[Computer Vision] Visual Understanding of Traffic Scenes - [Computer Vision] Visual Understanding of Traffic Scenes - HRI-US
[Computer Vision] Visual Understanding of Traffic Scenes
Job Number: P20INT-37
The title includes multiple positions, which focus on developing computer vision and machine learning algorithms to capture the detailed semantics of 2D and/or 3D traffic scenes.
San Jose, CA
You are expected to:
- Capturing the semantics of visual scenes by explicit modeling of objects, their attributes, and relationships to other objects and the environment.
- Higher-level classification/recognition of dynamic traffic scenes including place, conditions, and spatial relationships using temporal event detection, action recognition, and localization.
- Detection and understanding of unstructured events that impact navigation, such as disabled vehicles, construction zones, traffic accidents, etc.
- Develop and evaluate metrics to verify reliability of the proposed algorithms.
- Contribute to a portfolio of patents, academic publications, and prototypes to demonstrate research value.
- Ph.D. or highly qualified M.S. candidate in computer science, electrical engineering, or related field.
- Strong familiarity with computer vision and machine learning techniques pertaining to scene understanding, image classification, and object detection.
- Hands-on experience in one or more of the following: scene graphs, spatio-temporal graphs, graph neural networks, visual recognition, video classification.
- Experience in open-source deep learning frameworks such as TensorFlow or PyTorch preferred
- Excellent programming skills in Python or C++.
Duration: 3 months