Tackling Heterogeneous Light Detection and Ranging-Camera Alignment Challenges in Dynamic Environments: A Review for...

Area of Science:

• Computer Vision
• Robotics
• Autonomous Systems

Background:

• Object detection is vital for autonomous systems, utilizing heterogeneous data from LiDAR and camera sensors.
• Existing reviews often neglect the complexities of aligning multimodal data, especially in dynamic environments.

Purpose of the Study:

• To survey and analyze heterogeneous LiDAR-camera alignment methods for 3D object detection in dynamic environments.
• To provide a classification of alignment techniques and identify research gaps.

Main Methods:

• Comprehensive literature review of over 20 alignment methods (2019-2024).
• Focus on heterogeneous data alignment challenges in dynamic environments.
• Comparative analysis of strengths and limitations of various approaches.

Main Results:

• Classification of heterogeneous data alignment methods for 3D object detection.
• Identification of critical challenges including dynamic environments, sensor fusion, scalability, and real-time processing.

Conclusions:

• Heterogeneous alignment is crucial for accurate 3D object detection in dynamic scenarios.
• Future research should address identified limitations to advance multimodal sensor fusion.