• KSCI Review
• /
• v.8 no.2
• /
• pp.9-14
• /
• 2001

본 논문에서는 새로운 칼라 모폴로지 피라미드를 제안하고. 제안된 칼라 모폴로지의 유용성 평가를 위해 이미지에서 중요한 에지를 검출하고자 한다. 여기서 이미지 피라미드 구조는 최초 컬러 이미지의 반복적인 필터링과 샘플링의 순차적인 실험 과정의 단계를 본 논문에서 제안한 CMP를 이용하여 연속적인 필터링 처리로 불필요한 크기의 물체 및 잡음을 제거하여. 효율적인 특징 추출의 유효성을 검증하고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.449-450
• /
• 2011

본 논문에서는 영상에서의 물체 인식에 주로 사용되었던 공간 피라미드를 변형시킨 각도 피라미드를 이용한 bag-of-features 방법으로 회전 변화에도 강한 물체 인식에도 적용할 수 있도록 한다. 기존의 공간 피라미드에서 수직의 격자 모양으로 영상을 나누었던 것에 비해 각도 피라미드는 영상의 중심을 기준으로 동일한 각도로 영상을 분할하여 피라미드로 만든다. 각 영역 안에서 특징들의 히스토그램으로 영상을 표현하고 영상간의 유사도는 각도 피라미드를 단계별로 순환적 자리옮김을 통해 회전시켜가며 히스토그램 교집합을 구하여 측정한다. 이 방법을 Caltech-101 데이터베이스에 적용해본 결과 회전 변환을 준 테스트 영상에 대해 기존의 공간 피라미드를 사용한 방법에 비해 높은 성능을 보이는 것을 확인하였다. 따라서 이 방법을 통하여 다양한 상황의 일반적인 물체 분류할 수 있을 것으로 기대한다.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.283-294
• /
• 2022

The feature map used in the network for deep learning generally has larger data than the image and a higher compression rate than the image compression rate is required to transmit the feature map. This paper proposes a method for transmitting a pyramid feature map with high compression rate, which is used in a network with an FPN structure that has robustness to object size in deep learning-based image processing. In order to efficiently compress the pyramid feature map, this paper proposes a structure that predicts a pyramid feature map of a level that is not transmitted with pyramid feature map of some levels that transmitted through the proposed prediction network to efficiently compress the pyramid feature map and restores compression damage through the proposed reconstruction network. Suggested mAP, the performance of object detection for the COCO data set 2017 Train images of the proposed method, showed a performance improvement of 31.25% in BD-rate compared to the result of compressing the feature map through VTM12.0 in the rate-precision graph, and compared to the method of performing compression through PCA and DeepCABAC, the BD-rate improved by 57.79%.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.934-936
• /
• 2005

본 논문에서는 피라미드 계층간에 나타나는 잡음 신호의 특성을 바탕으로 라플라시안 피라미드를 이용한 X-ray 영상의 잡음 제거 방법을 제안한다. 제안하는 방법은 잡음 제거를 위해 X-ray 영상 신호의 지역적 표준 편차와 신호의 영역적 특징을 이용하였다. 지역적 표준 편차는 영상의 경계선 정도와 비례하는 특징을 가지기 때문에 지역적 표준 편차를 이용하여 경계 정보의 손실을 막았다. 또한 라플라시안 피라미드의 각 계층에 잡음 신호가 좁은 면적을 가지며 분포되는 영역적 특징을 이용하여 평평한 지역에서 잡음 신호의 제거 성능을 높였다. X-ray영상 및 잡음이 첨가된 표준 영상에 대한 실험을 통해 제안된 방법이 경계 정보의 유지와 잡음 제거에서 기존의 방법보다 향상된 성능을 보임을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.10 no.11
• /
• pp.1407-1416
• /
• 2007

This paper describes an algorithm for arbitrary point tracking using pyramidal optical flow. The optical flow is calculated based on the Lucas-Kanade's optical flow estimation in this paper. The image pyramid is employed to calculate a big motion while being sensitive to a small motion. Furthermore, a rectification process is proposed to reduce the error which is increased as it goes down to the lower level of the image pyramid. The accuracy of the optical flow estimation was increased by using some constraints and sub-pixel interpolation of the optical flow and this makes our algorithm to track points in which they do not have features such as edges or corners. The proposed algorithm is implemented and primary results are shown in this paper.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1358-1360
• /
• 2015

