• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.1134-1142
• /
• 2019

Detection of double compression is one of the most efficient ways of remarking the validity of videos. Many methods have been introduced to detect HEVC double compression with different coding parameters. However, HEVC double compression detection under the same coding environments is still a challenging task in video forensic. In this paper, we introduce a novel method based on the frame partitioning information in intra prediction mode for detecting double compression in with the same coding environments. We propose to extract statistical feature and Deep Convolution Neural Network (DCNN) feature from the difference of partitioning picture including Coding Unit (CU) and Transform Unit (TU) information. Finally, a softmax layer is integrated to perform the classification of the videos into single and double compression by combing the statistical and the DCNN features. Experimental results show the effectiveness of the statistical and the DCNN features with an average accuracy of 87.5% for WVGA and 84.1% for HD dataset.

• Steel and Composite Structures
• /
• v.46 no.2
• /
• pp.153-173
• /
• 2023

Rectangular concrete-filled steel tubular (RCFST) column, a type of concrete-filled steel tubular (CFST), is widely used in compression members of structures because of its advantages. This paper proposes a robust machine learning-based framework for predicting the ultimate compressive strength of RCFST columns under both concentric and eccentric loading. The gradient boosting neural network (GBNN), an efficient and up-to-date ML algorithm, is utilized for developing a predictive model in the proposed framework. A total of 890 experimental data of RCFST columns, which is categorized into two datasets of concentric and eccentric compression, is carefully collected to serve as training and testing purposes. The accuracy of the proposed model is demonstrated by comparing its performance with seven state-of-the-art machine learning methods including decision tree (DT), random forest (RF), support vector machines (SVM), deep learning (DL), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and categorical gradient boosting (CatBoost). Four available design codes, including the European (EC4), American concrete institute (ACI), American institute of steel construction (AISC), and Australian/New Zealand (AS/NZS) are refereed in another comparison. The results demonstrate that the proposed GBNN method is a robust and powerful approach to obtain the ultimate strength of RCFST columns.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.738-747
• /
• 2021

Today, with the improvement of deep learning technology, computer vision areas such as image classification, object detection, object segmentation, and object tracking have shown remarkable improvements. Various applications such as intelligent surveillance, robots, Internet of Things, and autonomous vehicles in combination with deep learning technology are being applied to actual industries. Accordingly, the requirement of an efficient compression method for video data is necessary for machine consumption as well as for human consumption. In this paper, we propose an object-based compression of thermal infrared images for machine vision. The input image is divided into object and background parts based on the object detection results to achieve efficient image compression and high neural network performance. The separated images are encoded in different compression ratios. The experimental result shows that the proposed method has superior compression efficiency with a maximum BD-rate value of -19.83% to the whole image compression done with VVC.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1188-1203
• /
• 2020

The human expression contains a lot of information that can be used to detect complex conditions such as pain and fatigue. After deep learning became the mainstream method, the traditional feature extraction method no longer has advantages. However, in order to achieve higher accuracy, researchers continue to stack the number of layers of the neural network, which makes the real-time performance of the model weak. Therefore, this paper proposed an expression recognition framework based on densely concatenated convolutional neural networks to balance accuracy and latency and apply it to humanoid robots. The techniques of feature reuse and parameter compression in the framework improved the learning ability of the model and greatly reduced the parameters. Experiments showed that the proposed model can reduce tens of times the parameters at the expense of little accuracy.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.821-824
• /
• 2022

최근 딥러닝(Deep Learning) 기술이 다양한 분야에서 활용되고 있으며, 사전 학습된 딥러닝 모델에 대한 압축과 전송 방안에 관한 연구 또한 활발히 진행되고 있다. 이와 관련하여, 국제 표준화 기구인 ISO/IEC 산하 MPEG(Moving Picture Expert Group)에서는 인공신경망 모델을 다양한 딥러닝 프레임워크(Deep Learning Framework)에서 상호운용 가능한 포맷으로 압축 표현할 수 있는 NNC(Compression of Neural Network for Multimedia Content Description nd Analysis) 표준화를 진행하고 있다. 압축된 딥러닝 모델의 데이터를 효과적으로 저장하여 전송 및 사용하기 위해서는 ISOBMFF(ISO based Media File Format) 캡슐화 과정이 필요하다. 본 논문에서는 MPEG의 NNC 표준에 따라 사전 학습된 딥러닝 모델을 압축한 후 이를 통해 생성된 비트스트림(bitstream)을 ISOBMFF로 캡슐화하기 위한 기술을 제안 및 실험한다. 또한, 실험에 대한 검증을 위하여 생성된 ISOBMFF 데이터를 비트스트림으로 복원한 뒤 복호화하여 입력 비트스트림과 차이가 없음을 확인한다.

• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.22-25
• /
• 2020

본 논문에서는 큰 크기의 심층 신경망을 압축하기위해 네트워크 수준의 가중치 공유방법인 Global Weight 패러다임을 최초로 제시한다. 기존의 가중치 공유방법은 계층별로 가중치를 공유하는 것이 대부분이었다. Global Weight 는 기존 방법과 달리 전체 네트워크에서 가중치를 공유하는 효율적인 방법이다. 우리는 Global Weight 를 사용하여 학습되는 새로운 컨볼루션 연산인 Global Weight Convolution(GWConv)연산과 GWConv를 적용한 Global Weight Networks(GWNet)을 제안한다. CIFAR10 데이터셋에서 실험한 결과 2.18 배 압축에서 85.64%, 3.41 배 압축에서 85.46%의 정확도를 보였다. Global Weight 패러다임은 가중치 공유가 궁극적으로 풀고자 했던 중복되는 가중치를 최소화하는 획기적인 방법이며, 추후 심도 있는 연구가 수행될 수 있음을 시사한다.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.472-484
• /
• 2019

This paper proposes a time-domain sound event detection algorithm using DNN (Deep Neural Network). In this system, time domain sound waveform data which is not converted into the frequency domain is used as input to the DNN. The overall structure uses CRNN structure, and GLU, ResNet, and Squeeze-and-excitation blocks are applied. And proposed structure uses structure that considers features extracted from several layers together. In addition, under the assumption that it is practically difficult to obtain training data with strong labels, this study conducted training using a small number of weakly labeled training data and a large number of unlabeled training data. To efficiently use a small number of training data, the training data applied data augmentation methods such as time stretching, pitch change, DRC (dynamic range compression), and block mixing. Unlabeled data was supplemented with insufficient training data by attaching a pseudo-label. In the case of using the neural network and the data augmentation method proposed in this paper, the sound event detection performance is improved by about 6 %(based on the f-score), compared with the case where the neural network of the CRNN structure is used by training in the conventional method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.64-67
• /
• 2020

최근 다양한 분야에서 딥 러닝 기반의 많은 연구가 진행되고 있으며 이에 따라 딥 러닝 모델의 경량화를 통해 제한된 메모리를 가진 하드웨어에 올릴 수 있는 경량화 된 딥 뉴럴 네트워크(DNN)를 개발하는 연구도 활발해졌다. 이에 본 논문은 주파수 영역에서의 군집화 기반 계층별 딥 뉴럴 네트워크 압축을 제안한다. 이산 코사인 변환, 양자화, 군집화, 적응적 엔트로피 코딩 과정을 각 모델의 계층에 순차적으로 적용하여 DNN이 차지하는 메모리를 줄인다. 제안한 알고리즘을 통해 VGG16을 손실률은 1% 미만의 손실에서 전체 가중치를 3.98%까지 압축, 약 25배가량 경량화 할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.675-679
• /
• 2020

최근 이미지 분류의 성능 향상을 위해 깊은 레이어와 넓은 채널을 가지는 모델들이 제안되어져 왔다. 높은 분류 정확도를 보이는 모델을 제안하는 것은 과한 컴퓨팅 파워와 계산시간을 요구한다. 본 논문에서는 이미지 분류 기법에서 사용되는 딥 뉴럴 네트워크 모델에 있어, 프루닝 방법을 통해 상대적으로 불필요한 가중치를 제거함과 동시에 분류 정확도 하락을 최소로 하는 동적 필터 프루닝 방법을 제시한다. 원샷 프루닝 기법, 정적 필터 프루닝 기법과 다르게 제거된 가중치에 대해서 소생 기회를 제공함으로써 더 좋은 성능을 보인다. 또한, 재학습이 필요하지 않기 때문에 빠른 계산 속도와 적은 컴퓨팅 파워를 보장한다. ResNet20 에서 CIFAR10 데이터셋에 대하여 실험한 결과 약 50%의 압축률에도 88.74%의 분류 정확도를 보였다.