• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.147-153
• /
• 2020

Conventional lane detection algorithms have problems in that the detection rate is lowered in road environments having a large change in curvature and illumination. The probabilistic Hough transform method has low lane detection rate since it exploits edges and restrictive angles. On the other hand, the method using a sliding window can detect a curved lane as the lane is detected by dividing the image into windows. However, the detection rate of this method is affected by road slopes because it uses affine transformation. In order to detect lanes robustly and avoid obstacles, we propose driving assist system using semantic segmentation based on deep learning. The architecture for segmentation is SegNet based on VGG-16. The semantic image segmentation feature can be used to calculate safety space and predict collisions so that we control a vehicle using adaptive-MPC to avoid objects and keep lanes. Simulation results with CARLA show that the proposed algorithm detects lanes robustly and avoids unknown obstacles in front of vehicle.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.6
• /
• pp.1-8
• /
• 2009

Detecting entry and exit zones in a view covered by multiple cameras is an essential step to determine the topology of the camera setup, which is critical for achieving and sustaining the accuracy and efficiency of multi-camera surveillance system. In this paper, a graph theoretic clustering method is proposed to detect zones using data points which correspond to entry and exit events of objects in the camera view. The minimum spanning tree (MST) is constructed by associating the data points. Then a set of well-formed clusters is sought by removing inconsistent edges of the MST, based on the concepts of the cluster balance and the cluster density defined in the paper. Experimental results suggest that the proposed method is effective, even for sparsely elongated clusters which could be problematic for expectation-maximization (EM). In addition, comparing to the EM-based approaches, the number of data required to obtain stable outcome is relatively small, hence shorter learning period.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.08a
• /
• pp.128-132
• /
• 2008

본 논문에서는 현재 자가용 차량 번호판으로 사용되고 있는 4종류의 번호판인, 구형 녹색 번호판 두 종류와 유럽식 신형 흰색 번호판 두 종류에 대해 개별 코드를 효과적으로 추출하기 위한 개선된 퍼지 이진화 방법을 제안한다. 차량 영상에서 수직 에지와 반복 이진화 기법, 그리고 Grassfire 알고리즘을 적용하여 번호판의 후보 영역을 추출하고, 번호판의 형태학적 특징을 이용해 잡음을 제거한 후, 최종 번호판 영역을 추출한다 추출된 번호판 영역에서 개선된 퍼지 이진화 기법을 적용하여 개별 코드를 추출한다. 본 논문에서 제안하는 개선된 퍼지 이진화 방법은 추출한 번호판 영역을 그레이 레벨로 변환한 후에 번호판의 명도를 2구간으로 나누고 각각의 구간에 퍼지 소속 함수를 적용하여 번호판 영역을 이진화한 후, 퍼지 소속 함수에 의해 이진화 된 2개의 번호판 영역 중에서 가장 최적화된 번호판 영역을 선택하여 개별 코드를 추출한다. 본 논문에서 제안한 기법을 4종류의 번호판이 부착된 327장(구형녹색 50장, 신형녹색 157장, 짧은 흰색 60장, 긴 흰색 60장)을 대상으로 실험한 결과, 번호판 영역 추출은 327장의 영상중 97%가 추출되었고 개별 코드 추출은 번호판 영역이 추출된 324장의 영상에서 97%가 추출된 결과를 보였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.10
• /
• pp.925-932
• /
• 2012

In this paper, we develop a pattern recognition algorithm applied to a humanoid robot which is exploited as a guide for visually handicapped persons to find a desired path to their destinations. Behavior primitives of a humanoid robot are defined, and Canny's edge detection algorithm is employed to extract the pattern and color of the paving blocks that especially devised for visually handicapped persons. Based on these, an efficient path finding algorithm is developed and implemented on a humanoid robot, running on an embedded linux operating system equipped with a video camera. The performance of our algorithm is experimentally examined in terms of the response time and the pattern recognition ratio. In order to validate our algorithm in various realistic environments, the experiments are repeatedly performed by changing the tilt of paving blocks and the brightness in surrounding area. The results show that our algorithm performs sufficiently well to be exploited as a path finding system for visually handicapped persons.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.805-808
• /
• 2004

본 논문에서는 두 단백질의 구조적 유사성을 기반으로 한 단백질 비교를 위해서 전처리 기법으로서의 주성분분석기법을 소개한다. 기존의 백본 및 알파탄소 간의 거리행렬(distance matrix), 2차 구조 비교기법, 구역(segment)단위의 비교 기법과 같은 단백질 비교 기법들은 위치이동(translation)와 회전(rotation)에 불변한(invariant) 차이를 구하기 위하여 거리행렬을 이용하였다. 그리고, 난 다음 이들의 최적화 과정을 거쳤다. 그러나, 본 논문에서 제시하는 전처리 기법으로서의 주성분분석기법은 단백질 구조를 전체적인 구조 관점에서 위치를 정렬시킨 후에 단백질 간의 구조를 비교하는 방식이다. 단백질의 구조의 방향성(Orientation)을 맞춘 다음에는 다양한 단백질 표현으로 구를 비교할 수 있다. 본 논문에서는 두 단백질의 구조의 유사성을 측정하기 위한 간결한 단백질 표현(representation)으로 3 차원 에지 히스토그램을 사용하였다. 이 기법은 방향성을 정렬하기 위하여 기존의 방법에서 사용되었던 반복적인 거리계산을 통한 최적화하는 과정을 없앰으로써 단백질 구조 비교 시간을 단축할 수 있는 새로운 단백질 구조 비교 패러다임을 가능하게 한다. 따라서, 이 패러다임을 통하여 적절한 단백질 구조 방향성 정렬과 단백질 구조 표현을 이용한 단백질 구조 비교 검색 시스템은 많은 양의 단백질 구조 정보로부터 원하는 형태의 단백질 구조를 빠른 시간에 검색할 수 있는 장점을 가질 수 있다.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.2
• /
• pp.115-126
• /
• 2012

