• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1597-1610
• /
• 2022

At present, the main method of high-speed train chassis detection is using computer vision technology to extract keypoints from two related chassis images firstly, then matching these keypoints to find the pixel-level correspondence between these two images, finally, detection and other steps are performed. The quality and accuracy of image matching are very important for subsequent defect detection. Current traditional matching methods are difficult to meet the actual requirements for the generalization of complex scenes such as weather, illumination, and seasonal changes. Therefore, it is of great significance to study the high-speed train image matching method based on deep learning. This paper establishes a high-speed train chassis image matching dataset, including random perspective changes and optical distortion, to simulate the changes in the actual working environment of the high-speed rail system as much as possible. This work designs a convolutional neural network to intensively extract keypoints, so as to alleviate the problems of current methods. With multi-level features, on the one hand, the network restores low-level details, thereby improving the localization accuracy of keypoints, on the other hand, the network can generate robust keypoint descriptors. Detailed experiments show the huge improvement of the proposed network over traditional methods.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.633-644
• /
• 2004

In this paper, we notice that the original NTSS algorithm can be proposed as the NTSS-3 Level algorithm by the multi-resolution technique. The fast block matching algorithm affects the speed by the patten combination and this paper proposes the block matching algorithm in different levels by multi-resolution technique, quite different from the original NTSS Patten. The block matching algorithm requires the multi-candidate to reduce the occurrence of low-image quality by the local minima problem. The simulation result compared to FS shows search speed 16 times quicker, and the PSNR 0.11-0.12［dB］ gets improved Image quality compared to the original fast block matching algorithm NTSS, and the speed is improved up to 0.1 times for improved image by the search point portion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3208-3229
• /
• 2017

Rectification is an essential procedure for simplifying the disparity extraction of stereo matching algorithms by removing vertical mismatches between left and right images. To support real-time stereo matching, studies have introduced several look-up table (LUT)- and computational logic (CL)-based rectification approaches. However, to support high-resolution images, the LUT-based approach requires considerable memory resources, and the CL-based approach requires numerous hardware resources for its circuit implementation. Thus, this paper proposes a multi-level accumulation-based rectification method as a simple CL-based method and its circuit implementation. The proposed method, which includes distortion correction, reduces addition operations by 29%, and removes multiplication operations by replacing the complex matrix computations and high-degree polynomial calculations of the conventional rectification with simple multi-level accumulations. The proposed rectification circuit can rectify $1,280{\times}720$ stereo images at a frame rate of 135 fps at a clock frequency of 125 MHz. Because the circuit is fully pipelined, it continuously generates a pair of left and right rectified pixels every cycle after 13-cycle latency plus initial image buffering time. Experimental results show that the proposed method requires significantly fewer hardware resources than the conventional method while the differences between the results of the proposed and conventional full rectifications are negligible.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.179-182
• /
• 1998

Carrier recovery, the process of recoverying the carrier in receiver, removes the phase difference between VCO and the received signal. However, the conventional structure of carrier recovery cannot be applied to multi-level QAM demodulator because of the increasing decision interval and the complexity of control as the number of symbol increases. In this paper, we suggest a new carrier recovery algorithm using $\theta-matching$ algorithm for multi-level QAM demodulation to overcome this problem and analysis the performance and implement it.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.12
• /
• pp.1043-1052
• /
• 2003

In this paper, we present a fast motion estimation algorithm to reduce the computations of block matching algorithm for motion estimation in video coding. The proposed algorithm is based on Multi-level Successive Elimination Algorithm and Efficient Multi-level Successive Elimination Algorithms. The best estimate of the motion vectors can be obtained by hierarchical search point sampling and thus the proposed algorithm can decrease the number of matching evaluations that require very intensive computations. The efficiency of the proposed algorithm was verified by experimental results.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.786-791
• /
• 2005

