Timezone: »

PolarStream: Streaming Object Detection and Segmentation with Polar Pillars
Qi Chen · Sourabh Vora · Oscar Beijbom

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @

Recent works recognized lidars as an inherently streaming data source and showed that the end-to-end latency of lidar perception models can be reduced significantly by operating on wedge-shaped point cloud sectors rather then the full point cloud. However, due to use of cartesian coordinate systems these methods represent the sectors as rectangular regions, wasting memory and compute. In this work we propose using a polar coordinate system and make two key improvements on this design. First, we increase the spatial context by using multi-scale padding from neighboring sectors: preceding sector from the current scan and/or the following sector from the past scan. Second, we improve the core polar convolutional architecture by introducing feature undistortion and range stratified convolutions. Experimental results on the nuScenes dataset show significant improvements over other streaming based methods. We also achieve comparable results to existing non-streaming methods but with lower latencies.

Author Information

Qi Chen (Johns Hopkins University)
Sourabh Vora (nuTonomy)
Oscar Beijbom (nuTonomy)

I'm the Machine Learning lead at nuTonomy, where I work on the computer vision system for their fleet of autonomous vehicles. Before joining nuTonomy I was a postdoctoral scholar in Trevor Darrell's lab at Berkeley AI Research. There, I worked on automated quantification of scientific image-data using deep learning. Before Berkeley, I studied computer vision and machine learning at UCSD under David Kriegman and Serge Belongie, and engineering physics at Lund University under Kalle Åström. Previously, I was lead developer at Hövding where I created the algorithmic framework and hardware design for their invisible bicycle helmet. I have also worked on automated dietary logging systems for consumer applications and focusing algorithms for image-based cell analysis. I also manage and develop CoralNet, deploying deep convolutional neural networks to help coral reef ecologists mine image data.

More from the Same Authors