• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.4
• /
• pp.231-238
• /
• 2017

Detecting small infrared targets from the low-SCR images at a long distance is very hard. The previous Local Contrast Method (LCM) algorithm based on the human visual system shows a superior performance of detecting small targets by a background suppression technique through local contrast measure. However, its slow processing speed due to the heavy multi-scale processing overhead is not suitable to a variety of real-time applications. This paper presents a lightweight real-time small target detection algorithm, called by the Improved Selective Local Contrast Method (ISLCM), to reduce the scale-invariant computational overhead. The proposed ISLCM applies the improved local contrast measure to the predicted selective region so that it may have a comparable detection performance as the previous LCM while guaranteeing low scale-invariant computational load by exploiting both adaptive scale estimation and small target feature feasibility. Experimental results show that the proposed algorithm can reduce its computational overhead considerably while maintaining its detection performance compared with the previous LCM.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.8
• /
• pp.839-844
• /
• 2009

In this paper, a real-time eye tracking method using fast face detection is proposed. Most of the current eye tracking systems have operational limitations due to sensors, complicated backgrounds, and uneven lighting condition. It also suffers from slow response time which is not proper for a real-time application. The tracking performance is low under complicated background and uneven lighting condition. The proposed algorithm detects face region from acquired image using elliptic Hough transform followed by eye detection within the detected face region using Haar-like features. In order to reduce the computation time in tracking eyes, the algorithm predicts next frame search region from the information obtained in the current frame. Experiments through simulation show good performance of the proposed method under various environments.

• Journal of Microbiology and Biotechnology
• /
• v.20 no.3
• /
• pp.569-573
• /
• 2010

A quantitative detection method for Salmonella in seafood was developed using a SYBR Green-based real-time PCR assay. The assay was developed using pure Salmonella DNA at different dilution levels [i.e., 1,000 to 2 genome equivalents (GE)]. The sensitivity of the real-time assay for Salmonella in seeded seafood samples was determined, and the minimum detection level was 20 CFU/g, whereas a detection level of 2 CFU/ml was obtained for pure culture in water with an efficiency of ${\geq}85%$. The real-time assay was evaluated in repeated experiments with seeded seafood samples and the regression coefficient ($R^2$) values were calculated. The performance of the real-time assay was further assessed with naturally contaminated seafood samples, where 4 out of 9 seafood samples tested positive for Salmonella and harbored cells <100 GE/g, which were not detected by direct plating on Salmonella Chromagar media. Thus, the method developed here will be useful for the rapid quantification of Salmonella in seafood, as the assay can be completed within 2-3 h. In addition, with the ability to detect a low number of Salmonella cells in seafood, this proposed method can be used to generate quantitative data on Salmonella in seafood, facilitating the implementation of control measures for Salmonella contamination in seafood at harvest and post-harvest levels.

• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.22-29
• /
• 2022

In this paper, for the purpose of designing an real-time unmanned monitoring system, the YOLOv5s (small) object detection model was applied on the NVIDIA TX2^TM AI (Artificial Intelligence) edge computing platform in order to design the fundamental function of an unmanned monitoring system that can detect objects in real time. YOLOv5s was applied to the our real-time unmanned monitoring system based on the performance evaluation of object detection algorithms (for example, R-CNN, SSD, RetinaNet, and YOLOv5). In addition, the performance of the four YOLOv5 models (small, medium, large, and xlarge) was compared and evaluated. Furthermore, based on these results, the YOLOv5s model suitable for the design purpose of this paper was ported to the NVIDIA TX2^TM AI edge computing system and it was confirmed that it operates normally. The real-time unmanned monitoring system designed as a result of the research can be applied to various application fields such as an security or monitoring system. Future research is to apply NMS (Non-Maximum Suppression) modification, model reconstruction, and parallel processing programming techniques using CUDA (Compute Unified Device Architecture) for the improvement of object detection speed and performance.

• ETRI Journal
• /
• v.37 no.3
• /
• pp.551-561
• /
• 2015

We propose a novel multiple-object tracking algorithm for real-time intelligent video surveillance. We adopt particle filtering as our tracking framework. Background modeling and subtraction are used to generate a region of interest. A two-step pedestrian detection is employed to reduce the computation time of the algorithm, and an iterative particle repropagation method is proposed to enhance its tracking accuracy. A matching score for greedy data association is proposed to assign the detection results of the two-step pedestrian detector to trackers. Various experimental results demonstrate that the proposed algorithm tracks multiple objects accurately and precisely in real time.

