• Journal of KIISE
• /
• v.44 no.9
• /
• pp.932-945
• /
• 2017

In this paper, a new hardware and software architecture for a stereo vision processing system including rectification, disparity estimation, and visualization was developed. The developed method, named LArge scale stereo matching method using Support Point Interpolation (LASPI), shows excellence in real-time processing for obtaining dense disparity maps from high quality image regions that contain high density support points. In the real-time processing of high definition (HD) images, LASPI does not degrade the quality level of disparity maps compared to existing stereo-matching methods such as Efficient LArge-scale Stereo matching (ELAS). LASPI has been designed to meet a high frame-rate, accurate distance resolution performance, and a low resource usage even in a limited resource environment. These characteristics enable LASPI to be deployed to safety-critical applications such as an obstacle recognition system and distance detection system for autonomous vehicles. A Field Programmable Gate Array (FPGA) for the LASPI algorithm has been implemented in order to support parallel processing and 4-stage pipelining. From various experiments, it was verified that the developed FPGA system (Xilinx Virtex-7 FPGA, 148.5MHz Clock) is capable of processing 30 HD ($1280{\times}720pixels$) frames per second in real-time while it generates disparity maps that are applicable to real vehicles.

• Journal of Life Science
• /
• v.30 no.10
• /
• pp.844-850
• /
• 2020

Disaster-related extreme weather is rapidly increasing due to climate change. In Korea, typhoons accompanied by rainfall usually approach in August and September, causing great damage. The purpose of this study is to find a gene that regulates the heading date of rice in order to avoid loss of harvest from climate change and typhoons. Cheongcheong/Nagdong doubled haploid (CNDH) was used as the plant material to investigate the location of heading-related genes using QTL and sequence analysis by cloning the gene. In the distribution chart, the heading dates, culm lengths, panicle lengths, numbers of panicles, and 1,000-grain weights all have normal distributions. QTL analysis found 13 contigs on chromosome 8. One QTL, named qHd8, was detected on chromosome 8. The range at qHd8 was approximately 7.7 cM, with RM72 and RM404 markers near the peak. There were 13 contigs and 1 ORF. Protein sequence analysis showed that rice was similar to Os08g0341700, AtSFH13, and AtSFH7 proteins. Os08g0341700, which is involved in signal transduction, is similar to phosphatidylinositol transfer-like protein II, and complete information is not available, but it is believed to play a role in the phosphatidylinositol-specific signaling pathway related to Sec14P.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.388-396
• /
• 2017

Since there are many variables such as various poses, illuminations and occlusions in a face detection problem, a high performance detection system is required. Although CNN is excellent in image classification, CNN operatioin requires high-performance hardware resources. But low cost low power environments are essential for small and mobile systems. So in this paper, the CPU-FPGA integrated system is designed based on 3-stage cascade CNN architecture using small size FPGA. Adaptive Region of Interest (ROI) is applied to reduce the number of CNN operations using face information of the previous frame. We use a Field Programmable Gate Array(FPGA) to accelerate the CNN computations. The accelerator reads multiple featuremap at once on the FPGA and performs a Multiply-Accumulate (MAC) operation in parallel for convolution operation. The system is implemented on Altera Cyclone V FPGA in which ARM Cortex A-9 and on-chip SRAM are embedded. The system runs at 30FPS with HD resolution input images. The CPU-FPGA integrated system showed 8.5 times of the power efficiency compared to systems using CPU only.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.9
• /
• pp.6227-6235
• /
• 2015

The HUD has recently been downsized due to the development of micro display and LED technology as a see through information display device, gradually expands the application areas. In this paper, using a DLP micro display device designed a compact head-up display(HUD) optical system for biocular observation of the image exhibition area 5 inches. It was analyzed for each design element of the optical system in order to design a compacted HUD. DLP, projection optical system and concave image combiner were discussed the design approach and the characteristics. Through a connection structure analysis of each optical system, detailed design specifications were set up and designed the optical system in detail. Put a folded configuration in the form of a white diffuse reflector between the projection lens and concave image combiner was designed to be independent, respectively. Distance of the projected image is adjustable up to approximately 2m ~ infinity and observation distance is 1m. Resolution could be recognized by 1 ~ 2pixels in HD($1,280{\times}720pixels$) class, various characters and symbols could be read. In addition, color navigation map, daytime video camera and thermal imaging cameras can be displayed.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.383-390
• /
• 2020

Car-mounted MMS (Mobile Mapping System) is the most effective tool for mapping of high definition road maps(HD Map). The MMS is composed of various sensor combinations, and the manufacturing methods and processing software are different for each manufacturer, performance cannot be predicted only by the specifications of the parts. Therefore, it is necessary to judge whether each equipment is suitable for mapping through performance evaluation, and facilities for periodic performance evaluation. In this paper, we explained the MMS performance evaluation facilities built at the SOC Evaluation Research Center of Korea Institute of Civil Engineering and Building Technology and analyzed the conditions that the evaluation facilities should have through a literature survey and field tests.

