Responsibilities
1、Responsible for detecting the 6D position of cargo in the unmanned vehicle operating environment based on 2D/3D point cloud sensors
2、Responsible for researching and testing the latest point cloud type sensors and importing them into the vehicle perception module
3、Research the application of deep learning in 3D vision, track the frontier theory, and translate into relevant algorithms
4、Responsible for the embedded porting of vehicle perception module
Translated with www.DeepL.com/Translator (free version)
Requirements
1, artificial intelligence, computer science, information and computational science, mathematical statistics, electronics and communications engineering, pattern recognition, machine vision and other related majors
2、Familiar with the principle and use of commonly used 2D/3D LIDAR, TOF depth camera, binocular camera and other sensors
3, proficient in basic point cloud processing methods, point cloud pre-processing, filtering, segmentation, alignment, fusion and reconstruction, etc.
4, proficient in OpenCV, PCL, open3d and other common open source libraries
5、Rich experience in RGB image and point cloud data processing, such as pose estimation, multi-view geometry vision, etc.
6、Knowledge of existing 3D visual depth models, such as VoxNet, PointNet, PointNet++, etc.
7、 Strong programming skills, familiar with C/C++, Python, C#, Matlab and other programming languages, familiar with multi-threaded programming, Git software version management system
8、 Good in mathematics, strong self-learning ability, like to specialize in research, can read Chinese and English patents and papers fluently.
9、 Provincial or national competition winners or those who have published papers in top journals are preferred.
10、 Consider excellent freshmen in 2022-2023 (can intern for six months and above)
Translated with www.DeepL.com/Translator (free version)
