• Smart Media Journal
• /
• v.13 no.2
• /
• pp.52-61
• /
• 2024

In the shipyard, aerial images are acquired at regular intervals using Unmanned Aerial Vehicles (UAVs) for the management of external storage yards. These images are then investigated by humans to manage the status of the storage yards. This method requires a significant amount of time and manpower especially for large areas. In this paper, we propose an automated management technology based on a semantic segmentation foundation model to address these challenges and accurately assess the status of external storage yards. In addition, as there is insufficient publicly available dataset for external storage yards, we collected a small-scale dataset for external storage yards objects and equipment. Using this dataset, we fine-tune an object detector and extract initial object candidates. They are utilized as prompts for the Segment Anything Model(SAM) to obtain precise semantic segmentation results. Furthermore, to facilitate continuous storage yards dataset collection, we propose a training data generation pipeline using SAM. Our proposed method has achieved 4.00%p higher performance compared to those of previous semantic segmentation methods on average. Specifically, our method has achieved 5.08% higher performance than that of SegFormer.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.3
• /
• pp.121-129
• /
• 2024

The rapid advancement of digital technology and the COVID-19 pandemic have significantly accelerated the growth of online commerce, highlighting the need for support mechanisms that enable small business owners to effectively respond to these market changes. In response, this paper presents a foundational technology leveraging the Online to Offline (O2O) strategy to automatically capture products displayed on retail shelves and utilize these images to create virtual stores. The essence of this research lies in precisely identifying and recognizing the location and names of displayed products, for which a single-class-targeted, lightweight model based on YOLOv8, named ESD-YOLOv8, is proposed. The detected products are identified by their names through feature-point-based technology, equipped with the capability to swiftly update the system by simply adding photos of new products. Through experiments, product name recognition demonstrated an accuracy of 74.0%, and position detection achieved a performance with an F2-Score of 92.8% using only 0.3M parameters. These results confirm that the proposed method possesses high performance and optimized efficiency.

• Journal of Broadcast Engineering
• /
• v.5 no.2
• /
• pp.281-289
• /
• 2000

While acquiring images, the relative motion between the imaging device and the object scene seriously damages the image quality. This phenomenon is called motion blur. The peak-trace approach, which is our recent previous work, identifies important parameters to characterize the point spread function (PSF) of the blur, given only the blurred image itself. With the peak-trace approach the direction of the motion blur can be extracted regardless of the noise corruption and does not need much Processing time. In this paper stochastic peak-trace approaches are introduced. The erroneous data can be selected through the ML classification, and can be made small through weighting. Therefore the distortion of the direction in the low frequency region can be prevented. Using the linear prediction method, the irregular data are prohibited from being selected as the peak point. The detection of the second peak using the proposed moving average least mean (MALM) method is used in the Identification of the motion extent. The MALM method itself includes a noise removal process, so it is possible to extract the parameters even an environment of heavy noise. In the experiment, we could efficiently restore the degraded image using the information obtained by the proposed algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2563-2567
• /
• 2011

Advances in smart sensors, embedded systems, low-power design, ad-hoc networks and MEMS have allowed the development of low-cost small sensor nodes with computation and wireless communication capabilities that can form distributed wireless sensor networks. Time information and time synchronization are fundamental building blocks in wireless sensor networks since many sensor network applications need time information for object tracking, consistent state updates, duplicate detection and temporal order delivery. Various time synchronization protocols have been proposed for sensor networks because of the characteristics of sensor networks which have limited computing power and resources. However, none of these protocols have been designed with time representation scheme in mind. Global time format such as UTC TOD (Universal Time Coordinated, Time Of Day) is very useful in sensor network applications. In this paper we propose network time protocol extension for global time presentation in wireless sensor networks.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1998.10a
• /
• pp.413-414
• /
• 1998

This paper presents a real-time Spatial Decision Support System(SDSS) for security camera image monitoring. Other SDSSs are not real-time systems, i.e., they show the images that are already transformed into data format such as virtual reality. In our system, the image is broadcasted in real-time since the purpose of the security camera needs to do it in real-time. With these real-time images, other systems do not add up anything more; the screen just shows the images from the camera. However in our system, we created a motion detection system so that the supervisor(Judge) of a sec.urity monitoring system does not have to pay attention to it constantly. In other words, we created a judge advising system for the supervisor of the security monitoring system. Most of small objects do not need the supervisor's attention since they could be birds, cats, dogs, etc. if they show up in the screen image. In this new system the system only report the unusual change to the supervisor by calculating the motion and size of objects in the screen. Thus the supervisor can be liberated from the 24-hour concentration duty; instead he/she can be only alerted when the real security threat such as a big moving object like an human intruder appears. Thus this system can be called a real-time Spatial DSS. The utility of this system is proved mathematically by using the concept of entropy. In other words, big objects like human intruders increase the entropy of the screen images significantly therefore the supervisor must be alerted. Thus by proving its utility of the system theoretically, we can claim that our new real-time SDSS is superior to others which do not use our technique.hnique.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.563-572
• /
• 2020

