• Title/Summary/Keyword: 다채널 구현

Search Result 157, Processing Time 0.027 seconds

Multi-channel Video Analysis Based on Deep Learning for Video Surveillance (보안 감시를 위한 심층학습 기반 다채널 영상 분석)

  • Park, Jang-Sik;Wiranegara, Marshall;Son, Geum-Young
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.13 no.6
    • /
    • pp.1263-1268
    • /
    • 2018
  • In this paper, a video analysis is proposed to implement video surveillance system with deep learning object detection and probabilistic data association filter for tracking multiple objects, and suggests its implementation using GPU. The proposed video analysis technique involves object detection and object tracking sequentially. The deep learning network architecture uses ResNet for object detection and applies probabilistic data association filter for multiple objects tracking. The proposed video analysis technique can be used to detect intruders illegally trespassing any restricted area or to count the number of people entering a specified area. As a results of simulations and experiments, 48 channels of videos can be analyzed at a speed of about 27 fps and real-time video analysis is possible through RTSP protocol.

Implementation of CNN Model for Classification of Sitting Posture Based on Multiple Pressure Distribution (다중 압력분포 기반의 착석 자세 분류를 위한 CNN 모델 구현)

  • Seo, Ji-Yun;Noh, Yun-Hong;Jeong, Do-Un
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.21 no.2
    • /
    • pp.73-78
    • /
    • 2020
  • Musculoskeletal disease is often caused by sitting down for long period's time or by bad posture habits. In order to prevent musculoskeletal disease in daily life, it is the most important to correct the bad sitting posture to the right one through real-time monitoring. In this study, to detect the sitting information of user's without any constraints, we propose posture measurement system based on multi-channel pressure sensor and CNN model for classifying sitting posture types. The proposed CNN model can analyze 5 types of sitting postures based on sitting posture information. For the performance assessment of posture classification CNN model through field test, the accuracy, recall, precision, and F1 of the classification results were checked with 10 subjects. As the experiment results, 99.84% of accuracy, 99.6% of recall, 99.6% of precision, and 99.6% of F1 were verified.

Detection of Incivility based on Attention-embedding and multi-channel CNN (어텐션임베딩과 다채널 CNN 기반 반시민성 검출 알고리즘)

  • Park, Youn-Jung;Lee, Se-Young;Keum, Hee-Jo
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.12
    • /
    • pp.1880-1889
    • /
    • 2022
  • The online portal platform provides online news with online comments, but the anonymity of comments causes incivility, and online comments are considered social problems. While there are many foreign language-based incivility detection studies, in-depth research is not being conducted in Korea since there has not been implemented Korean language dataset which is labeled detailed criteria of incivility. In this study, the incivility notation of comments was conducted in a total of 13 items, uncivil words were summarized. Furthermore, Attention algorithm was applied to each comment and summary to extract embedding vectors. 2-d CNN followed at the end to detect incivility in given data. As a result, we showed that the proposed algorithm is useful for anti-citizen detection such as name-calling and offensive tones. This study is expected to contribute to the formation of a healthy online comment culture by detecting uncivil comments which hinder democratic discourse.

A Study on Enhancement of 3D Sound Using Improved HRTFS (개선된 머리전달함수를 이용한 3차원 입체음향 성능 개선 연구)

  • Koo, Kyo-Sik;Cha, Hyung-Tai
    • The Journal of the Acoustical Society of Korea
    • /
    • v.28 no.6
    • /
    • pp.557-565
    • /
    • 2009
  • To perceive the direction and the distance of a sound, we always use a couple of information. Head Related Transfer Function (HRTF) contains the information that sound arrives from a sound source to the ears of the listener, like differences of level, phase and frequency spectrum. For a reproduction system using 2 channels, we apply HRTF to many algorithms which make 3d sound. But it causes a problem to localize a sound source around a certain places which is called the cone-of-confusion. In this paper, we proposed the new algorithm to reduce the confusion of sound image localization. The difference of frequency spectrum and psychoacoustics theory are used to boost the spectral cue among each directions. To confirm the performance of the algorithm, informal listening tests are carried out. As a result, we can make the improved 3d sound in 2 channel system based on a headphone. Also sound quality of improved 3d sound is much better than conventional methods.

