• 한국군사과학기술학회지
• /
• 제11권1호
• /
• pp.66-74
• /
• 2008

This paper presents a new small target detection method using scale invariant feature. Detecting small targets whose sizes are varying is very important to automatic target detection. Scale invariant feature using the Laplacian scale-space can detect different sizes of targets robustly compared to the conventional spatial filtering methods with fixed kernel size. Additionally, scale-reflected adaptive thresholding can reduce many false alarms. Experimental results with real IR images show the robustness of the proposed target detection in real world.

• 한국컴퓨터정보학회논문지
• /
• 제21권11호
• /
• pp.31-38
• /
• 2016

In this paper, we propose multi-scale infrared target detection algorithm with varied filter size using integral image. Filter based target detection is widely used for small target detection, but it doesn't suit for large target detection depending on the filter size. When there are multi-scale targets on the sky background, detection filter with small filter size can not detect the whole shape of the large targe. In contrast, detection filter with large filter size doesn't suit for small target detection, but also it requires a large amount of processing time. The proposed algorithm integrates the filtering results of varied filter size for the detection of small and large targets. The proposed algorithm has good performance for both small and large target detection. Furthermore, the proposed algorithm requires a less processing time, since it use the integral image to make the mean images with different filter sizes for subtraction between the original image and the respective mean image. In addition, we propose the implementation of real-time embedded system using FPGA.

• 대한임베디드공학회논문지
• /
• 제12권4호
• /
• 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.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.482-486
• /
• 2009

Scale-invariant feature is an effective method for retrieving and classifying images. In this study, we analyze a scale-invariant planar curve features for developing 2D shapes. Scale-space filtering is used to determine contour structures on different scales. However, it is difficult to track significant points on different scales. In mathematics, curvature is considered to be fundamental feature of a planar curve. However, the curvature of a digitized planar curve depends on a scale. Therefore, automatic scale detection for curvature analysis is required for practical use. We propose a technique for achieving automatic scale detection based on difference of curvature. Once the curvature values are normalized with regard to the scale, we can calculate difference in the curvature values for different scales. Further, an appropriate scale and its position are detected simultaneously, thereby avoiding tracking problem. Appropriate scales and their positions can be detected with high accuracy. An advantage of the proposed method is that the detected significant points do not need to be located in the same contour. The validity of the proposed method is confirmed by experimental results.

• 한국자동차공학회논문집
• /
• 제21권4호
• /
• pp.43-53
• /
• 2013

Lane marking detection based on a mono camera sensor provides a low cost solution to both ITS (intelligent transportation systems) and DAS (driver assistant systems). A number of methods and implementations have been reported in the literature. However, reliable detection is still an issue. Traditional approaches are mostly based on statistics or Hough transforms. However, the former approaches usually include many irrelevant detection areas, and the latter are not practical because actual lanes are not usually suitable for the approximation with linear or polynomial equations. In this paper, we focus on increasing the reliability of detection by reducing the detection of irrelevant areas while improving the detection of actual lane marking areas, which is usually a tradeoff for most conventional approaches. We use scale-space for that. Through experiments with real images obtained from various environments, we could achieve a significant improvement over traditional approaches.

• 융합신호처리학회논문지
• /
• 제11권3호
• /
• pp.183-188
• /
• 2010

본 논문에서는 LoG scale-space를 이용한 그레이스케일 영상에서 연속패턴 라인 중심축 검출 기법을 제안한다. 제안된 기법은 LoG의 스케일 크기를 적응적으로 가변하여 라인 중심축을 검출하는 방법이다. 작은 스케일의 LoG 연산자는 라인의 에지점에서 영교차 특성이 나타나며, 영교차점을 중심으로 좌우에 +/- 극성을 가진 극점이 존재하게 된다. 즉 일정한 폭을 가지는 라인은 양쪽 가장자리에서 2개의 +극점을 가지게 된다. LoG의 확산동작을 반복함에 따라 스케일을 증가시키면 +극점은 라인 양쪽 에지영역에서 중심영역으로 이동하여 점진적으로 가까워져서 최종적으로 하나의 극점으로 중첩되어진다. 연속패턴 라인 중심축은 2개의 +극점이 중심영역에서 중첩되는 점이다. 제안하는 방법은 기존의 이진영상에서 적용되는 세선화 방법보다 강인하게 연속패턴 라인 중심축을 검출함을 확인하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 추계학술발표대회
• /
• pp.506-509
• /
• 2016

