• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.1
• /
• pp.1-6
• /
• 2018

In this paper, we propose the method to eliminate repetitive processes for key-point detection on multi-scale image space. The proposed method detects key-points from the original image, and select a good key-points using the cluster filters, and create the key-point clusters. And it select reference objects by using direction angles of the key-point clusters, predict the scale of the original image by using the distributed distance ratio. It transform the scale of the reference image, and apply the detection of key-points to the transformed reference image. In the results of the experiment, the proposed method can be found to improve the key-points detection time by 75 % and 71 % compared to SIFT method and scaled ORB method using the multi-scale images.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.1
• /
• pp.1-11
• /
• 2023

Deep-learning-based image segmentation is one of the most widely employed lane detection approaches, and it requires a post-process for extracting the key points on the lanes. A general approach for key-point extraction is using a fixed threshold defined by a user. However, finding the best threshold is a manual process requiring much effort, and the best one can differ depending on the target data set (or an image). We propose a novel key-point extraction algorithm that automatically adapts to the target image without any manual threshold setting. In our adaptive key-point extraction algorithm, we propose a line-level normalization method to distinguish the lane region from the background clearly. Then, we extract a representative key point for each lane at a line (row of an image) using a kernel density estimation. To check the benefits of our approach, we applied our method to two lane-detection data sets, including TuSimple and CULane. As a result, our method achieved up to 1.80%p and 17.27% better results than using a fixed threshold in the perspectives of accuracy and distance error between the ground truth key-point and the predicted point.

• Journal of Drive and Control
• /
• v.21 no.2
• /
• pp.65-71
• /
• 2024

In this study, we suggested a key-point detection method for robot harvesting of oriental melon. Our suggested method could be used to detect the detachment part and major composition of oriental melon. We defined four points (harvesting point, calyx, center, bottom) based on tomato with characteristics similar to those of oriental melon. The evaluation of estimated key-points was conducted by pixel error and PDK (percentage of detected key-point) index. Results showed that the average pixel error was 18.26 ± 16.62 for the x coordinate and 17.74 ± 18.07 for the y coordinate. Considering the resolution of raw images, these pixel errors were not expected to have a serious impact. The PDK score was found to be 89.5% PDK@0.5 on average. It was possible to estimate oriental melon specific key-point. As a result of this research, we believe that the proposed method can contribute to the application of harvesting robot system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.11
• /
• pp.2478-2484
• /
• 2010

In this paper, real-time detection methods for Panorama system Key-Points offers. A recent study in PANORAMA system real-time area navigation or DVR to apply such research has recently been actively. The detection of the Key-Point is the most important elements that make up a Panorama system. Not affected by contrast, scale, Orientation must be detected Key-Point. Existing research methods are difficult to use in real-time Because it takes a lot of computation time. Therefore, this paper propose BLOG(BitRate Laplacian Of Gaussian)method for faster time Key-Point Detecting and Through various experiments to detect the Speed, Computation, detection performance is compared against.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.361-369
• /
• 2022

Unsafe actions and behaviors of workers cause most accidents at construction sites. Nowadays, occupational safety is a top priority at construction sites. However, this problem often requires money and effort from investors or construction owners. Therefore, decreasing the accidents rates of workers and saving monitoring costs for contractors is necessary at construction sites. This study proposes an unsafe behavior detection method based on a skeleton model to classify three common unsafe behaviors on the scaffold: climbing, jumping, and running. First, the OpenPose method is used to obtain the workers' key points. Second, all skeleton datasets are aggregated from the temporary size. Third, the key point dataset becomes the input of the action classification model. The method is effective, with an accuracy rate of 89.6% precision and 90.5% recall of unsafe actions correctly detected in the experiment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4355-4374
• /
• 2018

Crowd escape event detection has become one of the hottest problems in intelligent surveillance filed. When the 'escape event' occurs, pedestrians will escape in a disordered way with different velocities and directions. Based on these characteristics, this paper proposes a Direction-Collectiveness Model to detect escape event in crowd scenes. First, we extract a set of trajectories from video sequences by using generalized Kanade-Lucas-Tomasi key point tracker (gKLT). Second, a Direction-Collectiveness Model is built based on the randomness of velocity and orientation calculated from the trajectories to express the movement of the crowd. This model can describe the movement of the crowd adequately. To obtain a generalized crowd escape event detector, we adopt an adaptive threshold according to the Direction-Collectiveness index. Experiments conducted on two widely used datasets demonstrate that the proposed model can detect the escape events more effectively from dense crowd.

• International journal of advanced smart convergence
• /
• v.9 no.3
• /
• pp.192-198
• /
• 2020

The 3D point cloud is a key technology of object detection for virtual reality and augmented reality. In order to apply various areas of object detection, it is necessary to obtain 3D information and even color information more easily. In general, to generate a 3D point cloud, it is acquired using an expensive scanner device. However, 3D and characteristic information such as RGB and depth can be easily obtained in a mobile device. GNN (Graph Neural Network) can be used for object detection based on these characteristics. In this paper, we have generated RGB and RGBD by detecting basic information and characteristic information from the KITTI dataset, which is often used in 3D point cloud object detection. We have generated RGB-GNN with i-GNN, which is the most widely used LiDAR characteristic information, and color information characteristics that can be obtained from mobile devices. We compared and analyzed object detection accuracy using RGBD-GNN, which characterizes color and depth information.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.91-96
• /
• 2006

Presently, cycle-slip detection is done between adjacent two points in many cycle-slip methods. Inherently, it is simple wavelet analysis. A new idea is put forward that the number of difference point can adjust by a parameter factor; we study this method to smooth raw data and detect cycle-slip with wavelet analysis. Taking CHAMP satellite data for example, we get some significant conclusions. It is showed that it is valid to detect cycle-slip in GPS phase measurement based on this wavelet function, and it is helpful to improve the precision of GPS data pre-processing and positioning.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.141-149
• /
• 2023

Repacked mobile apps constitute about 78% of all malware of Android, and it greatly affects the technical ecosystem of Android. Although many methods exist for repacked app detection, most of them suffer from performance issues. In this manuscript, a novel method using the Constant Key Point Selection and Limited Binary Pattern (CKPS: LBP) Feature extraction-based Hashing is proposed for the identification of repacked android applications through the visual similarity, which is a notable feature of repacked applications. The results from the experiment prove that the proposed method can effectively detect the apps that are similar visually even that are even under the double fold content manipulations. From the experimental analysis, it proved that the proposed CKPS: LBP method has a better efficiency of detecting 1354 similar applications from a repository of 95124 applications and also the computational time was 0.91 seconds within which a user could get the decision of whether the app repacked. The overall efficiency of the proposed algorithm is 41% greater than the average of other methods, and the time complexity is found to have been reduced by 31%. The collision probability of the Hashes was 41% better than the average value of the other state of the art methods.