• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.2
• /
• pp.439-446
• /
• 2011

In this paper, we proposed and implemented a dedicated hardware for Huffman coding which is a method of entropy coding to use compressing multimedia data with video coding. The proposed Huffman codec consists Huffman encoder and decoder. The Huffman encoder converts symbols to Huffman codes using look-up table. The Huffman code which has a variable length is packetized to a data format with 32 bits in data packeting block and then sequentially output in unit of a frame. The Huffman decoder converts serial bitstream to original symbols without buffering using FSM(finite state machine) which has a tree structure. The proposed hardware has a flexible operational property to program encoding and decoding hardware, so it can operate various Huffman coding. The implemented hardware was implemented in Cyclone III FPGA of Altera Inc., and it uses 3725 LUTs in the operational frequency of 365MHz

• Electronics and Telecommunications Trends
• /
• v.35 no.7
• /
• pp.23-35
• /
• 2020

In this paper, we introduce ETRI AI Strategy #3, "Leading Future Technologies of Network, Media, and Content." Its first goal is "to innovate AI service technology to overcome the current limitations of AI technologies." Artificial intelligence (AI) services, such as self-driving cars and robots, are combinations of computing, network, AI algorithms, and other technologies. To develop AI services, we need to develop different types of network, media coding, and content creation technologies. Moreover, AI technologies are adopted in ICT technologies. Self-planning and self-managing networks and automatic content creation technologies using AI are being developed. This paper introduces the two directions of ETRI's ICT technology development plan for AI: ICT for AI and ICT by AI. The area of ICT for AI has only recently begun to develop. ETRI, the ICT leader, hopes to have opportunities for leadership in the second wave of AI services.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.180-182
• /
• 2020

최근 IoT 기술이 대중화됨에 따라 커넥티드 카, 스마트 시티와 같은 machine-to-machine 기술의 활용 분야가 다양화되고 있다. 이에 따라, 기계 지향 비디오 처리 및 부호화 기술에 대한 연구분야에 산업계와 학계의 관심 역시 집중되고 있다. 국제 표준화 단체인 MPEG은 이러한 추세를 반영하여 기존 비디오 부호화 표준을 개선할 새로운 표준을 수립하기 위해 Video Coding for Machines (VCM) 그룹을 구성하여 기계 소비를 대상으로 하는 비디오 표준의 표준화를 진행하고 있다. 이에 본 논문에서는 VCM이 기계 소비를 대상으로 진행하고 있는 특징맵 부호화의 부호화 효율을 개선하기 위해 특징맵을 시간적, 공간적으로 재정렬하는 방법을 제안한다. 실험 결과, 제안 방법이 CityScapes의 검증 세트 내 일부 이미지에 대해 시간적 재정렬을 수행한 결과 random access 조건에서 최대 1.48%의 부호화 효율이 향상됨이 확인되었다.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.4
• /
• pp.31-43
• /
• 1999

The main goal of this paper is to design a high performance SVP(Stack based Video Processor) for network applications. The SVP is a comprehensive scheme; 'better' in the sense that it is an optimal selection of previously proposed enhancements of a stack machine and a video processor. This can process effectively object-based video data using a S-RISC(Stack-based Reduced Instruction Set Computer) with a semi -general-purpose architecture having a stack buffer for OOP(Object-Oriented Programming) with many small procedures at running programs. And it includes a vector processor that can improve the MPEG coding speed. The vector processor in the SVP can execute advanced mode motion compensation, motion prediction by half pixel and SA-DCT(Shape Adaptive-Discrete Cosine Transform) of MPEG-4. Absolutors and halfers in the vector processor make this architecture extensive to a encoder. We also designed a VLSI stack-oriented video processor using the proposed architecture of stack-oriented video decoding. It was designed with O.5$\mu\textrm{m}$ 3LM standard-cell technology, and has 110K logic gates and 12 Kbits SRAM internal buffer. The operating frequency is 50MHz. This executes algorithms of video decoding for QCIF 15fps(frame per second), maximum rate of VLBV(Very Low Bitrate Video) in MPEG-4.

• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.30-32
• /
• 2021

최근 머신비전 임무(machine vision task)를 위해 기계에 소비되는 비디오가 증가하면서 MPEG 은 기계를 위한 비디오 부호화 표준으로 VCM(Video Coding for Machine) 표준화 진행하고 있다. VCM 은 기계분석 네트워크에 입력되는 비디오 또는 특징(feature)을 부/복호화하여 압축 대비 임무 수행 정확도를 평가한다. 본 논문은 기계분석 네트워크에서 추출한 특징 데이터를 기존의 비디오 코덱을 사용하여 부/복호화를 진행할 때, 각 채널의 특징맵을 SAD(Sum of Absolute Difference) 기반으로 재배열하는 방법을 제안한다. 제안기법은 VCM 의 기준성능(anchor)에는 미치지 못하지만, 채널 재배열하지 않은 특징을 비디오 코덱으로 부호화 할 때 보다 개선된 성능을 보인다.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.383-394
• /
• 2018

In this paper, we investigate image and video compression techniques based on deep learning which are actively studied recently. The deep learning based image compression technique inputs an image to be compressed in the deep neural network and extracts the latent vector recurrently or all at once and encodes it. In order to increase the image compression efficiency, the neural network is learned so that the encoded latent vector can be expressed with fewer bits while the quality of the reconstructed image is enhanced. These techniques can produce images of superior quality, especially at low bit rates compared to conventional image compression techniques. On the other hand, deep learning based video compression technology takes an approach to improve performance of the coding tools employed for existing video codecs rather than directly input and process the video to be compressed. The deep neural network technologies introduced in this paper replace the in-loop filter of the latest video codec or are used as an additional post-processing filter to improve the compression efficiency by improving the quality of the reconstructed image. Likewise, deep neural network techniques applied to intra prediction and encoding are used together with the existing intra prediction tool to improve the compression efficiency by increasing the prediction accuracy or adding a new intra coding process.

• Journal of Broadcast Engineering
• /
• v.25 no.7
• /
• pp.1081-1094
• /
• 2020

With the recent development of deep learning, most computer vision-related tasks are being solved with deep learning-based network technologies such as CNN and RNN. Computer vision tasks such as object detection or object segmentation use intermediate features extracted from the same backbone such as Resnet or FPN for training and inference for object detection and segmentation. In this paper, an experiment was conducted to find out the compression efficiency and the effect of encoding on task inference performance when the features extracted in the intermediate stage of CNN are encoded. The feature map that combines the features of 256 channels into one image and the original image were encoded in HEVC to compare and analyze the inference performance for object detection and segmentation. Since the intermediate feature map encodes the five levels of feature maps (P2 to P6), the image size and resolution are increased compared to the original image. However, when the degree of compression is weakened, the use of feature maps yields similar or better inference results to the inference performance of the original image.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.318-331
• /
• 2022

With the recent development of hardware computing devices and software based frameworks, machine tasks using deep learning networks are expected to be utilized in various industrial fields and personal IoT devices. However, in order to overcome the limitations of high cost device for utilizing the deep learning network and that the user may not receive the results requested when only the machine task results are transmitted from the server, Collaborative Intelligence (CI) proposed the transmission of feature maps as a solution. In this paper, an efficient compression method for feature maps with vast data sizes to support the CI paradigm was analyzed and presented through experiments. This method increases redundancy by applying feature map reordering to improve compression efficiency in traditional video codecs, and proposes a feature map method that improves compression efficiency and maintains the performance of machine tasks by simultaneously utilizing image compression format and video compression format. As a result of the experiment, the proposed method shows 14.29% gain in BD-rate of BPP and mAP compared to the feature compression anchor of MPEG-VCM.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.886-895
• /
• 2018

In this paper, we introduce a technique to detect the video forgery by using the regularity that occurs in the video compression process. The proposed method uses the hierarchical regularity lost by the video double compression and the frame deletion. In order to extract such irregularities, the depth information of CU and TU, which are basic units of HEVC, is used. For improving performance, we make a depth map of CU and TU using local information, and then create input data by grouping them in GoP units. We made a decision whether or not the video is double-compressed and forged by using a general three-dimensional convolutional neural network. Experimental results show that it is more effective to detect whether or not the video is forged compared with the results using the existing machine learning algorithm.