This paper is concerned with the examination and evaluation concerning a tuning method of multivariable PID controllers based on partial model matching on frequency domain proposed by authors from practical view point. In this case, PID controller parameters are determined by minimizing the loss function defined by the difference between frequency response of ideal model transfer function and actual frequency response on several frequency points. The purpose of the paper is to examine and evaluate the performance of the method through actual experiments of MIMO liquid level experimental process control equipment.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.98-113
• /
• 2002

In this paper, we present advanced algorithms to reduce the computations of block matching algorithms for motion estimation in video coding. Advanced multi-level successive elimination algorithms(AMSEA) are based on the Multi-level successive elimination algorithm(MSEA)[1]. The first algorithm is that when we calculate the sum of absolute difference (SAD) between the sum norms of sub-blocks in MSEA, we use the partial distortion elimination technique. By using the first algorithm, we can reduce the computations of MSEA further. In the second algorithm, we calculate SAD adaptively from large value to small value according to the absolute difference values between pixels of blocks. By using the second algorithm, the partial distortion elimination in SAD calculation can occur early. So, the computations of MSEA can be reduced. In the third algorithm, we can estimate the elimination level of MSEA. Accordingly, the computations of the MSEA related to the level lower than the estimated level can be reduced. The fourth algorithm is a very fast block matching algorithm with nearly 100% motion estimation accuracy. Experimental results show that AMSEA are very efficient algorithms for the estimation of motion vectors.

• The KSFM Journal of Fluid Machinery
• /
• v.18 no.6
• /
• pp.31-36
• /
• 2015

A multi-stage turbocharger system has been constructed for HALE UAV internal combustion engine. To boost rarefied intake air up to sea level condition, the turbocharger system should consist of 3 stages including heat exchanger located after compressor outlet to drop compressed air temperature. One dimensional system analysis has been conducted by matching required power between compressor and turbine and adequate turbochargers have been searched for from commercially available models targeting for automobiles. By applying commercial automobile turbochargers to the multi-stage turbocharger system, it is expected that considerable amount of research resources will be saved.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.248-250
• /
• 2003

An automatic approach and strategy for extracting building information from aerial images using combined image analysis and interpretation techniques is described in this paper. A dense DSM is obtained by stereo image matching. Multi-band classification, DSM, texture segmentation and Normalised Difference Vegetation Index (NDVI) are used to reveal building interest areas. Then, based on the derived approximate building areas, a shape modelling algorithm based on the level set formulation of curve and surface motion has been used to precisely delineate the building boundaries. Data fusion, based on the Dempster-Shafer technique, is used to interpret simultaneously knowledge from several data sources of the same region, to find the intersection of propositions on extracted information derived from several datasets, together with their associated probabilities. A number of test areas, which include buildings with different sizes, shape and roof colour have been investigated. The tests are encouraging and demonstrate that the system is effective for building extraction, and the determination of more accurate elevations of the terrain surface.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.5
• /
• pp.54-63
• /
• 2000

We present a multi-resolution block matching algorithm (BMA) for fast motion estimation At the coarsest level, a motion vector (MV) having minimum matching error is chosen via a full search, and a MV with minimum matching error is concurrently found among the MVs of the spatially adjacent blocks Here, to examine the spatial MVs accurately, we propose an efficient method for searching full resolution MV s without MV quantization even at the coarsest level The chosen two MV s are used as the initial search centers at the middle level At the middle level, the local search is performed within much smaller search area around each search center If the method used at the coarsest level is adopted here, the local searches can be done at integer-pel accuracy A MV having minimum matching error is selected within the local search areas, and then the final level search is performed around this initial search center Since the local searches are performed at integer-pel accuracy at the middle level, the local search at the finest level does not take an effect on the overall performance So we can skip the final level search without performance degradation, thereby the search speed increases Simulation results show that in comparison with full search BMA, the proposed BMA without the final level search achieves a speed-up factor over 200 with minor PSNR degradation of 02dB at most, under a normal MPEG2 coding environment Furthermore, our scheme IS also suitable for hardware implementation due to regular data-flow.