• Journal of Korea Game Society
• /
• v.20 no.3
• /
• pp.45-54
• /
• 2020

An automated system using a embedded board is required to generate the notation input of the offline Go game. This paper integrates shape and color information of the objects on the Go game board for light-insensitive processing and reduces the computation step. This paper combined the detection of obstacles using connected components with the computation of canny edge detection and HSV-based detection. As a result, the processing time is reduced in the embedded environment so that reliable notation can be automatically stored even in real-time play environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.421-441
• /
• 2021

Fruit detection in orchards is one of the most crucial tasks for designing the visual system of an automated harvesting robot. It is the first and foremost tool employed for tasks such as sorting, grading, harvesting, disease control, and yield estimation, etc. Efficient visual systems are crucial for designing an automated robot. However, conventional fruit detection methods always a trade-off with accuracy, real-time response, and extensibility. Therefore, an improved method is proposed based on coarse-to-fine multitask cascaded convolutional networks (MTCNN) with three aspects to enable the practical application. First, the architecture of Fruit-MTCNN was improved to increase its power to discriminate between objects and their backgrounds. Then, with a few manual labels and operations, synthetic images and labels were generated to increase the diversity and the number of image samples. Further, through the online hard example mining (OHEM) strategy during training, the detector retrained hard examples. Finally, the improved detector was tested for its performance that proved superior in predicted accuracy and retaining good performances on portability with the low time cost. Based on performance, it was concluded that the detector could be applied practically in the actual orchard environment.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.24 no.4
• /
• pp.484-491
• /
• 2014

Objectives: An image processing program for asbestos fibers analyzing the gradient components and partial linearity was developed in order to accurately segment fibers. The objectives were to increase the accuracy of counting through the formulation of the size and shape of fibers and to guarantee robust fiber detection in noisy backgrounds. Methods: We utilized samples mixed with sand and sepiolite, which has a similar structure to asbestos. Sample concentrations of 0.01%, 0.05%, 0.1%, 0.5%, 1%, 2%, and 3%(w/w) were prepared. The sand used was homogenized after being sieved to less than $180{\mu}m$. Airborne samples were collected on MCE filters by utilizing a personal pump with 2 L/min flow rate for 30 minutes. We used the NIOSH 7400 method for pre-treating and counting the fibers on the filters. The results of the NIOSH 7400 method were compared with those of the image processing program. Results: The performance of the developed algorithm, when compared with the target images acquired by PCM, showed that the detection rate was on average 88.67%. The main causes of non-detection were missing fibers with a low degree of contrast and overlapping of faint and thin fibers. Also, some duplicate countings occurred for fibers with breaks in the middle due to overlapping particles. Conclusions: An image detection algorithm that could increase the accuracy of fiber counting was developed by considering the direction of the edge to extract images of fibers. It showed comparable results to PCM analysis and could be used to count fibers through real-time tracking by modeling a branch point to graph. This algorithm can be utilized to measure the concentrations of asbestos in real-time if a suitable optical design is developed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.959-979
• /
• 2024

Rice pest identification is essential in modern agriculture for the health of rice crops. As global rice consumption rises, yields and quality must be maintained. Various methodologies were employed to identify pests, encompassing sensor-based technologies, deep learning, and remote sensing models. Visual inspection by professionals and farmers remains essential, but integrating technology such as satellites, IoT-based sensors, and drones enhances efficiency and accuracy. A computer vision system processes images to detect pests automatically. It gives real-time data for proactive and targeted pest management. With this motive in mind, this research provides a novel farmland fertility algorithm with a deep learning-based automated rice pest detection and classification (FFADL-ARPDC) technique. The FFADL-ARPDC approach classifies rice pests from rice plant images. Before processing, FFADL-ARPDC removes noise and enhances contrast using bilateral filtering (BF). Additionally, rice crop images are processed using the NASNetLarge deep learning architecture to extract image features. The FFA is used for hyperparameter tweaking to optimise the model performance of the NASNetLarge, which aids in enhancing classification performance. Using an Elman recurrent neural network (ERNN), the model accurately categorises 14 types of pests. The FFADL-ARPDC approach is thoroughly evaluated using a benchmark dataset available in the public repository. With an accuracy of 97.58, the FFADL-ARPDC model exceeds existing pest detection methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.3
• /
• pp.251-258
• /
• 2014

