2019

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

• Journal of Korea Multimedia Society
• /
• v.8 no.1
• /
• pp.46-55
• /
• 2005

In this paper, we realize the panoramic infrared warning system to detect the small threaten object and propose the infrared image enhancement method to improve the warning ability of this system. This system composes of the sense head unit, the signal processing unit, and so on. In the proposed system, the sense head unit acquires the panoramic IR image with 360 degree field of view(FOV) by rotating the thermal sensor. The signal processing unit divides panoramic image into four sub-images with 90 degree FOV and computes the adaptive plateau value by using statistical characteristics of each subimage. Then the histogram equalization is performed for each subimage by using the adaptive plateau value. We realize the signal Processing unit by using the DSP and FPGA to perform the proposed method in real time. Experimental results show that the proposed method has better discrimination and lower false alarm rate than the conventional methods in this warning system.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.3-12
• /
• 2022

Image deblurring aims to remove image blur, which can be generated while shooting the pictures by the movement of objects, camera shake, blurring of focus, and so forth. With the rise in popularity of smartphones, it is common to carry portable digital cameras daily, so image deblurring techniques have become more significant recently. Originally, image deblurring techniques have been studied using traditional optimization techniques. Then with the recent attention on deep learning, deblurring methods based on convolutional neural networks have been actively proposed. However, most of them have been developed while focusing on better performance. Therefore, it is not easy to use in real situations due to the speed of their algorithms. To tackle this problem, we propose a novel deep learning-based deblurring algorithm that can be operated in real-time on HD resolution. In addition, we improved the training and inference process and could increase the performance of our model without any significant effect on the speed and the speed without any significant effect on the performance. As a result, our algorithm achieves real-time performance by processing 33.74 frames per second at 1280×720 resolution. Furthermore, it shows excellent performance compared to its speed with a PSNR of 29.78 and SSIM of 0.9287 with the GoPro dataset.