• Korean Journal of Agricultural Science
• /
• v.47 no.2
• /
• pp.205-217
• /
• 2020

In this study, a deep learning-based tillage boundary detection method for autonomous tillage by a tractor was developed, which consisted of image cropping, object classification, area segmentation, and boundary detection methods. Full HD (1920 × 1080) images were obtained using a RGB camera installed on the hood of a tractor and were cropped to 112 × 112 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the path boundary was detected using a probability map, which was generated by the integration of softmax outputs. The results show that the F1-score of the classification was approximately 0.91, and it had a similar performance as the deep learning-based classification task in the agriculture field. The path boundary was determined with edge detection and the Hough transform, and it was compared to the actual path boundary. The average lateral error was approximately 11.4 cm, and the average angle error was approximately 8.9°. The proposed technique can perform as well as other approaches; however, it only needs low cost memory to execute the process unlike other deep learning-based approaches. It is possible that an autonomous farm robot can be easily developed with this proposed technique using a simple hardware configuration.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.11C
• /
• pp.940-947
• /
• 2010

Motion Compensated Frame Interpolation(MCFI) has been used to reduce motion jerkiness for dynamic scenes and motion blurriness for LCD-panel display as post processing for high quality display. However, MCFI that directly uses the motion information often suffers from annoying artifacts such as blockiness, ghost effects, and deformed structures. So in this paper, we propose a novel edge-based adaptively weighted vector median filter as post-processing. At first, the proposed method generates an edge direction map through a sobel mask and a weighted maximum frequent filter. And then, outlier MVs are removed by average of angle difference and replaced by a median MV of $3{\times}3$ window. Finally, weighted vector median filter adjusts the weighting values based on edge direction derived from spatial coherence between the edge direction continuity and motion vector. The results show that the performance of PSNR and SSIM are higher up to 0.5 ~ 1 dB and 0.4 ~ 0.8 %, respectively.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.6
• /
• pp.1395-1402
• /
• 2024

This paper proposes an autonomous driving pesticide robot system capable of performing pest control tasks autonomously in orchard and greenhouse environments. The proposed system is designed to perform efficient pest control operations in both indoor and outdoor settings by integrating a replaceable 50-liter pesticide container with autonomous driving technology. To overcome the limitations of existing agricultural autonomous robots in navigating indoor and outdoor environments, a 3D global mapping technology combining LiDAR, INS, and GNSS, along with an autonomous tracking algorithm, was implemented. The robot's operational status is stably controlled via a real-time monitoring system based on 5G, LTE, and WiFi, and it provides accurate detection and avoidance of dynamic obstacles using an AI-based object recognition algorithm. The proposed system is expected to improve the efficiency of agricultural tasks, address labor shortages by replacing human work in hazardous environments, and further promote agricultural automation.

• Journal of Life Science
• /
• v.30 no.4
• /
• pp.331-342
• /
• 2020

The suppression of neuroinflammatory responses in microglial cells can be considered a key target for improving the progression of neurodegenerative diseases such as Alzheimer's disease (AD), Parkinson's disease (PD), and Huntington's disease (HD). Asparagus cochinchinensis has traditionally been used as a medicine to treat fever, cough, kidney disease, breast cancer, inflammatory diseases, and brain diseases. In this study, we investigated the neuroprotective mechanism of an aqueous extract from A. cochinchinensis root (AEAC), particularly its anti-inflammatory effects on lipopolysaccharide (LPS)-activated BV-2 microglial cells. BV-2 cells were treated with four different concentrations of AEAC. No significant toxicity was detected in BV-2 cells treated with AEAC. Nitric oxide (NO), cyclooxygenase-2 (COX-2) mRNA, and inducible nitric oxide synthase (iNOS) mRNA levels were 21% lower in the AEAC+LPS group than in the Vehicle+LPS group. Lower proinflammatory (TNF-α and IL-1β) and anti-inflammatory cytokine (IL-6 and IL-10) levels were also detected in the AEAC+LPS group than in the Vehicle+LPS group, albeit at varying rates. Moreover, the phosphorylation of mitogen-activated protein kinase (MAPK) members after LPS treatment was significantly recovered in the AEAC-pretreated group compared to the Vehicle+LPS group, enhancement of the phosphorylation of mitogen-activated protein kinase (MAPK) members after LPS treatment was significantly recovered in the AEAC-pretreated group, while cell cycle arrest at the G2/M phase caused by LPS treatment was less severe in the AEAC+LPS group. The increase in reactive oxygen species (ROS) generation induced by LPS treatment was also lower in the AEAC-pretreated group than in the Vehicle+LPS group. This is the first study to show that AEAC exerts anti-neuroinflammatory activity against LPS stimulation by regulating the MAPK signaling pathway, the cell cycle, and ROS production.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.363-373
• /
• 2012

This paper proposes a method to generate a depth image at an arbitrary intermediate view-point, which is targeting a video service for free-view, auto-stereoscopy, holography, etc. It assumes that the leftmost and the rightmost depth images are given and they both have been camera-calibrated and image-rectified. This method calculates and uses a disparity increment per depth value. In this paper, it is obtained by stereo matching for the given two depth image by considering more general cases. The disparity increment is used to find the location in the intermediate view-point depth image (IVPD) for each depth in the given images. Thus, this paper finds two IVPDs, from left image and from right image. Noises are removed and holes are filled in each IVPDs and the two results are combined to get the final IVPD. The proposed method was implemented and applied to several test sequences. The results revealed that the quality of the generated IVPD corresponds to 33.84dB of PSNR in average and it takes about 1 second to generate a HD IVPD. We evaluate that this image quality is quite good by considering the low correspondency among the left images, intermediate images, and the right images in the test sequences. If the execution speed is improved, the proposed method can be a very useful method to generate an IVPD at an arbitrary view-point, we believe.