We present real-time pedestrian detection that exploit accuracy of Faster R-CNN network. Faster R-CNN has shown to success at PASCAL VOC multi-object detection tasks, and their ability to operate on raw pixel input without the need to design special features is very engaging. Therefore, in this work we apply and adjust Faster R-CNN to single object detection, which is pedestrian detection. The drawback of Faster R-CNN is its failure when object size is small. Previously, small sized object problem was solved by Scale-aware Network. We incorporate Scale-aware Network to Faster R-CNN. This made our method Scale-aware Faster R-CNN (DF R-CNN) that is both fast and very accurate. We separated Faster R-CNN networks into two sub-network, that is one for large-size objects and another one for small-size objects. The resulting approach achieves a 28.3% average miss rate on the Caltech Pedestrian detection benchmark, which is competitive with the other best reported results.

• 디지털산업정보학회논문지
• /
• 제9권3호
• /
• pp.13-20
• /
• 2013

In this paper, we propose a multi-scale crack detection method. This method uses decomposition, composition, and shape properties. It is based on morphology algorithm, crack features. We use a morphology operator which extracts patterns of crack. It segments cracks and background using opening and closing operations. Morphology based segmentation is better than existing integration methods using subtraction in detecting a crack it has small width. However, morphology methods using only one structure element could detect only fixed width crack. Thus, we use decomposition and composition methods. We use a decimation method for decomposition. After decomposition and morphology operation, we get edge images given by binary values. Our method calculates values of properties such as the number of pixels and the maximum length of the segmented region. We decide whether the segmented region belongs to cracks according to those data. Experimental results show that our proposed multi-scale crack detection method has better results than those of existing detection methods.

• 제어로봇시스템학회논문지
• /
• 제6권12호
• /
• pp.1113-1119
• /
• 2000

To operate a process plant safely and economically, process monitoring is very important. Process monitoring is the task to identify the state of the system from sensor data. Process monitoring includes data acquisition, regulatory control, data reconciliation, fault detection, etc. This research focuses on the data recon-ciliation using scale-space filtering and fault detection using functional-link associative neural networks. Scale-space filtering is a multi-resolution signal analysis method. Scale-space filtering can extract highest frequency factors(noise) effectively. But scale-space filtering has too large calculation costs and end effect problems. This research reduces the calculation cost of scale-space filtering by applying the minimum limit to the gaussian kernel. And the end-effect that occurs at the end of the signal of the scale-space filtering is overcome by using extrapolation related with the clustering change detection method. Nonlinear principal component analysis methods using neural network have been reviewed and the separately expanded functional-link associative neural network is proposed for chemical process monitoring. The separately expanded functional-link associative neural network has better learning capabilities, generalization abilities and short learning time than the exiting-neural networks. Separately expanded functional-link associative neural network can express a statistical model similar to real process by expanding the input data separately. Combining the proposed methods-modified scale-space filtering and fault detection method using the separately expanded functional-link associative neural network-a process monitoring system is proposed in this research. the usefulness of the proposed method is proven by its application a boiler water supply unit.

• Smart Structures and Systems
• /
• 제16권1호
• /
• pp.223-242
• /
• 2015

Wireless sensor networks (WSNs) have emerged as a novel solution to many of the challenges of structural health monitoring (SHM) in civil engineering structures. While research projects using WSNs are ongoing worldwide, implementations of WSNs on full-scale structures are limited. In this study, a WSN is deployed on a full-scale 17.3m-long, 11-bay highway sign support structure to investigate the ability to use vibration response data to detect damage induced in the structure. A multi-level damage detection strategy is employed for this structure: the Angle-between-String-and-Horizon (ASH) flexibility-based algorithm as the Level I and the Axial Strain (AS) flexibility-based algorithm as the Level II. For the proposed multi-level damage detection strategy, a coarse resolution Level I damage detection will be conducted first to detect the damaged region(s). Subsequently, a fine resolution Level II damage detection will be conducted in the damaged region(s) to locate the damaged element(s). Several damage cases are created on the full-scale highway sign support structure to validate the multi-level detection strategy. The multi-level damage detection strategy is shown to be successful in detecting damage in the structure in these cases.