• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.283-294
• /
• 2022

The feature map used in the network for deep learning generally has larger data than the image and a higher compression rate than the image compression rate is required to transmit the feature map. This paper proposes a method for transmitting a pyramid feature map with high compression rate, which is used in a network with an FPN structure that has robustness to object size in deep learning-based image processing. In order to efficiently compress the pyramid feature map, this paper proposes a structure that predicts a pyramid feature map of a level that is not transmitted with pyramid feature map of some levels that transmitted through the proposed prediction network to efficiently compress the pyramid feature map and restores compression damage through the proposed reconstruction network. Suggested mAP, the performance of object detection for the COCO data set 2017 Train images of the proposed method, showed a performance improvement of 31.25% in BD-rate compared to the result of compressing the feature map through VTM12.0 in the rate-precision graph, and compared to the method of performing compression through PCA and DeepCABAC, the BD-rate improved by 57.79%.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.1
• /
• pp.64-75
• /
• 2010

This study introduces a complete feature map building method of sonar sensors for mobile robots. This method enhances the reality of feature maps by extracting even circle features as well as line and point features from sonar data. Edge features are, moreover, generated by combining line features close to circle features extracted around comer sites. The uncertainties of the specular reflection phenomenon and wide beam width of sonar data can be, therefore, reduced through this map building method. The experimental results demonstrate a practical validity of the proposed method in those environments.

• Journal of Mechanical Science and Technology
• /
• v.19 no.2
• /
• pp.558-566
• /
• 2005

We propose a feature-based multi-resolution representation of B-rep solid models using history-based Boolean operations based on the merge-and-select algorithm. Because union and subtraction are commutative in the history-based Boolean operations, the integrity of the models at various levels of detail (LOD) is guaranteed for the reordered features regardless of whether the features are subtractive or additive. The multi-resolution solid representation proposed in this paper includes a non-manifold topological merged-set model of all feature primitives as well as a feature-modeling tree reordered consistently with a given LOD criterion. As a result, a B-rep solid model for a given LOD can be provided quickly, because the boundary of the model is evaluated without any geometric calculation and extracted from the merged set by selecting the entities contributing to the LOD model shape.

• Journal of information and communication convergence engineering
• /
• v.5 no.3
• /
• pp.245-248
• /
• 2007

In this paper, we research the content-based analysis and classification according to the composition of the feature parameter data base for the audio data to implement the audio data index and searching system. Audio data is classified to the primitive various auditory types. We described the analysis and feature extraction method for the feature parameters available to the audio data classification. And we compose the feature parameters data base in the index group unit, then compare and analyze the audio data centering the including level around and index criterion into the audio categories. Based on this result, we compose feature vectors of audio data according to the classification categories, and simulate to classify using discrimination function.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.786-799
• /
• 2021

Road damage detection is important for road maintenance. With the development of deep learning, more and more road damage detection methods have been proposed, such as Fast R-CNN, Faster R-CNN, Mask R-CNN and RetinaNet. However, because shallow and deep layers cannot be extracted at the same time, the existing methods do not perform well in detecting objects with fewer samples. In addition, these methods cannot obtain a highly accurate detecting bounding box. This paper presents a Multi-level Feature Pyramids method based on M2det. Because the feature layer has multi-scale and multi-level architecture, the feature layer containing more information and obvious features can be extracted. Moreover, an attention mechanism is used to improve the accuracy of local boundary boxes in the dataset. Experimental results show that the proposed method is better than the current state-of-the-art methods.

• Journal of Mechanical Science and Technology
• /
• v.19 no.2
• /
• pp.549-557
• /
• 2005

The requirements of multi-resolution models of feature-based solids, which represent an object at many levels of feature detail, are increasing for engineering purposes, such as analysis, network-based collaborative design, virtual prototyping and manufacturing. To provide multi-resolution models for various applications, it is essential to generate adequate solid models at varying levels of detail (LOD) after feature rearrangement, based on the LOD criteria. However, the non-commutative property of the union and subtraction Boolean operations is a severe obstacle to arbitrary feature rearrangement. To solve this problem we propose history-based Boolean operations that satisfy the commutative law between union and subtraction operations by considering the history of the Boolean operations. Because these operations guarantee the same resulting shape as the original and reasonable shapes at the intermediate LODs for an arbitrary rearrangement of its features, various LOD criteria can be applied for multi-resolution modeling in different applications.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.85-92
• /
• 2019

