• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.83-93
• /
• 2013

Recently, the SURF algorithm, which is conjugated for object tracking system as part of many computer vision applications, is a well-known scale- and rotation-invariant feature detection algorithm. The SURF, due to its high computational complexity, there is essential to develop a hardware accelerator in order to be used on an IP in embedded environment. However, the SURF requires a huge local memory, causing many problems that increase the chip size and decrease the value of IP in ASIC and SoC system design. In this paper, we proposed a way to design a SURF algorithm in hardware with greatly reduced local memory by partitioning the algorithms into several Sub-IPs using external memory and a DMA. To justify validity of the proposed method, we developed an example of simplified object tracking algorithm. The execution speed of the hardware IP was about 31 frame/sec, the logic size was about 74Kgate in the 30nm technology with 81Kbytes local memory in the embedded system platform consisting of ARM Cortex-M0 processor, AMBA bus(AHB-lite and APB), DMA and a SDRAM controller. Hence, it can be used to the hardware IP of SoC Chip. If the image processing algorithm akin to SURF is applied to the method proposed in this paper, it is expected that it can implement an efficient hardware design for target application.

• Journal of Practical Engineering Education
• /
• v.15 no.1
• /
• pp.1-11
• /
• 2023

The purpose of this study is to develop and validate a tool that measures the satisfaction of virtual training learners' use of virtual training content. To this end, 491 copies of the basic questions derived from the satisfaction questions used by the K University Online Lifelong Education Center were used for the final analysis by conducting an online survey of learners who accessed STEP, the K University Online Lifelong Education Center portal. The 491 copies of data finally used were analyzed by methods such as basic question analysis, exploratory factor analysis, reliability analysis, and confirmatory factor analysis. First, in the basic question analysis, there were no questions that exceeded the acceptance criteria of an average of 4 points or more, skewness ±2, and kurtosis ±4. Second, the correlation coefficient for each sub-factor of virtual training content satisfaction derived after exploratory factor analysis was good as r=.682 to .822 (p<.01). The reliability coefficient for each sub-factor is content .849, content utilization .922, System and Operations Support .841, Intention to Continue Utilization .920, the overall reliability is. It was very high at .956 Fifth, as a result of confirmatory factor analysis, the compositional conceptual diagram is. It was .842 to .926, higher than the recommended standard of .7, and the average variance extraction degree. It appears to be .640 to .796, higher than the recommended standard of .5, which can be seen as representative of each constituent concept. As a result of verifying the validity of virtual training learners' content satisfaction recruitment, four factor models were derived: content substance, content utilization, system and operation support, and intention to continue use. This study is meaningful in that it empirically developed a tool to measure content satisfaction of virtual training learners and provided a reference frame and criteria.

• Journal of Practical Engineering Education
• /
• v.14 no.3
• /
• pp.593-600
• /
• 2022

Various sensors such as lidar, radar, and camera are fused and used in autonomous vehicles. Rider and radar sensors are difficult to popularize because they are expensive equipment. In order to popularize autonomous vehicles, research that can replace expensive equipment is continuously being conducted. In this paper, we use a single camera that is inexpensive and can be easily mounted. We propose a method for detecting the wheels and adjacent lanes of a front-side vehicle of a driving vehicle and estimating distances. Our proposed method detects lanes and wheels from frame images after frame extraction via input images. In addition, the distance is measured and compared with the actual distance measured in the actual road environment. The distance could be calculated relatively accurately within the error range of ± 3 cm. Through this, it is expected that the camera can be used as an alternative means when the cost of autonomous vehicles is reduced or when the lidar or radar sensor fails.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.2 s.308
• /
• pp.21-32
• /
• 2006

The license plate recognition (LPR) unit consists of the following core components: plate region segmentation, individual character extraction, and character recognition. Out of the above three components, accuracy in the performance of plate region segmentation determines the overall recognition rate of the LPR unit. This paper proposes an algorithm for segmenting the license plate region on the front or rear of a vehicle in a fast and accurate manner. In the case of the proposed algorithm images are captured on the spot where unmanned monitoring of illegal parking and stowage is performed with a variety of roadway environments taken into account. As a means of enhancing the segmentation performance of the on-the-spot-captured images of license plate regions, the proposed algorithm uses a mathematical model for license plate colors to convert color images into digital data. In addition, this algorithm uses Gaussian smoothing and double threshold to eliminate image noises, one-pass boundary tracing to do region labeling, and MBR to determine license plate region candidates and extract individual characters from the determined license plate region candidates, thereby segmenting the license plate region on the front or rear of a vehicle through a verification process. This study contributed to addressing the inability of conventional techniques to segment the license plate region on the front or rear of a vehicle where the frame of the license plate is damaged, through processing images in a real-time manner, thereby allowing for the practical application of the proposed algorithm.