Design and Implementation of Multi-channel FFT Processor for MIMO Systems (MIMO 시스템을 위한 다채널 FFT 프로세서의 설계 및 구현)

  • Jung, Yongchul;Cho, Jaechan;Jung, Yunho
    • Journal of Advanced Navigation Technology
    • /
    • v.21 no.6
    • /
    • pp.659-665
    • /
    • 2017
  • In this paper, a low complexity fast Fourier transform(FFT) processor is proposed for multiple input multiple output(MIMO) systems. The IEEE 802.11ac standard has been adopted along with the demand for a system capable of high channel capacity and Gbps transmission in order to utilize various multimedia services using a wireless LAN. The proposed scalable FFT processor can support the variable length of 64, 128, 256, and 512 for 8x8 antenna configuration as specified in IEEE 802.11ac standard with MIMO-OFDM scheme. By reducing the required number of non-trivial multipliers with mixed-radix(MR) and multipath delay commutator(MDC) architecture, the complexity of the proposed FFT processor was dramatically decreased. Implementation results show that the proposed FFT processor can reduced the logic gate count by 50%, compared with the radix-2 SDF FFT processor. Also, compared with the 8-channel MR-2/2/2/4/2/4/2 MDC processor and 8-channel MR-2/2/2/8/8 MDC processor, it is shown that the gate count is reduced by 18% and 17% respectively.

Implementation of pressure monitoring system(PMS) for ship's engine performance analysis(SEPA) based on the web (웹기반 선박엔진 성능분석용 압력모니터링 시스템 구현)

  • Yang, Hyun-Suk;Kwon, Hyuk-Joo;Lee, Sung-Geun
    • Journal of Advanced Marine Engineering and Technology
    • /
    • v.38 no.7
    • /
    • pp.929-935
    • /
    • 2014
  • This paper is study on the pressure monitoring system(PMS) for ship's engine performance analysis( SEPA) based on web, with high speed and accuracy. This system is composed of pressure sensor, monitoring module with multi channel A/D converter, TCP/IP and satellite internet communication system. Existing domestic products measure cylinder pressure when piston of first explosive cylinder reached TDC(the top dead center) point and then measure next cylinder pressure manually each angle divided by a constant rotating interval. But presented system monitors in the local and web computer, using pressure information transmitted from pressure sensor installed on each engine. In this system, it is possible to increase the accuracy of the engine performance analysis because not only each TDC points but cylinder pressures synchronized with the TDC points could be measured in real time, accurately. And therefore, it may be used in a various diagnosis of main engines, such as deviations of each cylinder maximum pressures(Pmax) and the TDC firing positions and combustion conditions.

A Study On the Design of a Floating Point Unit for MPEG-2 AAC Decoder (MPEG-2 AAC 복호기를 위한 부동소수점유닛 설계에 관한 연구)

  • 구대성;김필중;김종빈
    • Journal of the Institute of Electronics Engineers of Korea TE
    • /
    • v.39 no.4
    • /
    • pp.355-355
    • /
    • 2002
  • In this paper, we designed a FPU(floating point unit) that it is very important and requires of high density when digital audio is designed. Almost audio system must support the multi-channel and required for high quality. A floating point arithmetic function in MPEG-2 AAC that implemented by hardware is able to realtime decoding when DSP realization. The reason is that MPEG-2 AAC is compatible to the Audio field of MPEG-4 and afterwards. We designed a FPU by hardware to increase the speed of a floating point unit with much calculation part in the MPEG-2 AAC Decoder. A FPU is composed of a multiplier and an adder. A multiplier used the Radix-4 Booth algorithm and an adder adopted 1's complement method for speed up. A form of a floating point unit has 8bit of exponent part and 24bit of mantissa. It's compatible with the IEEE single precision format and adopted a pipeline architecture to increase the speed of a processor. All of sub blocks are based on ISO/IEC 13818-7 standard. The algorithm is tested by C language and the design does by use of VHDL(VHSIC Hardware Description Language). The maximum operation speed is 23.2MHz and the stable operation speed is 19MHz.

