• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.944-953
• /
• 2020

Object detection plays a crucial role in a self-driving system. With the advances of image recognition based on deep convolutional neural networks, researches on object detection have been actively explored. In this paper, we proposed a lightweight model of the mask R-CNN, which has been most widely used for object detection, to efficiently predict location and shape of various objects on the road environment. Furthermore, feature maps are adaptively re-calibrated to improve the detection performance by applying an attention module to the neural network layer that plays different roles within the mask R-CNN. Various experimental results for real driving scenes demonstrate that the proposed method is able to maintain the high detection performance with significantly reduced network parameters.

• Journal of KIISE
• /
• v.44 no.1
• /
• pp.44-50
• /
• 2017

Pedestrian detection, an important component of autonomous driving and driving assistant system, has been extensively studied for many years. In particular, image based pedestrian detection methods such as Hierarchical classifier or HOG and, deep models such as ConvNet are well studied. The evaluation score has increased by the various methods. However, pedestrian detection requires high sensitivity to errors, since small error can lead to life or death problems. Consequently, further reduction in pedestrian detection error rate of autonomous systems is required. We proposed a new method to detect pedestrians and reduce the error rate by using the Faster R-CNN with new developed pedestrian training data sets. Finally, we compared the proposed method with the previous models, in order to show the improvement of our method.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.31 no.4
• /
• pp.351-359
• /
• 2011

In a structure, damage can occur at several scales from micro-cracking to corrosion or loose bolts. This makes the identification of damage difficult with one mode of sensing. Hence, a multi-mode actuated sensing system is proposed based on a self-sensing circuit using a piezoelectric sensor. In the self sensing-based multi-mode actuated sensing, one mode provides a wide frequency-band structural response from the self-sensed impedance measurement and the other mode provides a specific frequency-induced structural wavelet response from the self-sensed guided wave measurement. In this study, an experimental study on the pipeline system is carried out to verify the effectiveness and the robustness of the proposed structural health monitoring approach. Different types of structural damage are artificially inflicted on the pipeline system. To classify the multiple types of structural damage, a supervised learning-based statistical pattern recognition is implemented by composing a two-dimensional space using the damage indices extracted from the impedance and guided wave features. For more systematic damage classification, several control parameters to determine an optimal decision boundary for the supervised learning-based pattern recognition are optimized. Finally, further research issues will be discussed for real-world implementation of the proposed approach.

• Journal of Digital Contents Society
• /
• v.10 no.2
• /
• pp.327-332
• /
• 2009

In this paper, we propose the diagnosis system that can predict pet's state of health for pet lovers lacking a technical knowledge of dog-diseases. The proposed system deduces diseases of dogs from input symptoms by our database constructed with 105 kinds of diseases and symptoms. First, a disease is clustered by ART2, the self-learning method in neural network and secondly, the result values, outputs and the weight values clustered by the algorithm are stored to database. Finally, our system diagnoses the state of health by means of comparing the learned information of diseases with the input vectors of each symptom and the related results of questions on diseases. The correct information of diseases and symptom diagnosing is important to predict the state of health of dogs. Therefore, in this paper, the proposed system can manage symptoms and diseases efficiently by database and ART2. We ask veterinary specialist with the efficiency of our system. As a result, we could confirm the possibility as the auxiliary diagnosis system for dog diseases.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.85-92
• /
• 2023

Recently, interest in artificial intelligence has increased due to the development of artificial intelligence fields such as ChatGPT and self-driving cars. However, there are still many unknown elements in training process of artificial intelligence, so that optimizing the model requires more time and effort than it needs. Therefore, there is a need for a tool or methodology that can analyze the weight changes during the training process of artificial intelligence and help out understatnding those changes. In this research, I propose a visualization system which helps people to understand the accumulated weight changes. The system calculates the weights for each training period to accumulates weight changes and stores accumulated weight changes to plot them in 3D space. This research will allow us to explore different aspect of artificial intelligence learning process, such as understanding how the model get trained and providing us an indicator on which hyperparameters should be changed for better performance. These attempts are expected to explore better in artificial intelligence learning process that is still considered as unknown and contribute to the development and application of artificial intelligence models.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.178-188
• /
• 2020

This paper proposes a lane recognition CNN network using split-attention network as a backbone to extract feature. Split-attention is a method of assigning weight to each channel of a feature map in the CNN feature extraction process; it can reliably extract the features of an image during the rapidly changing driving environment of a vehicle. The proposed deep neural networks in this paper were trained and evaluated using the Tusimple data set. The change in performance according to the number of layers of the backbone network was compared and analyzed. A result comparable to the latest research was obtained with an accuracy of up to 96.26, and FN showed the best result. Therefore, even in the driving environment of an actual vehicle, stable lane recognition is possible without misrecognition using the model proposed in this study.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.635-642
• /
• 2002

There is a rapidly growing demand for the intellectualization of information technology. Especially, in the area of KDD (Knowledge Discovery in Database) which should make an optimal decision of finding knowledge from a large amount of data, the demand is enormous. A large volume of Knowledge Base should be efficiently managed for a more intellectual choice. This study is proposing a Hybrid SOM for an efficient search and renewal of knowledge base, which combines a self-study nerve network, Self-Organization Map with a probable distribution theory in order to get knowledge needed for decision-making management from the Knowledge Base. The efficient knowledge base management through this proposed method is carried out by a stimulation test. This test confirmed that the proposed Hybrid SOM can manage with efficiency Knowledge Base.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.1-9
• /
• 2019

The image obtained from systems such as autonomous driving cars or fire-fighting robots often suffer from several degradation such as noise, motion blur, and compression artifact due to multiple factor. It is difficult to apply image recognition to these degraded images, then the image restoration is essential. However, these systems cannot recognize what kind of degradation and thus there are difficulty restoring the images. In this paper, we propose the deep neural network, which restore natural images from images degraded in several ways such as noise, blur and JPEG compression in situations where the distortion applied to images is not recognized. We adopt the channel attention modules and skip connections in the proposed method, which makes the network focus on valuable information to image restoration. The proposed method is simpler to train than other methods, and experimental results show that the proposed method outperforms existing state-of-the-art methods.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.66-73
• /
• 2019

Recently, object recognition technology using computer vision has attracted attention as a technology to replace sensor-based object recognition technology. It is often difficult to commercialize sensor-based object recognition technology because such approach requires an expensive sensor. On the other hand, object recognition technology using computer vision may replace sensors with inexpensive cameras. Moreover, Real-time recognition is viable due to the growth of CNN, which is actively introduced into other fields such as IoT and autonomous vehicles. Because object recognition model applications demand expert knowledge on deep learning to select and learn the model, such method, however, is challenging for non-experts to use it. Therefore, in this paper, we analyze the structure of deep - learning - based object recognition models, and propose a platform that can automatically select a deep - running object recognition model based on a user 's desired condition. We also present the reason we need to select statistics-based object recognition model through conducted experiments on different models.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.