본 논문에서는 MB-LBP(Multi-scale Block Local Binary Patterns)와 공간피라미드를 이용하여 생성된 특징을 랜덤 포레스트(Random Forest) 분류기에 적용하여 영상내의 표지판 속도를 인식하는 알고리즘을 제안한다. 입력 영상에서 표지판 영역은 다양한 위치와 크기를 가지며 주위 배경이 후보 영역에 포함되므로 먼저 입력 영상에 원형 Hough Transform을 적용하여 원형의 표지판 후보 영역만을 검출한다. 그 후 영상의 화질을 향상시키기 위해 히스토그램 평활화와 모폴로지 연산을 적용하여 표지판의 숫자 영역과 배경 영역의 대비를 높이도록 한다. 표지판의 크기 변화에 강건한 시스템의 구현을 위해 후보 영역에서 LBP(Local Binary Patterns)보다 우수한 성능을 보이는 MB-LBP를 적용하고, 다양한 크기의 속도 표지판을 인식하기 위해 공간 피라미드를 사용하여 지역적 특징과 전역적 특징 모두를 추출하였다. 추출된 특징은 랜덤 포레스트(Random Forest)를 이용하여 각 9개의 속도 표지판으로 분류, 각 속도별 클래스에 대한 인식 성능을 측정하였다.

• Journal of KIISE:Databases
• /
• v.35 no.4
• /
• pp.345-355
• /
• 2008

SIFT is popularly used in computer vision application such as object recognition, motion tracking, and 3D reconstruction among various shape descriptors. However, it is not easy to apply SIFT into the image similarity search as it is since it uses many high dimensional keypoint vectors. In this paper, we present a SIFT based image similarity search method using an edge image pyramid and an interesting region detection. The proposed method extracts keypoints, which is invariant to contrast, scale, and rotation of image, by using the edge image pyramid and removes many unnecessary keypoints from the image by using the hough transform. The proposed hough transform can detect objects of ellipse type so that it can be used to find interesting regions. Experimental results demonstrate that the retrieval performance of the proposed method is about 20% better than that of traditional SIFT in average recall.

• Journal of KIISE:Databases
• /
• v.36 no.6
• /
• pp.446-454
• /
• 2009

Among various region detector and shape feature extraction method, MSER(Maximally Stable Extremal Region) and SIFT and its variant methods are popularly used in computer vision application. However, since SIFT is sensitive to the illumination change and MSER is sensitive to the scale change, it is not easy to apply the image similarity retrieval. In this paper, we present a Scale and Rotation Invariant Region Feature(SRIRF) descriptor using scale pyramid, MSER and affine normalization. The proposed SRIRF method is robust to scale, rotation, illumination change of image since it uses the affine normalization and the scale pyramid. We have tested the SRIRF method on various images. Experimental results demonstrate that the retrieval performance of the SRIRF method is about 20%, 38%, 11%, 24% better than those of traditional SIFT, PCA-SIFT, CE-SIFT and SURF, respectively.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.2 s.302
• /
• pp.11-18
• /
• 2005

To detect vehicles in image, first the image is transformed with the steerable pyramid which has independent directions and levels. Feature vectors are the collection of filter responses at different scales of a steerable image pyramid. For the detection of vehicles in image, feature vectors in feature points of the vehicle image is used. First the feature points are selected with the grid points in vehicle image that are evenly spaced, and second, the feature points are comer points which m selected by human, and last the feature points are corner Points which are selected in grid points. Next the feature vectors of the model vehicle image we compared the patch of the test images, and if the distance of the model and the patch of the test images is lower than the predefined threshold, the input patch is decided to a vehicle. In experiment, the total 11,191 vehicle images are captured at day(10,576) and night(624) in the two local roads. And the $92.0\%$ at day and $87.3\%$ at night detection rate is achieved.