Previous studies detected mounting in CCTV video taken in side-view, top-view and formatted experimental environments. In this paper, we propose deep learning based Mounting Detection System that detects mounting scene and extracts video section for mounting from CCTV video in various environments. We use the trained model created by transfer learning with TensorFlow’s SSD-based object detection model to detect mounting object from the frame image extracted from CCTV video. In addition, we finally extract video section for mounting by unifying a number of true and false mounting detections during an average of 1-3 seconds. As a result of the experiment, the precision, accuracy, and recall of the trained model were recorded at about 84%, 88%, and 93% respectively. And the performance of the Mounting Detection System that apply unification to the detection results of each frame were about 87%, 91%, and 96%, respectively.
한국어
CCTV 영상을 이용한 승가행위 탐지 연구는 side-view, top-view, 정형화된 실험 환경에서 촬영한 CCTV 영상에서 승가행위를 탐지하였다. 이 논문에서는 실제 축산농가에 설치된 다양한 환경의 CCTV 영상에서 승가행위를 탐지하고, 승가행위 구간을 추출하는 딥러닝 기반의 승가행위 검출 시스템을 제안한다. 제안 시스템에 서는 텐서플로우의 SSD 기반 객체인식 모델을 전이학습하여 생성한 학습모델(trained model)을 이용하여 CCTV 영상에서 추출한 프레임 이미지로부터 승가행위 객체를 탐지한 후, 평균 1-3초동안 이루어지는 승가행위 구간에서 탐지되는 다수의 정상탐지와 오탐지를 하나의 승가행위로 단일화하여 최종적인 승가행위를 검출한다. 실험 결과, 승가행위 탐지 학습모델의 정밀도, 정확도, 재현율은 각각 약 84%, 88%, 93%를 기록하였고, 프레임 단위의 탐지 결과에 단일화를 적용한 승가행위 검출 시스템의 정밀도, 정확도, 재현율은 각각 약 87%, 91%, 96%로 향상된 결 과를 기록하였다.
목차
요약 Abstract Ⅰ. 서론 Ⅱ. 제안 시스템 Ⅲ. 승가행위 탐지 학습모델 생성 3.1 데이터 수집 3.2 승가행위 학습데이터 구축 3.3 승가행위 탐지를 위한 딥러닝 모델 및 학습 환경 Ⅳ. 성능 평가 4.1 테스트셋 및 평가 지표 4.2 학습모델 평가 결과 및 분석 4.3 검출 시스템 평가 결과 및 분석 Ⅴ. 결론 REFERENCES
Ever since next generation convergence technology became one of the most important industries in the nation, computing professionals have encountered a growing number of challenges. Along with scholars and colleagues in related fields, they have gathered in avariety of forums and meetings over the last few decades to share their knowledge, experiences and the outcome of their research. These exchanges have led to the founding of the International Next-generation Convergence technology (INCA) on December 1, 2015. INCA was registered as an incorporated association under the Ministry of Information and Communications. The main purpose of the organization is to improve our society by achieving the highest capability possible in next generation convergence technology.
간행물
간행물명
차세대융합기술학회논문지 [The Journal of Next-generation Convergence Technology Association]