Traffic Scene Classification from Video
Traffic Scene Classification from Video (Job Number: P17INT-09)

This project focuses on research and development of computer vision and machine learning algorithms for video based classification/recognition of road scenes, including places, road surface and weather conditions, and spatial relationships.  This core technology is to be used for higher level understanding of traffic scenes, including temporal event detection, action recognition, video captioning, and localization.

 

Qualifications:

  • MS or PhD candidate in computer science, electrical engineering, or related field
  • Strong familiarity with machine learning techniques pertaining to visual recognition, place recognition, and/or video classification
  • Highly proficient in software engineering using C++ and Python
  • Experience in TensorFlow (or Caffe) and CAD rendering tools preferred