• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제27권1호
• /
• pp.37-55
• /
• 2023

In this paper we propose a new algorithm for detecting and counting flowers in a complex background based on digital images. The algorithm mainly includes the following parts: edge contour extraction of flowers, edge contour determination of overlapped flowers and flower counting. We use a contour detection technique in Computer Vision (CV) to extract the edge contours of flowers and propose an improved algorithm with a concave point detection technique to find accurate segmentation for overlapped flowers. In this process, we first use the polygon approximation to smooth edge contours and then adopt the second-order central moments to fit ellipse contours to determine whether edge contours overlap. To obtain accurate segmentation points, we calculate the curvature of each pixel point on the edge contours with an improved Curvature Scale Space (CSS) corner detector. Finally, we successively give three adaptive judgment criteria to detect and count flowers accurately and automatically. Both experimental results and the proposed evaluation indicators reveal that the proposed algorithm is more efficient for flower counting.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권5호
• /
• pp.380-388
• /
• 2004

This study proposed an improved spike detection algorithm which automatically detects suitable spike threshold on the amplitude of surface electromyography(SEMG) signal during isometric contraction. The EMG data from the low back muscles was obtained in six channels and the proposed signal processing algorithm is compared with the median frequency and Gabriel's spike parameter. As a result, the reliability of spike parameter was inferior to the median frequency. This fact indicates that a spike parameter is inadequate for analysis of multi-channel EMG signal. Because of uncertainty of fixed spike threshold, the improved spike detection algorithm was proposed. It automatically detects suitable spike threshold depending on the amplitude of the EMG signal, and the proposed algorithm was able to detect optimal threshold based on mCFAR(modified Constant False Alarm Rate) in the every EMG channel. In conclusion, from the reliability points of view, neither median frequency nor existing spike detection algorithm was superior to the proposed method.

• 전기전자학회논문지
• /
• 제20권1호
• /
• pp.82-88
• /
• 2016

영상 인식에서 널리 이용되는 PPHT(Progressive Probability Hough Transform)는 직선을 정확하게 인식하는 우수한 알고리즘이나 원본 영상이 선명하지 않거나 복잡하여 잡음 성분이 많은 경우 인식률이 감소하는 문제가 있다. 이러한 문제를 해결하기 위해 잡음에 강하고 손상된 가장자리 패턴을 복구하며 직선을 인식하는 개선된 PPHT 방식을 제안한다. 제안하는 알고리즘은 픽셀 단위로 직선을 추적하고 검증하여 선분을 검출하는 방식으로 잡음의 영향을 최소화하고 손상된 가장자리 패턴을 일정 범위 내에서 복구하여 인식률을 증가시켰다. 제안한 알고리즘을 차선 인식에 적용하여 직선의 오인식률을 30% 이상 감소시키고 선분 인식률이 15%까지 증가함을 확인하였다.

• Journal of information and communication convergence engineering
• /
• 제4권4호
• /
• pp.174-179
• /
• 2006

In this paper we present a text detection method inspired by wavelet packet analysis and improved fuzzy clustering algorithm(IAFC).This approach assumes that the text and non-text regions are considered as two different texture regions. The text detection is achieved by using wavelet packet analysis as a feature analysis. The wavelet packet analysis is a method of wavelet decomposition that offers a richer range of possibilities for document image. From these multi scale features, we adapt the improved fuzzy clustering algorithm based on the unsupervised learning rule. The results show that our text detection method is effective for document images scanned from newspapers and journals.

• 한국멀티미디어학회논문지
• /
• 제24권3호
• /
• pp.416-422
• /
• 2021

Due to the large differences in human activity within classes, the large similarity between classes, and the problems of visual angle and occlusion, it is difficult to extract features manually, and the detection rate of human behavior is low. In order to better solve these problems, an improved Faster R-CNN-based detection algorithm is proposed in this paper. It achieves multi-object recognition and localization through a second-order detection network, and replaces the original feature extraction module with Dense-Net, which can fuse multi-level feature information, increase network depth and avoid disappearance of network gradients. Meanwhile, the proposal merging strategy is improved with Soft-NMS, where an attenuation function is designed to replace the conventional NMS algorithm, thereby avoiding missed detection of adjacent or overlapping objects, and enhancing the network detection accuracy under multiple objects. During the experiment, the improved Faster R-CNN method in this article has 84.7% target detection result, which is improved compared to other methods, which proves that the target recognition method has significant advantages and potential.