Tidal flats provide important indicators that inform the condition of the environment, so we need to monitor them systematically. Currently, the projects to monitor tidal flats by periodically observing the creatures in tidal flats are underway. Still, it is done in a way that people observe directly, so it is not systematic and efficient. In this paper, we propose a background modeling method for tidal flat images that can be applied to a system that automatically monitors creatures living in tidal flats using sensor network technology. The application of sensor network technology makes it difficult to collect enough images due to the limitation of transmission capacity. Therefore, in this paper, we propose a method to effectively model the background and generate foreground maps by reflecting the characteristics of tidal flat images in the situation where the number of images to be used for analysis is small. Experimental results show that the proposed method models the background of a tidal flat image easily and accurately.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2019.10a
• /
• pp.87-87
• /
• 2019

The consumption of herbal medicine and related products (herbal products) have increased in South Korea. At the same time the quality, safety, and efficacy of herbal products is being raised. Currently, the herbal products are standardized and controlled according to the requirements of the Korean Pharmacopoeia, the National Institute of Health and the Ministry of Public Health and Social Affairs. The validation of herbal products and their medicinal component is important, since many of these herbal products are composed of two or more medicinal plants. However, there are no tools to support the validation process. Interest in deep learning has exploded over the past decade, for herbal medicine using algorithms to achieve herb recognition, symptom related target prediction, and drug repositioning have been reported. In this study, individual images of four herbs (Panax ginseng C.A. Meyer, Atractylodes macrocephala Koidz, Poria cocos Wolf, Glycyrrhiza uralensis Fischer), actually sold in the market, were achieved. Certain image preprocessing steps such as noise reduction and resize were formatted. After the features are optimized, we applied GoogLeNet_Inception v4 model for herb image recognition. Experimental results show that our method achieved test accuracy of 95%. However, there are two limitations in the current study. Firstly, due to the relatively small data collection (100 images), the training loss is much lower than validation loss which possess overfitting problem. Secondly, herbal products are mostly in a mixture, the applied method cannot be reliable to detect a single herb from a mixture. Thus, further large data collection and improved object detection is needed for better classification.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.19-26
• /
• 2022

With the recent development of intelligent transportation systems, car license plate recognition systems are being used in various fields. Such systems need to guarantee real-time performance to recognize the license plate of a driving car. Also, they should keep a high recognition rate even in problematic situations such as small license plates in low-resolution and unclear image due to distortion. In this paper, we propose a real-time car license plate recognition system that improved processing speed using object detection algorithm based on anchor-free method and text recognition algorithm based on Convolutional Neural Network(CNN). In addition, we used Spatial Transformer Network to increase the recognition rate on the low resolution or distorted images. We confirm that the proposed system is faster than previously existing car license plate recognition systems and maintains a high recognition rate in a variety of environment and quality images because the proposed system's recognition rate is 93.769% and the processing speed per image is about 0.006 seconds.

• Journal of Sensor Science and Technology
• /
• v.32 no.2
• /
• pp.88-94
• /
• 2023

Recently, piezoelectric tactile sensors have garnered considerable attention in the field of texture recognition owing to their high sensitivity and high-frequency detection capability. Despite their remarkable potential, improving their mechanical flexibility to attach to complex surfaces remains challenging. In this study, we present a flexible piezoelectric sensor that can be bent to an extremely small radius of up to 2.5 mm and still maintain good electrical performance. The proposed sensor was fabricated by controlling the thickness that induces internal stress under external deformation. The fabricated piezoelectric sensor exhibited a high sensitivity of 9.3 nA/kPa ranging from 0 to 10 kPa and a wide frequency range of up to 1 kHz. To demonstrate real-time texture recognition by rubbing the surface of an object with our sensor, nine sets of fabric plates were prepared to reflect their material properties and surface roughness. To extract features of the objects from the detected sensing data, we converted the analog dataset to short-term Fourier transform images. Subsequently, texture recognition was performed using a convolutional neural network with a classification accuracy of 97%.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.81-81
• /
• 2022

Recently, many studies on big data based smart farming have been conducted. Research to quantify morphological characteristics using image data from various crops in smart farming is underway. Rice is one of the most important food crops in the world. Much research has been done to predict and model rice crop yield production. The number of productive tillers per plant is one of the important agronomic traits associated with the grain yield of rice crop. However, modeling the basic growth characteristics of rice requires accurate data measurements. The existing method of measurement by humans is not only labor intensive but also prone to human error. Therefore, conversion to digital data is necessary to obtain accurate and phenotyping quickly. In this study, we present an image-based method to predict leaf number and evaluate tiller number of individual rice crop using YOLOv5 deep learning network. We performed using various network of the YOLOv5 model and compared them to determine higher prediction accuracy. We ako performed data augmentation, a method we use to complement small datasets. Based on the number of leaves and tiller actually measured in rice crop, the number of leaves predicted by the model from the image data and the existing regression equation were used to evaluate the number of tillers using the image data.