http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Background Compensation for Pan-Tilt-Zoom Cameras Using 1-D Feature Matching and Outlier Rejection
Jae Kyu Suhr,Ho Gi Jung,Gen Li,Seung-In Noh,Jaihie Kim IEEE 2011 IEEE transactions on circuits and systems for vide Vol.21 No.3
<P>This letter proposes an efficient and robust background compensation method for pan-tilt-zoom cameras. The proposed method approximates the relation between consecutive images to a three-parameter similarity transformation, which is separable in horizontal and vertical axes, and extracts and matches 1-D features that are local minima and maxima of intensity projection profiles in each axis. These correspondences are used to estimate transformation parameters via an outlier rejection approach. Experimental results show that the proposed method is more robust with respect to blurring effects and moving object proportion while dramatically decreasing computational costs compared to previous methods.</P>
Suhr, Jae Kyu,Jung, Ho Gi IEEE 2018 IEEE transactions on intelligent transportation sy Vol.19 No.4
<P>This paper proposes a practical backover warning system using a wide-angle rearview camera. The proposed system utilizes simple but cost-effective techniques for pedestrian detection, verification, and tracking to achieve real-time operation. This system first transforms fisheye images via Mercator projection to reduce pedestrian shape variations. Second, it detects pedestrians based on lower and upper body detectors. This is for handling upright and non-upright poses as well as severe occlusions of upper bodies. Then, it confirms pedestrians by checking the existence of feet or a head inside the lower or upper body region. This step ensures that the system achieves a low false alarm rate. Finally, the confirmed pedestrians are visually tracked by fusing generative and discriminative models in a score level. In the experiment, the proposed system was quantitatively evaluated and compared with the previous method.</P>
Mixture of Gaussians-Based Background Subtraction for Bayer-Pattern Image Sequences
Jae Kyu Suhr,Ho Gi Jung,Gen Li,Jaihie Kim IEEE 2011 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDE Vol.21 No.3
<P>This letter proposes a background subtraction method for Bayer-pattern image sequences. The proposed method models the background in a Bayer-pattern domain using a mixture of Gaussians (MoG) and classifies the foreground in an interpolated red, green, and blue (RGB) domain. This method can achieve almost the same accuracy as MoG using RGB color images while maintaining computational resources (time and memory) similar to MoG using grayscale images. Experimental results show that the proposed method is a good solution to obtain high accuracy and low resource requirements simultaneously. This improvement is important for a low-level task like background subtraction since its accuracy affects the performance of high-level tasks, and is preferable for implementation in real-time embedded systems such as smart cameras.</P>
Jae Kyu Suhr,Ho Gi Jung,Kwanghyuk Bae,Jaihie Kim 대한전자공학회 2008 ICEIC:International Conference on Electronics, Inf Vol.1 No.1
This paper proposes an algorithm for rejecting mismatched points. The proposed algorithm identifies and rejects mismatched points in image pairs obtained under automobile-like motions. The camera rotation is approximated to the simple image shift by assuming that the narrow field of camera is used. The voting method estimates the focus of expansion (FOE) while shifting one of the images. Using the properties of the FOE, the mismatched points are identified and then rejected. Experimental results show that the proposed algorithm effectively rejects the mismatched points while retaining most of the correctly matched points.
Piece-wise Linear 함수 기반 스테레오 영상에서의 도로면 추정 개선 방법
서재규(Jae Kyu Suhr),정호기(Ho Gi Jung) 한국자동차공학회 2012 한국자동차공학회 학술대회 및 전시회 Vol.2012 No.11
This paper proposes a novel road surface estimation method using a piece-wise linear function and RANSAC framework. The proposed method achieves robustness against 3D points on obstacle surfaces by sampling 3D points expected to compose road surface, and it also makes the estimation procedure insensitive to stereo matching errors on textureless road regions by sequentially calculating a piece-wise linear function using a RANSAC-based robust line estimator with adaptively chosen road interval and slope angle parameters. Experimental results show that the proposed method successfully estimates road surfaces in various real world situations including complex road surface shape and severe stereo matching error.
서재규(Jae Kyu Suhr),배광혁(Bea Kwanghyuk),정호기(Ho Gi Jung),김재희(Jaihie Kim) 대한전자공학회 2007 대한전자공학회 학술대회 Vol.2007 No.7
This paper proposes an algorithm for rejecting mismatched points (known as outliers). The proposed algorithm identifies and rejects outliers in image pairs obtained under automobile-like motions which consist of two translations and one rotation. The camera rotation is approximated to the image shift by assuming that the narrow field of lens is used. The voting method estimates the focus of expansion (FOE) while shifting one of the images. Using the properties of the FOE, the outliers are rejected while most of the inliers are retained.