• Journal of Broadcast Engineering
• /
• v.13 no.2
• /
• pp.222-235
• /
• 2008

Recently, as growing of high definition media services like HDTV and IPTV, fast moving picture manipulation techniques need to meet what those services require. Especially, a fast reduced-size image extracting method is required in the areas of video indexing and video summary Conventional DC image extracting methods, however, can't be applied to H.264/AVC streams since a spatial domain prediction scheme is adopted in H.264/AVC intra mode. In this paper, we propose a theoretical method for extracting a thumbnail image from an H.264/AVC intra frame in the frequency domain. Furthermore, the proposed scheme can extract the thumbnail very fast since all operations are applied to transform coefficients directly, after a general equation for the thumbnail extraction in nine H.264/AVC intra prediction modes is introduced, an LUT(Look Up Table) for each mode is designed. Through the implementation and performance evaluation, while the subject quality difference between the output of our scheme and a conventional output is negligible, the former can extract the thumbnail faster then the latter by up to 63%.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.3
• /
• pp.74-82
• /
• 2024

In this study, feature point detection and displacement measurement performance depending on feature extraction algorithms were compared and analyzed according to environmental changes and target types in the feature point-based displacement measurement algorithm. A three-story frame structure was designed for performance evaluation, and the displacement response of the structure was digitized into FHD (1920×1080) resolution. For performance analysis, the initial measurement distance was set to 10m, and increased up to 40m with an increment of 10m. During the experiments, illuminance was fixed to 450lux or 120lux. The artificial and natural targets mounted on the structure were set as regions of interest and used for feature point detection. Various feature detection algorithms were implemented for performance comparisons. As a result of the feature point detection performance analysis, the Shi-Tomasi corner and KAZE algorithm were found that they were robust to the target type, illuminance change, and increase in measurement distance. The displacement measurement accuracy using those two algorithms was also the highest. However, when using natural targets, the displacement measurement accuracy is lower than that of artificial targets. This indicated the limitation in extracting feature points as the resolution of the natural target decreased as the measurement distance increased.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.3
• /
• pp.91-101
• /
• 2011

Internet is becoming increasingly popular due to the rapid development of information and communication technology. There has been a convenient social activities such as the mutual exchange of information, e-commerce, internet banking, etc. through cyberspace on a computer. However, by using the convenience of the internet, the personal IDs(identity card, driving license, passport, student ID, etc.) represented by the electronic media are exposed on the internet frequently. Therefore, this study propose a feature extraction method to analyze the characteristics of image files containing personal information and a image retrieval method to find the images using the extracted features. The proposed method selects the feature information from color, texture, and shape of the images, and the images as searched by similarity analysis between feature information. The result which it experiments from the image which it acquires from the web-based image DB and correct image retrieval rate is 89%, the computing time per frame is 0.17 seconds. The proposed method can be efficiently apply a system to search the image files containing personal information and to determine the criteria of exposure of personal information.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.12
• /
• pp.8649-8653
• /
• 2015

A number of video indexing and retrieval algorithms have been proposed to manage large video databases efficiently. The video similarity measure is one of most important technical factor for video content management system. In this paper, we propose the luminance characteristics model to measure the video similarity efficiently. Most algorithms for video indexing have been commonly used histograms, edges, or motion features, whereas in this paper, the proposed algorithm is employed an efficient similarity measure using the luminance projection. To index the video sequences effectively and to reduce the computational complexity, we calculate video similarity using the key frames extracted by the cumulative measure, and compare the set of key frames using the modified Hausdorff distance. Experimental results show that the proposed luminance projection model yields the remarkable improved accuracy and performance than the conventional algorithm such as the histogram comparison method, with the low computational complexity.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.20 no.4
• /
• pp.333-341
• /
• 2008

A remote sensing technique to identify trajectories of breaking waves in the surf zone using oblique digital nearshore videos is proposed. The noise arising from white foam induced by wave breaking has hindered accurate remote sensing of wave properties in the surf zone. For this reason, this paper focuses on image processing to remove the noise and wave trajectory identification essential for wave property estimation. The nearshore video imagery sampled at 3 Hz are used, covering length scale(100 m). Original image sequences are processed through image frame differencing and directional low-pass image filtering to remove the noise characterized by high frequencies in the video imagery. The extraction of individual wave crest features is conducted using a Radon transform-based line detection algorithm in the processed cross-shore image timestacks having a two-dimensional space-time domain. The number of valid wave crest trajectories identified corresponds to about 2/3 of waves recorded by the in-situ sensors.