Presentation
DAWN: Accelerating Point Cloud Object Detection via Object-Aware Partitioning and 3D Similarity-Based Filtering
DescriptionAs a fundamental perception task, 3D point cloud detection has become essential for autonomous systems. Point-based detection methods offer high accuracy but are computationally expensive, primarily due to sequential point processing operations, such as set abstraction. To address these challenges, we propose DAWN, an acceleration framework for point cloud object detection that identifies partial similarities via well-designed partitioning and filters redundant points. We leverage spatio-temporal information from consecutive frames to accelerate point cloud detection. Frame partitioning enables partial similarity identification, but naive partitioning can lead to object fragmentation and detection errors. Our dynamic object-aware partitioning leverages previous detection results to determine boundaries and prevent fragmentation errors. Axis-sorted point selection refines the partitioning for better similarity identification and an efficient 3D similarity algorithm accurately filters out redundant points. Our experiments demonstrate that DAWN enables flexible latency-accuracy trade-offs and achieves up to 1.7x detection speedup by filtering more than 50% of points, with negligible impact on accuracy.
Event Type
Research Manuscript
TimeWednesday, June 253:30pm - 3:45pm PDT
Location3006, Level 3
Systems
SYS4: Embedded System Design Tools and Methodologies