• Publications
  • Influence
Road Extraction from High-Resolution SAR Images via Automatic Local Detecting and Human-Guided Global Tracking
Because of existence of various kinds of disturbances, layover effects, and shadowing, it is difficult to extract road from high-resolution SAR images. A new road center-point searching method is
An Improved Text Localization Method for Natural Scene Images
TLDR
The Maximally Stable Extremal Region (MSER) method is used to detect text candidate regions and the SWT algorithm is used in the candidate regions, which can improve the edge detection compared with tradition SWT method.
Semi-automatic road centerline extraction in high-resolution SAR images based on circular template matching
TLDR
A new semi-automatic road centerline extraction method based on circular template matching that is effective in high resolution SAR images and linked by quadratic curve fitting.
AN IMPROVED SCHEME FOR PARAMETER ESTIMATION OF G° DISTRIBUTION MODEL IN HIGH-RESOLUTION SAR IMAGES
TLDR
An improved parameter estimation scheme of the G 0 distribution is proposed, which combines the classical moment estimation with the mellin transform and adopts the Kullback- Leibler distance, Kolmogorov-Smirnov test and Mean Square Error as similarity measurements.
Road junction extraction in high-resolution SAR images via morphological detection and shape identification
TLDR
A road junction extraction method with two stages that has a higher recognition rate than two other methods, is robust to various interferences, and is validated by airborne synthetic aperture radar images of 1 m resolution.
视频和图像文本提取方法综述 (Text Extraction in Video and Images: A Review)
TLDR
This paper reviewed text extraction methods from video and images, and classified the course of text extraction into two steps: text region detection and localization, text segmentation.
A fast and automatic algorithm for built-up areas classification in high-resolution SAR images based on geostatistical texture
TLDR
A new scheme for fast and automatic classification of built-up areas is presented, based on geostatistical texture analysis and mainly consists of four parts: semivariogram calculation, best lag distance finding, FCM (Fuzzy C-Mean) clustering, and edge detection.
Color CCD camera calibration in virtual studio
In this paper, we describe some new methods to perform color CCD camera calibration in virtual studio. Our work is based on the pinhole camera model with lens radial distortion. Generally, the
ECE Undergraduate Computer Engineering Education Mode Analysis
The Edward S. Rogers Sr. Department of Electrical and Computer Engineering (ECE) is one of the important departments in the Faculty of Applied Science and Engineering of the University of Toronto.
...
1
2
...