Responsibilities
- Develop advanced image processing and video processing algorithm for real product.
- Develop camera image processing pipeline from camera row data to optimized RGB including but not limited to noise reduction, interpolation, 3A, gamma correction.
- Develop fixed point image processing algorithm for hardware implementation.
- Research and develop advanced image processing algorithm such as noise cancellation, motion detection, edge detection.
- Research and develop advanced computer vision algorithm such as real-time robotic SLAM (Simultaneous Localization and Mapping) solutions including 3D sensing, position tracking, 3D mapping / reconstruction, and sensor fusion.
- Research and develop practical solutions for 3D scene understanding (e.g., object detection) using state-of-the-art deep learning (DL) and machine learning (ML) methods.
Essential Requirements
- M.S. in Electrical Engineering, Computer Science, Robotics or similar field (Ph.D. is preferred).
- Solid understanding on image processing, signal processing, camera pipeline.
- Solid understanding on fixed point algorithm design.
- Understanding on 3D geometry such as SLAM, SfM, and 3D reconstruction is a big plus.
- Understanding and experience of applying deep learning to real problems in the fields of computer vision and robotics is a big plus.
- Strong experience in C/C++ programing.
- Hands-on experience in computer vision and deep learning frameworks is a big plus, e.g., OpenCV, Tensorflow, Keras, Pytorch, and Caffe.
- Ability to quickly adapt to new situations, learn new technologies, and collaborate and communicate effectively.
- 3+ years of industry experience with image processing and camera pipeline algorithm development and optimization.
技能標籤： computer vision, deep learning, ISP