The artificial captions appearing in videos include information that relates to the videos. In order to obtain the information carried by captions, many methods for caption extraction from videos have been studied. Most traditional methods of detecting caption region have used one frame. However video include not only spatial information but also temporal information. So we propose a method of detection caption region using temporal and spatial information. First, we make improved Text-Appearance-Map and detect continuous candidate regions through matching between candidate-regions. Second, we detect disappearing captions using disappearance test in candidate regions. In case of captions disappear, the caption regions are decided by a merging process which use temporal and spatial information. Final, we decide final caption regions through ANNs using edge direction histograms for verification. Our proposed method was experienced on many kinds of captions with a variety of sizes, shapes, positions and the experiment result was evaluated through Recall and Precision.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.135-142
• /
• 2013

Contour detection is important for many computer vision applications, such as shape discrimination and object recognition. In many cases, local luminance changes turn out to be stronger in textured areas than on object contours. Therefore, local edge features, which only look at a small neighborhood of each pixel, cannot be reliable indicators of the presence of a contour, and some global analysis is needed. The novelty of this operator is that dilation is limited to Deluanary triangular. An efficient implementation is presented. The grouping algorithm is then embedded in a multi-threshold contour detector. At each threshold level, small groups of edges are removed, and contours are completed by means of a generalized reconstruction from markers. Both qualitative and quantitative comparison with existing approaches prove the superiority of the proposed contour detector in terms of larger amount of suppressed texture and more effective detection of low-contrast contour.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.12
• /
• pp.17-26
• /
• 1998

Ultrasonic sensors are widely used in various applications due to advantages of low cost, simplicity in construction, mechanical robustness, and little environmental restriction in usage. But for the application of object recognition, ultrasonic sensors exhibit several shortcomings of poor directionality which results in low spatial resolution of objects, and specularity which gives frequent erroneous range readings. The time-of-flight(TOF) method generally used for distance measurement can not distinguish small object patterns of plane, corner or edge. To resolve the problem, an increased number of the sensors in the forms of a linear array or 2-dimensional array of the sensors has been used. Also better resolution has been obtained by shifting the array in several steps using mechanical actuators. Also simple patterns are classified based on analyzing signal reflections. In this paper we propose a method of a sensor array system with improved capability in pattern distinction using electronic circuits accompanying the sensor array, and intelligent algorithm based on neuro-fuzzy processing of data fusion. The circuit changes transmitter output voltages of array elements in several steps. A set of different return signals from neighborhood sensors is manipulated to provide enhanced pattern recognition in the aspects of inclination angle, size and shift as well as distance of objects. The results show improved resolution of the measurements for smaller targets.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.8
• /
• pp.1783-1788
• /
• 2009

We newly propose that we may reuse scrap powders ($Z_rO_2$+8 mol%-$Y_2O_3$) as $Y_2O_3$-stabilized zirconia (YSZ) sintered products through sintering process at 1550$^{circ}C$ for 2hrs. We also prepared the reference specimen from fresh $Z_rO_2$+30 mol%-$Y_2O_3$ powder mixture (celluar type with 1㎛-length). The reference sample showed a dense microstructure with grains of $\sim$10㎛ in diameter, while the sintered sample from scrap powder showed irregular grains of 1$\sim$30 ㎛ in diameter. Through XRD analysis, we confirmed that the reference sample has mixed phases of $Y_2O_3$(cubic), $Z_{r0.8}O_{1.9}$(cubic), and $Z_rO_2$(monoclinic), while the sintered YSZ sample from scrap powder has only tetragonal phase. Moreover, the sintered YSZ from scrap powder showed vickers hardness and apparent density more than 70 and 4.11 g/cc, which implies that it can be suitable for structural material application.

• The KIPS Transactions:PartB
• /
• v.16B no.4
• /
• pp.299-308
• /
• 2009

AAM(Active Appearance Model) is an algorithm to extract face feature points with statistical models of shape and texture information based on PCA(Principal Component Analysis). This method is widely used for face recognition, face modeling and expression recognition. However, the detection performance of AAM algorithm is sensitive to initial value and the AAM method has the problem that detection error is increased when an input image is quite different from training data. Especially, the algorithm shows high accuracy in case of closed lips but the detection error is increased in case of opened lips and deformed lips according to the facial expression of user. To solve these problems, we propose the improved AAM algorithm using lip feature points which is extracted based on a new lip detection algorithm. In this paper, we select a searching region based on the face feature points which are detected by AAM algorithm. And lip corner points are extracted by using Canny edge detection and histogram projection method in the selected searching region. Then, lip region is accurately detected by combining color and edge information of lip in the searching region which is adjusted based on the position of the detected lip corners. Based on that, the accuracy and processing speed of lip detection are improved. Experimental results showed that the RMS(Root Mean Square) error of the proposed method was reduced as much as 4.21 pixels compared to that only using AAM algorithm.