• Journal of KIISE
• /
• v.42 no.1
• /
• pp.93-96
• /
• 2015

The SIFT method is well-known for robustness against various image transformations, and is widely used for image retrieval and matching. The SIFT method extracts keypoints using scale space analysis, which is different from conventional keypoint detection methods that depend only on the image space. The SIFT method has also been extended to use higher-order scale space derivatives for increasing the number of keypoints detected. Such detection of additional keypoints detected was shown to provide performance gain in image retrieval experiments. Herein, a sigma based normalization method for keypoint detection is introduced using higher-order scale space derivatives.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.3
• /
• pp.135-149
• /
• 2008

Traditional attack detection schemes based on packets or flows have very high computational complexity. And, network based anomaly detection schemes can reduce the complexity, but they have a limitation to figure out the pattern of the distributed global scale network attack. In this paper, we propose an efficient and fast method for detecting distributed global-scale network attack symptoms in high-speed backbone networks. The proposed method is implemented at the aggregate traffic level. So, our proposed scheme has much lower computational complexity, and is implemented in very high-speed backbone networks. In addition, the proposed method can detect attack patterns, such as attacks in which the target is a certain host or the backbone infrastructure itself, via collaboration of edge routers on the backbone network. The effectiveness of the proposed method are demonstrated via simulation.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1188-1194
• /
• 2018

This paper proposes an image enhancement-based license plate detection algorithm to improve the overall performance of system. Non-uniform illumination conditions have huge impact on overall plate detection system accuracy. In this paper, we propose an algorithm for color image enhancement-based license plate detection for improving accuracy of images degraded by excessively strong and low sunlight. Firstly, the image is enhanced by Multi-Scale Retinex algorithm. Secondly, a plate detection method is employed to take advantage of geometric properties of connected components, which can significantly reduce the undesired plate regions. Finally, intersection over union method is applied for detecting the accurate location of number plate. Experimental results show that the proposed method significantly improves the accuracy of plate detection system.

• ETRI Journal
• /
• v.39 no.1
• /
• pp.124-134
• /
• 2017

Data races are one of the most difficult types of bugs in concurrent multithreaded systems. It requires significant time and cost to accurately detect bugs in complex large-scale programs. Although many race detection techniques have been proposed by various researchers, none of them are effective in all aspects. In this paper, we compare the performance of five recent dynamic race detection techniques: FastTrack, Acculock, Multilock-HB, SimpleLock+, and causally precedes (CP) detection. We experimentally demonstrate the strengths and weaknesses of these dynamic race detection techniques in terms of their detection capability, running time, and runtime overhead using 20 benchmark programs with different characteristics. The comparison results show that the detection capability of CP detection does not differ from that of FastTrack, and that SimpleLock+ generates the lowest overhead among the hybrid detection techniques (Acculock, SimpleLock+, and Multilock-HB) for all benchmark programs. SimpleLock+ is 1.2 times slower than FastTrack on average, but misses one true data race reported from Mutilock-HB on the large-scale benchmark programs.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1431-1438
• /
• 2018

In this paper, we proposed a river water level detection and tracking of the river or dams based on image processing system. In past, most of the water level detection system used various water sensors. Those water sensors works perfectly but have many drawbacks such as high cost and harsh weather. Water level monitoring system helps in forecasting early river disasters and maintenance of the water body area. However, the early river disaster warning system introduces many conflicting requirements. Surveillance camera based water level detection system depends on either the area of interest from the water body or on optical flow algorithm. This proposed system is focused on water scaling area of a river or dam to detect water level. After the detection of scale area from water body, the proposed algorithm will immediately focus on the digits available on that area. Using the numbers on the scale, water level of the river is predicted. This proposed system is successfully tested on different water bodies to detect the water level area and predicted the water level.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.1-8
• /
• 2023

In this paper, we propose a black ice detection platform framework using Convolutional Neural Networks (CNNs). To overcome black ice problem, we introduce a real-time based early warning platform using CNN-based architecture, and furthermore, in order to enhance the accuracy of black ice detection, we apply a multi-scale dilation convolution feature fusion (MsDC-FF) technique. Then, we establish a specialized experimental platform by using a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Experimental results of a real-time black ice detection platform show the better performance of our proposed network model compared to conventional image segmentation models. Our proposed platform have achieved real-time segmentation of road black ice areas by deploying a road black ice area segmentation network on the edge device Jetson Nano devices. This approach in parallel using multi-scale dilated convolutions with different dilation rates had faster segmentation speeds due to its smaller model parameters. The proposed MsCD-FF Net(2) model had the fastest segmentation speed at 5.53 frame per second (FPS). Thereby encouraging safe driving for motorists and providing decision support for road surface management in the road traffic monitoring department.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.53-62
• /
• 2001

In this paper, the hybrid function by local scale control is proposed to detect the optimal edges from blurred images. In the case of image capturing, some blurring is occurred by the characteristics of the illumination and the reflected light. During processing the blurred image, it is difficult to detect perfect edges. This algorithm proposed a new hybrid function which is merged Gaussian function and the second derivative of Gaussian function. And it detects the optimal edges applying directional edge detection by Canny algorithm as the scale factor of $\sigma$ in the given local mask has been changed after convolving the hybrid function for input image. In the result, the performance is confirmed that this algorithm is better than Sobel, Robert and Canny edge detector by analyzing the some test images. And the results is obtained 0.2 ㏈ ~ 14 ㏈ of PSNR than those conventional method.