• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.137-140
• /
• 1996

Finding line segments in an intensity image has been one of the most fundamental issues in computer vision. In complex scenes, it is hard to detect the locations of point features. Line features are more robust in providing greater positional accuracy. In this paper we present a robust "line features extraction" algorithm which extracts line feature in a single pass without using any assumptions and constraints. Our algorithm consists of five steps: (1) edge scanning, (2) edge normalization, (3) line-blob extraction, (4) line-feature computation, and (5) line linking. By using edge scanning, the computational complexity due to too many edge pixels is drastically reduced. Edge normalization improves the local quantization error induced from the gradient space partitioning and minimizes perturbations on edge orientation. We also analyze the effects of edge processing, and the least squares-based method and the principal axis-based method on the computation of line orientation. We show its efficiency with some real images.al images.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.45-48
• /
• 2015

오늘날 하드웨어의 발전으로 인해 영상 해상도는 FHD를 넘어 4K UHD 이상의 영상 해상도가 사용화되고 있다. 하지만 Edge Map을 만들기 위해 일반적으로 사용하는 함수들은 Convolution 함수 일종으로서 영상의 해상도가 높을수록 더 많은 Complexity를 요구한다. 또한 현재 주요 영상 압축 기술인 JPEG, H.264/AVC High efficiency video coding(HEVC)같은 기법들은 자연 영상을 중점으로 개발되어 있어 Edge map 압축에 있어 자연 영상만큼의 효율을 보여주지 못하고 있다. 본 논문은 원 영상을 Down Scaling한 뒤 이미지를 다시 원래 사이즈로 Up Scaling하여 두 영상의 차를 이용한 Edge Map을 생성하는 새로운 방법을 소개한다. 생성된 Edge Map의 특성인 Histogram 값의 분포가 0을 중심으로 Gaussian 분포를 가지는 것을 이용한 Zero Based 코덱을 제안한다. 제안된 알고리즘을 이용하여 고 해상도 영상에서도 빠르게 Edge Map을 생성하고 제안한 코덱을 통해 해당 Edge map을 압축한 결과 다른 압축 기술보다 더 뛰어난 성능을 보여주었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.1
• /
• pp.17-21
• /
• 2011

This paper presents a real- time detection of on-road succeeding vehicles based on low level edge features and a boosted cascade of Haar-like features. At first, the candidate vehicle location in an image is found by low level horizontal edge and symmetry characteristic of vehicle. Then a boosted cascade of the Haar-like features is applied to the initial hypothesized vehicle location to extract the refined vehicle location. The initial hypothesis generation using simple edge features speeds up the whole detection process and the application of a trained cascade on the hypothesized location increases the accuracy of the detection process. Experimental results on real world road scenario with processing speed of up to 27 frames per second for $720{\times}480$ pixel images are presented.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1268-1271
• /
• 2003

In the edge detection of RS image, the useful detail losing and the spurious edge often appear. To solve the problem, we use the dyadic wavelet to detect the edge of surface features by combining the edge detecting with the multi-resolution analyzing of the wavelet transform. Via the dyadic wavelet decomposing, we obtain the RS image of a certain appropriate scale, and figure out the edge data of the plane and the upright directions respectively, then work out the grads vector module of the surface features, at last by tracing them we get the edge data of the object therefore build the RS image which obtains the checked edge. This method can depress the effect of noise and examine exactly the edge data of the object by rule and line. With an experiment of a RS image which obtains an airport, we certificate the feasibility of the application of dyadic wavelet in the object edge detection.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.1
• /
• pp.125-133
• /
• 2004

In this paper, we present a new method that combines the characteristics of edge in-formation and second-order neural networks for the classification of structural textures. The edges of a texture are extracted using an edge detection approach. From this edge information, classification features called second-order features are obtained. These features are fed into a second-order neural network for training and subsequent classification. It will be shown that the main disadvantage of using structural methods in texture classifications, namely, the difficulty of the extraction of texels, is overcome by the proposed method.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.2
• /
• pp.64.2-64.2
• /
• 2014

Interacting galaxy pairs are important for study of galaxy evolution. We selected 8,542 interacting galaxy pairs out of 593,514 KIAS-VAGC galaxy sample with 0.02 < z < 0.047 and r_mag <17.6. We then classified by their interacting features into 6 types by visual inspection. We focused on two types whose spiral tidal features extend to the center of early type galaxy (ETG) or to the edge of ETG. We compared galactic parameters of these two types with those of entire 8,542 pairs as well as between the two types. Preliminary result shows both types are very close pairs (projected distance ~ 20 kpc). Spiral galaxies in the center type are more massive but less bright than those in edge type. ETGs in the edge type are brighter but not more massive than those in the center type. The center type has a mass ratio 3.4 times greater than the edge type, but the edge type has a higher angular momentum than the center type.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.25 no.5
• /
• pp.285-290
• /
• 2013

Both full linear and shallow water edge waves are compared to get a better understanding of edge wave behavior. By using method of separation of variables, we are able to get solution of full linear edge wave presented by Ursell (1952) without derivation. The shallow water edge waves show dispersive features despite being derived from shallow water equations. When bottom slope is mild enough, shallow water edge wave tends to linear edge wave and has some advantages of manipulation. Solution of edge wave generated by a moving landslide of Gaussian shape is constructed by an expansion of shallow water normal modes. Numerical results are presented and discussed on their main features.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.

• International Journal of Automotive Technology
• /
• v.6 no.2
• /
• pp.171-181
• /
• 2005

The purpose of this paper is two-fold: 1) A novel algorithm in order to extract lane-related information from road images is presented; 2) Design specifications of an image processing onboard unit capable of extracting lane­related information in real-time is also presented. Obtaining precise information from road images requires many features due to the effects of noise that eventually leads to long processing time. By exploiting a FPGA and DSP, we solve the problem of real-time processing. Due to the fact that image processing of road images relies largely on edge features, the FPGA is adopted in the hardware design. The schematic configuration of the FPGA is optimized in order to perform 3 $\times$ 3 Sobel edge extraction. The DSP carries out high-level image processing of recognition, decision, estimation, etc. The proposed algorithm uses edge features to define an Edge Distribution Function (EDF), which is a histogram of edge magnitude with respect to the edge orientation angle. The EDF enables the edge-related information and lane-related to be connected. The performance of the proposed system is verified through the extraction of lane-related information. The experimental results show the robustness of the proposed algorithm and a processing speed of more than 25 frames per second, which is considered quite successful.