• Journal of Information Processing Systems
• /
• v.15 no.1
• /
• pp.67-90
• /
• 2019

Accurate detection, tracking and analysis of human movement using robots and other visual surveillance systems is still a challenge. Efforts are on to make the system robust against constraints such as variation in shape, size, pose and occlusion. Traditional methods of detection used the sliding window approach which involved scanning of various sizes of windows across an image. This paper concentrates on employing a state-of-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation for color-consistent segments and object level segmentation for category-consistent regions. The tracking phase is achieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking scheme with validation phase. Localization of human region in each frame is performed by keypoints by casting votes for the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-based framework is used to detect voting behavior. The designed methodology is tested on the video sequences having 3 to 4 persons.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.37-38
• /
• 2023

본 논문에서는 딥러닝을 기반으로 하는 키포인트 인식 모델을 산업용 품질검사 머신비전에 응용하는 방법을 제안한다. 전이학습 방법을 이용하여 딥러닝 모델의 인식률을 높이는 방법을 제시하였고, 전이시킨 특성 추출 모델에 대해 추가로 데이터 세트에 대한 학습을 진행하는 것이 특성추출 모델의 초기 ImageNet 가중치를 동결시켜 학습하는 것보다 학습 속도나 정확도가 높다는 것을 보여준다. 실험을 통해 딥러닝을 응용하는 산업용 품질 검사 공정에는 특성추출 모델의 추가 학습이 중요하다는 점을 확인할 수 있었다.

• Journal of Broadcast Engineering
• /
• v.19 no.2
• /
• pp.166-173
• /
• 2014

Recently, human action recognition have been developed for various broadcasting and video process. Since a video can consist of various scenes, keypoint approaches have been more attracted than template based methods for real application. Keypoint approahces tried to find regions having motion in video, and made 3-dimensional patches. Then, descriptors using histograms were computed from the patches, and a classifier based on machine learning method was applied to detect actions in video. However, a single classifier was difficult to handle various human actions. In order to improve this problem, approaches using multi classifiers were used to detect and to recognize objects. Thus, we propose a new human action recognition using decision-level fusion with support vector machine and sparse representation. The proposed method extracted descriptors based on keypoint approach from a video, and acquired results from each classifier for human action recognition. Then, we applied weights which were acquired by training stage to fuse each results from two classifiers. The experiment results in this paper show better result than a previous fusion method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.1
• /
• pp.13-22
• /
• 2009

In this paper, we propose the 3D shape reconstruction method that combine the mosaic method and the active stereo matching using the laser beam. The active stereo matching method detects the position information of the irradiated laser beam on object by analyzing the color and brightness variation of left and right image, and acquires the depth information in epipolar line. The mosaic method extracts feature point of image by using harris comer detection and matches the same keypoint between the sequence of images using the keypoint descriptor index method and infers correlation between the sequence of images. The depth information of the sequence image was calculated by the active stereo matching and the mosaic method. The merged depth information was reconstructed to the 3D shape information by wrapping and blending with image color and texture. The proposed reconstruction method could acquire strong the 3D distance information, and overcome constraint of place and distance etc, by using laser slit beam and stereo camera.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.6
• /
• pp.49-59
• /
• 2008

SIFT(Scale Invariant Feature Transform) is an algorithm to extract vectors at pixels around keypoints, in which the pixel colors are very different from neighbors, such as vortices and edges of an object. The SIFT algorithm is being actively researched for various image processing applications including 3-D image constructions, and its most computation-intensive stage is a keypoint localization. In this paper, we develope a fixed-point model of the keypoint localization and propose its efficient hardware architecture for embedded applications. The bit-length of key variables are determined based on two performance measures: localization accuracy and error rate. Comparing with the original algorithm (implemented in Matlab), the accuracy and error rate of the proposed fixed point model are 93.57% and 2.72% respectively. In addition, we found that most of missing keypoints appeared at the edges of an object which are not very important in the case of keypoints matching. We estimate that the hardware implementation will give processing speed of $10{\sim}15\;frame/sec$, while its fixed point implementation on Pentium Core2Duo (2.13 GHz) and ARM9 (400 MHz) takes 10 seconds and one hour each to process a frame.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.764-768
• /
• 2015

