Title

• 국문: 머신 러닝을 활용한 영상기반 교통버스 사고예방 안전시스템

• English: Video-based Public Bus Accident Prevention System Using Machine Running

Funded by: 중소벤처기업부

Period: 2019-06-16 ~ 2020-03-19

Role: leader

Manager: 한승헌

Project summary:

• Development of image-based lane recognition technology using machine learning
  - Use of the Convolutional Neural Network (CNN) method, which is well known for its effective image processing

           
          - Create dataset- Pre-processing phase
          - Learning machine learning for lane detection and labeling for testing

• Development of pedestrian awareness technology
  - Leverage the R-CNN (Region with Convolutional Neural Network)
  - 1-Stage Object Detector - You Only Look Once (YOLO) and Single Shot Detector (SSD)
  - Data collection for machine learning
  - Design and learn about machine learning networks
  - Analyze learned results and repeat redesign
  - Measure the distance between the pedestrian and the vehicle using a stereo camera.

• Used as information for locating pedestrians and recognizing accident situations

• Recognition of road images in front and rear of a vehicle

• Recognition of information in night situations

•  Development of an accident situation recognition algorithm using recognized information

• An overall consideration of the lane in which the vehicle is currently being driven and the location of the pedestrian is taken to predict the situation of the accident.

Acknowledgement

• 국문표기:

• English:

Images:
Currently there are no images yet.