Key Responsibilities:
- Design and implement advanced image and video processing algorithms to stitch multiple drone video streams into a cohesive panoramic output.
- Develop and optimize real-time techniques for video alignment, motion estimation, and seamless image blending.
- Integrate computer vision algorithms into autonomous drone platforms in collaboration with cross-functional engineering teams.
- Ensure high performance of algorithms on embedded systems or edge computing devices.
- Conduct experiments and real-world testing to validate algorithm robustness and accuracy.
- Maintain clear technical documentation, including design specs, development steps, and evaluation results.
- Communicate with projects to recommend technical solutions, troubleshoot issues, and provide expert-level support.
Required Qualifications:
- Bachelor’s, Master’s, or PhD in Computer Vision, Computer Science, Electrical Engineering, or related fields.
- 7 years of experience in computer vision, image processing, or related domain.
- Strong coding skills in Python and/or C++ with practical knowledge of libraries such as OpenCV, PyTorch, TensorFlow, or equivalents.
- Proven experience in video stitching, multi-view geometry, or similar areas.
- Familiarity with real-time video processing and performance optimization techniques.
- Strong analytical and problem-solving skills with the ability to work independently or in a collaborative team setup.
Preferred Qualifications:
- Software engineering experience in developing application frontends (e.g., UI for visual outputs or control panels).
- Exposure to embedded systems or edge computing platforms.
- Familiarity with swarm robotics, autonomous navigation systems, or drone-based applications.