Long-term Monitoring System for Ship's Engine Performance Analysis Based on the Web (선박엔진성능분석용 웹기반 장기모니터링시스템 구현)

  • Kwon, Hyuk-Joo;Yang, Hyun-Suk;Kim, Min-Kwon;Lee, Sung-Geun
    • Journal of Advanced Marine Engineering and Technology
    • /
    • v.39 no.4
    • /
    • pp.483-488
    • /
    • 2015
  • This paper implements a long-term monitoring system (LMS) for ship's engine performance analysis (SEPA) based on the web, for the purpose of the communication speed and engine maintenance. This system is composed of a simulator, monitoring module with a multi channel A/D converter, monitoring computer, network attached storage (NAS), RS485 serial and wireless internet communication system. The existing products monitor the information transmitted from pressure sensors installed in the upper parts of each of engines in the local or web computer, but have a delay in the communication speed and errors in long-term monitoring due to the large volume of sampling pressure data. To improve these problems, the monitoring computer saves the sampling pressure data received from the pressure sensors in NAS, monitors the long-term sampling data generated by the sectional down sampling method on a local computer, and transmits them to the web for long-term monitoring. Because this method has one tenth of the original sampling data, it will use memory with small capacity, save communication cost, monitor the long-term sampling data for 30 days, and as a result, make a great contribution to engine maintenance.

Designing a Wideband Antenna Using Diplexer Matching Network for Tactical Vehicles (다이플렉서 정합구조를 이용한 전술차량형 광대역 안테나 설계)

  • Cho, Ji-Haeng;Dong, Moon-Ho
    • The Journal of Korean Institute of Electromagnetic Engineering and Science
    • /
    • v.29 no.9
    • /
    • pp.661-667
    • /
    • 2018
  • Tactical communication radio systems that employ software defined radios(SDRs) have been developed for achieving high-speed data transmissions and voice communications. Such systems possess multiband and multichannel features, and can potentially replace several existing radio systems. This paper proposes a design for wideband antennas by incorporating a diplexer matching network for tactical vehicles. The proposed antenna design includes two radiators(upper and lower) and a diplexer matching network connected to the end of the feed line such that the LC matching networks are interleaved in the lower radiator and spring mount. By employing the diplexer matching network, the designed antenna can perform wideband impedance matching for the fifty ohm feed line. The designed LC networks aid in varying the effective electrical length of the antenna according to the operation frequency. The primary objective behind adjusting the electrical length is to vary the current distribution above and below the LC networks. The proposed antenna was fabricated and tested in an open site. The obtained evaluation results show that the designed antenna can achieve a relative bandwidth of 190% with a VSWR value of 3.5:1, and can attain good antenna gains over VHF and UHF bands.

A Cooperative Marketing Strategy using Mobile Communications: The New OB Mobile Campaign (모바일 채널을 활용한 협동적인 마케팅 전략: OB 맥주 신제품 모바일 캠페인)

  • Lee, Joong-Yeup;Kim, Beom-Soo;Ahn, Joong-Ho
    • Information Systems Review
    • /
    • v.7 no.1
    • /
    • pp.153-171
    • /
    • 2005
  • As the mobile telecommunications industry in Korea boasts record-high revenue from its businesses, consumers and other industries are looking for new business applications and opportunities using mobile technologies. Many firms are seeking guidelines or business models for an effective use of this new mobile technology in their operations. This paper reviews the characteristics that distinguish mobile marketing, and analyzes marketing approaches which utilize the potential of the new mobile technologies. This paper shows that the new mobile advertising channel is not only complementary to traditional marketing channels, but also delivers benefits for multiple parties involved in mobile marketing. The key success factors in the new OB (Oriental Brewery) marketing campaign include a shortening of the stages in the AIDMA model and a broadening of customer contact points by exposing the brand through well-coordinated marketing efforts. The OB case shows that a mutually beneficial relationship between co-marketing participants can lead to a win-win marketing strategy. It also highlights that collaborative channel management in mobile marketing methodology is critical for successful mobile marketing.