• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.408-411
• /
• 2019

고양이를 기르는 가구의 증가와 함께 건강한 애묘 방법을 찾는 애묘인 또한 증가하고 있다. 본 논문에서는 고양이의 건강 상태를 모니터링하기 위해 반드시 선행되어야만 하는 고양이의 행동 정보를 딥러닝 방법론을 기반으로 인식하고자 한다. 인식을 위해 먼저, 카메라 센서를 이용하여 고양이 영상 데이터를 수집한 후, 수집된 영상에서 RGB 프레임과 optical flow 프레임 정보를 각각 수집한다. 각각의 프레임은 RGB Network 와 Flow Network 에 입력되고, 두 네트워크 결과 정보에 대하여 concatenation 을 수행한다. 연계된 특징 정보는 행동 인식 알고리즘인 Two-Stream YOLO 에 입력이 되어 고양이의 행동을 인식한다. 고양이의 행동 인식은 일곱 개의 클래스로 나누어 진행하였다. 행동 인식 실험 수행 결과 mAP와 f1-score 모두에서 0.9이상의 높은 성능을 보였으며, 실시간으로 수행이 가능함을 확인하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.971-974
• /
• 2020

Infants express their physical and emotional needs to the outside world mainly through crying. However, most of parents find it challenging to understand the reason behind their babies' cries. Failure to correctly understand the cause of a baby' cry and take appropriate actions can affect the cognitive and motor development of newborns undergoing rapid brain development. In this paper, we propose an infant cry recognition system based on deep transfer learning to help parents identify crying babies' needs the same way a specialist would. The proposed system works by transforming the waveform of the cry signal into log-mel spectrogram, then uses the VGGish model pre-trained on AudioSet to extract a 128-dimensional feature vector from the spectrogram. Finally, a softmax function is used to classify the extracted feature vector and recognize the corresponding type of cry. The experimental results show that our method achieves a good performance exceeding 0.96 in precision and recall, and f1-score.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.354-357
• /
• 2021

Infants communicate their feelings and needs to the outside world through non-verbal methods such as crying and displaying diverse facial expressions. However, inexperienced parents tend to decode these non-verbal messages incorrectly and take inappropriate actions, which might affect the bonding they build with their babies and the cognitive development of the newborns. In this paper, we propose an aural-visual two-stream based infant cry recognition system to help parents comprehend the feelings and needs of crying babies. The proposed system first extracts the features from the pre-processed audio and video data by using the VGGish model and 3D-CNN model respectively, fuses the extracted features using a fully connected layer, and finally applies a SoftMax function to classify the fused features and recognize the corresponding type of cry. The experimental results show that the proposed system classification exceeds 0.92 in F1-score, which is 0.08 and 0.10 higher than the single-stream aural model and single-stream visual model.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.700-703
• /
• 2021

Infrared cameras are widely used in recent research for automatic monitoring the abnormal behaviors of the pig. However, when deployed in real pig farms, infrared cameras always get polluted due to the harsh environment of pig farms which negatively affects the performance of pig monitoring. In this paper, we propose a real-time noise-robust infrared camera-based pig automatic monitoring system to improve the robustness of pigs' automatic monitoring in real pig farms. The proposed system first uses a preprocessor with a U-Net architecture that was trained as a GAN generator to transform the noisy images into clean images, then uses a YOLOv5-based detector to detect pigs. The experimental results show that with adding the preprocessing step, the average pig detection precision improved greatly from 0.639 to 0.759.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.704-707
• /
• 2021

Pigs' aggressive behavior represents one of the common issues that occur inside pigpens and which harm pigs' health and welfare, resulting in a financial burden to farmers. Continuously monitoring several pigs for 24 hours to identify those behaviors manually is a very difficult task for pig caretakers. In this study, we propose a lightweight video-based approach for monitoring pigs' aggressive behavior that can be implemented even in small-scale farms. The proposed system receives sequences of frames extracted from an RGB video stream containing pigs and uses MnasNet with a DM value of 0.5 to extract image features from pigs' ROI identified by predefined annotations. These extracted features are then forwarded to a lightweight LSTM to learn temporal features and perform behavior recognition. The experimental results show that our proposed model achieved 0.92 in recall and F1-score with an execution time of 118.16 ms/sequence.

• 한국융합학회논문지
• /
• 제5권2호
• /
• pp.25-32
• /
• 2014

Indian economy growth changed due Indian business operational approach with convergent technologies. The current economy growth supported by Information Technology Development and Information Technology Enabled Service. As part of the Information technology enabled upcoming Knowledge processing outsourcing provide huge opportunities to develop Indian business with our human resources. The KPO business sector basis and frame work can be achieve through Development Dynamic initiatives. This paper discuss about the basis of KPO and Dynamic Development Initiative frame work strategic compact components and its characters.

• 한국산업융합학회 논문집
• /
• 제7권2호
• /
• pp.207-213
• /
• 2004

This paper describes the development of Behind-Tape-Reader (BTR) type DNC system using CYBER 180-830 as a central computer and IBM PC-AT cell control computer and NC lathe with FANUC 5T NC controller. In this system, the connection between central computer and cell control computer is done via RS-232C serial interface board, and that between cell control computer and FANUC 5T controller is done via parallel interface board. The software consists of two module, central computer communication module for NC program downloading and status uploading, NC machine running module for NC operating.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2000년도 추계종합학술대회논문집
• /
• pp.165-168
• /
• 2000

In this paper, we propose a method, an optimized architecture of a device with an image signal process of a field unit to minimize the flick phenomenon that happens in direction of a color temperature at a color tone change. The proposed IIR loop filter has an optimized architecture and reduced hardware compared with previous filters. In order to achieve the optimization for the hardware complexity. It is designed by time-multiplexing architecture. The proposed IIR loop filter is synthesized by using the STD90 0.35um cell library.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2000년도 하계종합학술대회논문집
• /
• pp.265-268
• /
• 2000

In this paper, we propose an algorithm, an optimized architecture, and an implementation for an improved performance of image downscaler. The proposed downscaler uses two-dimensional digital filters for horizontal and vertical scalings, respectively. It also improves scaling precisions and decreases the loss of data, compared with the 1/32 scaler 〔1〕. In order to achieve the optimization, the digital filters are implemented by the multiplexer -adder type scheme 〔2〕. The scaler is designed by using the Verilog-HDL. It is synthesized into gates by using the Samsung 0.35 um STD90 TLM library.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2014년도 제50차 하계학술대회논문집 22권2호
• /
• pp.51-52
• /
• 2014

본 논문에서는 경량화 설계가 반영된 차량의 내구성 및 안전성을 증가시키기 위해 사용되는 구조용 접착제의 비균일적, 미도포 된 부분을 검사하기 위한 방법에 대해 제안한다. 이 방법은 차량이 조립되기 전 구조용 접착체가 균일하게 도포되지 않은 부분을 사전에 알려줌으로써 차량의 전체적인 강성을 높일 수 있어, 차량의 조립에 있어 의무화되어 가는 추세이다. 이 방법은 머신전용 카메라와 보드 기반으로 간단하게 구성이 가능하다.