• 자동차안전학회지
• /
• 제11권2호
• /
• pp.35-43
• /
• 2019

This paper describes the improved environment recognition algorithms using some type of sensors like LiDAR and cameras. Additionally, integrated control algorithm for an autonomous vehicle is included. The integrated algorithm was based on C++ environment and supported the stability of the whole driving control algorithms. As to the improved vision algorithms, lane tracing and traffic sign recognition were mainly operated with three cameras. There are two algorithms developed for lane tracing, Improved Lane Tracing (ILT) and Histogram Extension (HIX). Two independent algorithms were combined into one algorithm - Enhanced Lane Tracing with Histogram Extension (ELIX). As for the enhanced traffic sign recognition algorithm, integrated Mutual Validation Procedure (MVP) by using three algorithms - Cascade, Reinforced DSIFT SVM and YOLO was developed. Comparing to the results for those, it is convincing that the precision of traffic sign recognition is substantially increased. With the LiDAR sensor, static and dynamic obstacle detection and obstacle avoidance algorithms were focused. Therefore, improved environment recognition algorithms, which are higher accuracy and faster processing speed than ones of the previous algorithms, were proposed. Moreover, by optimizing with integrated control algorithm, the memory issue of irregular system shutdown was prevented. Therefore, the maneuvering stability of the autonomous vehicle in severe environment were enhanced.

• 플랜트 저널
• /
• 제16권4호
• /
• pp.33-39
• /
• 2020

For several decades, productivity in construction industry has been regressed and it is inevitable to improve productivity for major EPC players. One of challenges to achieve this goal is automatically extracting information from imaged drawings. Although computer vision technique has been advanced rapidly, it is still a problem to detect pipe lines in a drawing. Earlier works for line detection have problems that detected line elements be broken into small pieces and accuracy of detection is not enough for engineers. Thus, we adopted Contour and Hough Transform algorithm and reinforced these to improve detection results. First, Contour algorithm is used with Ramer Douglas Peucker algorithm(RDP). Weakness of contour algorithm is that some blank spaces are occasionally found in the middle of lines and RDP covers them around 17%. Second, HEC Hough Transform algorithm, we propose on this paper, is improved version of Hough Transform. It adopted iteration of Hough Transform and merged detected lines by conventional Hough Transform based on Euclidean Distance. As a result, performance of Our proposed method improved by 30% than previous.

• 자동차안전학회지
• /
• 제13권2호
• /
• pp.35-41
• /
• 2021

In this study, improved path tracking control algorithm based on pure pursuit algorithm is newly proposed by using improved lane detection algorithm through real time post-processing with interpolation methodology. Since the original pure pursuit works well only at speeds below 20 km/h, the look-ahead distance is implemented as a sigmoid function to work well at an average speed of 45 km/h to improve tracking performance. In addition, a smoothing filter was added to reduce the steering angle vibration of the original algorithm, and the stability of the steering angle was improved. The post-processing algorithm presented has implemented more robust lane recognition system using real-time pre/post processing method with deep learning and estimated interpolation. Real time processing is more cost-effective than the method using lots of computing resources and building abundant datasets for improving the performance of deep learning networks. Therefore, this paper also presents improved lane detection performance by using the final results with naive computer vision codes and pre/post processing. Firstly, the pre-processing was newly designed for real-time processing and robust recognition performance of augmentation. Secondly, the post-processing was designed to detect lanes by receiving the segmentation results based on the estimated interpolation in consideration of the properties of the continuous lanes. Consequently, experimental results by utilizing driving guidance line information from processing parts show that the improved lane detection algorithm is effective to minimize the lateral offset error in the diverse maneuvering roads.

• 한국정보통신학회논문지
• /
• 제22권10호
• /
• pp.1334-1339
• /
• 2018

Viola & Jones의 얼굴 검출 알고리즘은 대표적인 얼굴 검출 알고리즘으로 매우 우수한 얼굴 검출 성능을 보인다. 그러나 많은 얼굴을 포함하는 영상들을 대상으로 한 Viola & Jones 알고리즘은 얼굴의 다양성으로 미검출 얼굴들, 가짜 얼굴들과 중복 검출된 얼굴들 같은 잘못 검출된 얼굴들을 발생시킨다. 본 논문은 Viola & Jones 알고리즘에서 생성된 잘못 검출된 얼굴들을 제거하는 얼굴 검증 알고리즘을 이용한 개선된 얼굴 검출 알고리즘을 제안한다. 제안된 얼굴 검증 알고리즘은 검출된 얼굴들에 대한 크기, 지정된 영역의 피부색, 눈과 입에서 발생된 에지, 중복 검출을 평가하여 얼굴이 유효한지를 확인한다. Viola & Jones 알고리즘에 의해 검출된 658개의 얼굴 영상들을 대상으로 한 얼굴 검증 실험에서 제안된 얼굴 검증 알고리즘은 실제 사람들에 의해 생성된 모든 얼굴 영상들을 검증하는 것을 보여준다.

• Smart Structures and Systems
• /
• 제3권3호
• /
• pp.263-280
• /
• 2007

In this paper, an improved GA-based damage detection algorithm using a set of combined modal features is proposed. Firstly, a new GA-based damage detection algorithm is formulated for beam-type structures. A schematic of the GA-based damage detection algorithm is designed and objective functions using several modal features are selected for the algorithm. Secondly, experimental modal tests are performed on free-free beams. Modal features such as natural frequency, mode shape, and modal strain energy are experimentally measured before and after damage in the test beams. Finally, damage detection exercises are performed on the test beam to evaluate the feasibility of the proposed method. Experimental results show that the damage detection is the most accurate when frequency changes combined with modal strain-energy changes are used as the modal features for the proposed method.