Dengxiang Chang
Papers
3
Total Citations
15
H-Index
3
About
Dengxiang Chang is a researcher advancing sensor fusion and autonomous navigation, with a focus on calibration and localization for mobile robots and autonomous vehicles. Their work centers on developing robust methods for integrating LiDAR, cameras, GNSS, and IMU systems—critical for reliable perception in self-driving cars and robotics. Chang’s major contributions include a target-free stereo camera-GNSS/IMU self-calibration technique that uses iterative refinement to achieve accurate extrinsic calibration without specialized targets, addressing a key bottleneck in sensor fusion. They also developed WiCRF2, a multi-weighted LiDAR odometry and mapping approach that leverages motion observability features to enhance localization accuracy in SLAM systems. Additionally, their improved LiDAR–camera calibration method adapts the hand–eye model to work under motion limitations typical of ground vehicles, where full 6-DoF movement is impractical. With papers published in 2023 already accumulating citations (6, 5, and 4 respectively), Chang’s work is gaining traction for its practical solutions to real-world calibration and mapping challenges. Their research directly supports the deployment of lightweight, low-cost sensor suites in automated systems, making them a notable contributor to the field of autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3