Requirement of effective image handling methods such as image retrieval has been increasing with the rising production and consumption of multimedia data. In this paper, a method of constructing more effective descriptor is proposed for robust keypoint based image retrieval. The proposed method uses information embedded in the first order and second order derivative images, in addition to the scale space image, for the descriptor construction. The performance of multi-image descriptor is evaluated in terms of the similarities in keypoints with a public domain image database that contains various image transformations. The proposed descriptor shows significant improvement in keypoint matching with minor increase of the length.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1931-1932
• /
• 2006

로봇이 어떤 물체를 인지하고 그 물체에 대해 어떤 작업을 하고자 할 때 특정 물체의 인식 문제, 3차원 정보를 획득하는 문제, 자세를 추정하는 문제 등 해결해야 될 문제들이 있다. 물체를 인식하는 과정에서는 주위 배경과 물체의 크기의 변화, 회전, 가려짐 등으로 인해 물체 인식을 어렵게 만드는 요소들이 있다. 2차원 이미지를 통해 3차원 정보를 추출하는 과정은 일반적으로 두 대의 카메라를 이용하여 스테레오 이미지를 통해 얻는다. 이 때 좌우 영상간의 매칭의 과정이 필요하다. 자세 추정의 문제는 카메라 좌표와 물체의 좌표간의 관계를 알아야 한다. Visual Servoing을 어렵게 만드는 많은 요인들이 있으며 본 논문에서는 물체의 크기, 회전, 이동에 불변인 디스크립터(descriptor)를 사용하는 SIFT(Scale Invariant Feature Transform)를 통해 3차원 물체의 인식과 자세를 추정하는 방법을 제시한다. 또한 자세 추정을 위해 2차원 Keypoint들의 매칭을 3차원 정보를 통해 검증하는 방법을 제시한다. (SIFT에 의해 추출된 point를 Keypoint라 명한다.)

• ETRI Journal
• /
• v.39 no.1
• /
• pp.97-107
• /
• 2017

A fast and accurate building-level visual place recognition method built on an image-retrieval scheme using street-view images is proposed. Reference images generated from street-view images usually depict multiple buildings and confusing regions, such as roads, sky, and vehicles, which degrades retrieval accuracy and causes matching ambiguity. The proposed practical database refinement method uses informative reference image and keypoint selection. For database refinement, the method uses a spatial layout of the buildings in the reference image, specifically a building-identification mask image, which is obtained from a prebuilt three-dimensional model of the site. A global-positioning-system-aware retrieval structure is incorporated in it. To evaluate the method, we constructed a dataset over an area of $0.26km^2$. It was comprised of 38,700 reference images and corresponding building-identification mask images. The proposed method removed 25% of the database images using informative reference image selection. It achieved 85.6% recall of the top five candidates in 1.25 s of full processing. The method thus achieved high accuracy at a low computational complexity.

• Journal of Korea Multimedia Society
• /
• v.16 no.9
• /
• pp.1057-1066
• /
• 2013

Personal verification using finger-knuckle-print(FKP) uses lines and creases at the finger-knuckle area, so the orientation information of texture is an important feature. In this paper, we propose an effective FKP verification method which extracts keypoints using SIFT algorithm and matches the keypoints by vector similarity. The vector is defined as a direction vector which connects a keypoint extracted from a query image and a corresponding keypoint extracted from a reference image. Since the direction vector is created by a pair of local keypoints, the direction vector itself represents only a local feature. However, it has an advantage of expanding a local feature to a global feature by comparing the vector similarity among vectors in two images. The experimental results show that the proposed method is superior to the previous methods based on orientation codes.

• Advances in robotics research
• /
• v.2 no.1
• /
• pp.33-44
• /
• 2018

This paper presents a novel feature detection algorithm called depth-hybrid speeded-up robust features (DH-SURF) augmented by depth information in the speeded-up robust features (SURF) algorithm. In the keypoint detection part of classical SURF, the standard deviation of the Gaussian kernel is varied for its scale-invariance property, resulting in increased computational complexity. We propose a keypoint detection method with less variation of the standard deviation by using depth data from a red-green-blue depth (RGB-D) sensor. Our approach maintains a scale-invariance property while reducing computation time. An RGB-D simultaneous localization and mapping (SLAM) system uses a feature extraction method and depth data concurrently; thus, the system is well-suited for showing the performance of the DH-SURF method. DH-SURF was implemented on a central processing unit (CPU) and a graphics processing unit (GPU), respectively, and was validated through the real-time RGB-D SLAM.