Yiming Wang
Papers
1
Total Citations
25
H-Index
1
About
Yiming Wang is an emerging researcher specializing in 3D computer vision and autonomous driving perception systems, with a particular focus on multi-object detection and tracking (MODT). His most recognized work, "Boost Correlation Features with 3D-MiIoU-Based Camera-LiDAR Fusion for MODT in Autonomous Driving" (2023), has already garnered 25 citations, reflecting rapid recognition within the autonomous driving research community. This contribution addresses a critical challenge in the field: effectively leveraging multimodal sensor data by fusing camera and LiDAR inputs to enhance tracking accuracy in complex, real-world driving environments. By introducing a novel 3D Mean Intersection over Union (3D-MiIoU) framework, Wang's approach advances the state of the art in correlating features across sensor modalities, a problem that has long limited the reliability of autonomous perception pipelines. His work sits at the intersection of robotics, human–computer interaction, and intelligent transportation systems, making it broadly applicable beyond autonomous vehicles. For students and researchers entering the field of 3D scene understanding or sensor fusion, Wang's research represents a valuable methodological foundation for building robust, real-time multi-object tracking systems.
Research Focus
Key Achievements
Top Papers
- 1