• Fisheries and Aquatic Sciences
• /
• v.11 no.4
• /
• pp.205-208
• /
• 2008

The mixotrophic dinoflagellate Cochlodinium polykrikoides was reported to be linked to major fish kills in Korea and Japan since the 1990s. Rapid and sensitive detection of microalgae has been problematic because morphological identification of dinoflagellates requires light microscopic and scanning electron microscopic observations that are time consuming and laborious compared to real-time PCR. To address this issue, a real-time PCR probe targeting the ITS2 rRNA gene was used for rapid detection and quantification of C. polykrikoides. PCR inhibitors in water column samples were removed by dilution of template DNA for elimination of false-negative reactions. A strong association between cell quantification using real-time PCR and microscopic counts suggests that the real-time PCR assay is an alternative method for cell estimation of C. polykrikoides in environment samples.

• Journal of Food Hygiene and Safety
• /
• v.34 no.2
• /
• pp.135-139
• /
• 2019

The objective of this research was to compare loop-mediated isothermal amplification (LAMP) with real-time polymerase chain reaction (PCR) for the rapid detection of pathogens in foods. In this study, the limits of detection (LODs) for Salmonella Typhimurium, Listeria monocytogenes, and Cronobacter sakazakii were evaluated in various foods. Among 11 samples tested for S. Typhimurium, LAMP and real-time PCR had the same LODs in beef and duck meat whereas real-time PCR was more sensitive than the LAMP in 8 samples. However, S. Typhimurium in chocolate samples was not detected by real-time PCR. The sensitivity of real-time PCR was high in all samples inoculated with L. monocytogenes and C. sakazakii whereas LAMP was more sensitive than real-time PCR in oil-rich foods. Therefore, LAMP can be shown as an easrer, more convenient method, as well as effective analytical method for testing difficult samples when employed in PCR.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.693-698
• /
• 2018

This paper proposes a vehicle detection method for parking areas using unmanned aerial vehicles (UAVs) and using YOLOv2, which is a recent, known, fast, object-detection real-time algorithm. The YOLOv2 convolutional network algorithm can calculate the probability of each class in an entire image with a one-pass evaluation, and can also predict the location of bounding boxes. It has the advantage of very fast, easy, and optimized-at-detection performance, because the object detection process has a single network. The sliding windows methods and region-based convolutional neural network series detection algorithms use a lot of region proposals and take too much calculation time for each class. So these algorithms have a disadvantage in real-time applications. This research uses the YOLOv2 algorithm to overcome the disadvantage that previous algorithms have in real-time processing problems. Using Darknet, OpenCV, and the Compute Unified Device Architecture as open sources for object detection. a deep learning server is used for the learning and detecting process with each car. In the experiment results, the algorithm could detect cars in a dense area using UAVs, and reduced overhead for object detection. It could be applied in real time.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.163-166
• /
• 2000

Real-time traffic detection scheme based on Computer Vision is capable of efficient traffic control using automatically computed traffic information and obstacle detection in moving automobiles. Traffic information is extracted by segmenting vehicle region from road images, in traffic detection system. In this paper, we propose the advanced segmentation of vehicle from road images using multiple local region information. Because multiple local region overlapped in the same lane is processed sequentially from small, the traffic detection error can be corrected.

• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.583-599
• /
• 2022

Although the object detection accuracy with a single image has been significantly improved with the advance of deep learning techniques, the detection accuracy for pig monitoring is challenged by occlusion problems due to a complex structure of a pig room such as food facility. These detection difficulties with a single image can be mitigated by using a video data. In this research, we propose a method in pig detection for video monitoring environment with a static camera. That is, by using both image processing and deep learning techniques, we can recognize a complex structure of a pig room and this information of the pig room can be utilized for improving the detection accuracy of pigs in the monitored pig room. Furthermore, we reduce the execution time overhead by applying a pruning technique for real-time video monitoring on an embedded board. Based on the experiment results with a video data set obtained from a commercial pig farm, we confirmed that the pigs could be detected more accurately in real-time, even on an embedded board.