The purpose of the neural image analysis is to trace the velocities and the directions of moving mitochondria migrating through axons. This paper proposes an automated technique for detecting axon structure. Previously, the detection process has been carried out using a partially automated technique combined with some human intervention. In our algorithm, a consolidated image is built by taking the maximum intensity value on the all image frames at each pixel Axon detection is performed through vessel enhancement filtering followed by a peak detection procedure. In order to remove errors contained in ridge points, a filtering process is devised using a local reliability measure. Experiments have been performed using real neural image sequences and ground truth data extracted manually. It has been turned out that the proposed algorithm results in high detection rate and precision.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.20-25
• /
• 2022

This paper represents an adaptive Region of Interest (ROI) decision for real-time performance in an autonomous driving perception module. Since the whole automated driving system consists of numerous modules and subdivisions of module occur, it is necessary to consider the characteristics, complexity, and limitations of each module. Furthermore, Light Detection And Ranging (Lidar) sensors require a considerable amount of time. In view of these limitations, division of submodule is inevitable to represent high real-time performance for stable system. This paper proposes ROI to reduce the number of data respect to computation time. ROI is set by a road's design speed and the corresponding ROI is applied differently to each vehicle considering its speed. The simulation model is constructed by ROS, and overall data analysis is conducted by Matlab. The algorithm is validated using real-time driving data in urban environment, and the result shows that ROI provides low computational costs.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• pp.420-425
• /
• 2009

In this paper, image detection and recognition algorithms are studied with respect to embedded carrier system. There are many suggested techniques to detect and recognize objects. But they have the propensity to need much calculation for high hit rate. Advanced and modified method needs to study for embedded systems that low power consumption and real time response are requested. The proposed methods were implemented using Intel(R) Open Source Computer Vision Library provided by Intel Corporation. And they run and tested on embedded system using a ARM920T processor by cross-compiling. They showed 1.6sec response time and 95% hit rate and supported the automated moving carrier system smoothly.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.829-833
• /
• 1992

This paper presents the design of an automated EEG analyzing system. The design considerations including processing speed, A/D conversion, filtering, and waveforms detection, are overviewed with the description of the associated EEG characteristics. The architecture of the currently implemented system consists of a p-controller based front-end signal processing unit and a host computer system. The data acquisition procedures are described along with a couple of illustrations of the acquired EEG/EOG signal.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.383-387
• /
• 2007

The improved accuracy of the Land Cover/Land Use Map constructed using Hyperspectal Satellite Image and the possibility of real time classification of Land Use using optimal Band Selective Factor enable the change detection from automatic classification using the existed Land Cover/Land Use Map and the newly acquired Hyperspectral Satellite Image. In this study, the effective analysis techniques for automatic generation of training regions, automatic classification and automatic change detection are proposed to minimize the expert's interpretation for automatic update of the Land Cover/Land Use Map. The proposed algorithms performed successfully the automatic Land Cover/Land Use Map construction, automatic change detection and automatic update on the image which contained the changed region. It would increase applicability in actual services. Also, it would be expected to present the effective methods of constructing national land monitoring system.

• Annual Conference of KIPS
• /
• 2007.05a
• /
• pp.1093-1095
• /
• 2007

As the networking and data communication technology is making progress, there has been an augmented concern about the security. Intrusion Detection and Prevention Systems have long being providing a reliable layer in the field of Network Security. Intrusion Detection System works on analyzing the traffic and finding a known intrusion or attack pattern in that traffic. But as the new technology provides betterment for the world of the Internet; it also provides new and efficient ways for hacker to intrude in the system. Hence, these patterns on which IDS & IPS work need to be updated. For detecting the power and knowledge of attackers we sometimes make use of Honey-pots. In this paper, we propose a Honey-pot architecture that automatically updates the Intrusion's Signature Knowledge Base of the IDS in a Network.