In this paper, we propose a efficient feature point extraction method that can solve the problem of performance degradation by introducing a preprocessing process when extracting feature points by utilizing the characteristics of 360-degree realistic media. 360-degree realistic media is composed of images produced by two or more cameras and this image combining process is accomplished by extracting feature points at the edges of each image and combining them into one image if they cover the same area. In this production process, however, the stitching process where images are combined into one piece can lead to the distortion of non-seamlessness. Since the realistic media of 4K-class image has higher resolution than that of a general image, the feature point extraction and matching process takes much more time than general media cases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.5132-5148
• /
• 2017

Cyber attacks are evolving commensurate with recent developments in information security technology. Intrusion detection systems collect various types of data from computers and networks to detect security threats and analyze the attack information. The large amount of data examined make the large number of computations and low detection rates problematic. Feature selection is expected to improve the classification performance and provide faster and more cost-effective results. Despite the various feature selection studies conducted for intrusion detection systems, it is difficult to automate feature selection because it is based on the knowledge of security experts. This paper proposes a feature selection technique to overcome the performance problems of intrusion detection systems. Focusing on feature selection, the first phase of the proposed system aims at constructing a feature subset using a sequential forward floating search (SFFS) to downsize the dimension of the variables. The second phase constructs a classification model with the selected feature subset using a random forest classifier (RFC) and evaluates the classification accuracy. Experiments were conducted with the NSL-KDD dataset using SFFS-RF, and the results indicated that feature selection techniques are a necessary preprocessing step to improve the overall system performance in systems that handle large datasets. They also verified that SFFS-RF could be used for data classification. In conclusion, SFFS-RF could be the key to improving the classification model performance in machine learning.

• Korean Journal of Computational Design and Engineering
• /
• v.16 no.3
• /
• pp.178-186
• /
• 2011

Static CAD models are the CAD models that do not have feature information and modeling history. These static models are generated by translating CAD models in a specific CAD system into neutral formats such as STEP and IGES. When a CAD model is translated into a neutral format, its precious feature information such as feature parameters and modeling history is lost. Once the feature information is lost, the advantage of feature based modeling is not valid any longer, and modification for the model is purely dependent on geometric and topological manipulations. However, the capabilities of the existing methods to modify static CAD models are limited, Direct modification methods such as tweaking can only handle the modifications that do not involve topological changes. There was also an approach to modify static CAD model by using volume decomposition. However, this approach was also limited to modifications of protrusion features. To address this problem, we extend the volume decomposition approach to handle not only protrusion features but also depression features in a static CAD model. This method first generates the model that contains the volume of depression feature using the bounding box of a static CAD model. The difference between the model and the bounding box is selectively decomposed into so called the feature volume and the base volume. A modification of depression feature is achieved by manipulating the feature volume of the static CAD model.

• Korean Journal of Computational Design and Engineering
• /
• v.9 no.1
• /
• pp.51-61
• /
• 2004

Mechanical parts are often grouped into part families based on the similarity of their shapes, to support efficient manufacturing process planning and design modification. The 2-part sequence papers present similarity assessment techniques to support part family classification for machined parts. These exploit the multiple feature decompositions obtained by the feature recognition method using convex decomposition. Convex decomposition provides a hierarchical volumetric representation of a part, organized in an outside-in hierarchy. It provides local accessibility directions, which supports abstract and qualitative similarity assessment. It is converted to a Form Feature Decomposition (FFD), which represents a part using form features intrinsic to the shape of the part. This supports abstract and qualitative similarity assessment using positive feature volumes.. FFD is converted to Negative Feature Decomposition (NFD), which represents a part as a base component and negative machining features. This supports a detailed, quantitative similarity assessment technique that measures the similarity between machined parts and associated machining processes implied by two parts' NFDs. Features of the NFD are organized into branch groups to capture the NFD hierarchy and feature interrelations. Branch groups of two parts' NFDs are matched to obtain pairs, and then features within each pair of branch groups are compared, exploiting feature type, size, machining direction, and other information relevant to machining processes. This paper, the second one of the two companion papers, describes the similarity assessment method using NFD.