2023 · 28 citations · 28 references
ComputingAutonomous SystemsComputer ScienceAutonomous VehiclesComputer VisionMachine LearningAction RecognitionInstance SegmentationOptical FlowRobotic VisionScene UnderstandingVehicle PerceptionBird's-eye PerspectiveConvolutional Neural NetworksInstance Segmentation For Autonomous DrivingMotion PredictionPost-processingPrediction For Autonomous Driving
Accurately perceiving instances and predicting their future motion are key tasks for autonomous vehicles, enabling them to navigate safely in complex urban traffic. While bird’s-eye view (BEV) representations are commonplace in perception for autonomous driving, their potential in a motion prediction setting is less explored. Existing approaches for BEV instance prediction from surround cameras rely on a multi-task auto-regressive setup coupled with complex post-processing to predict future instances in a spatio-temporally consistent manner. In this paper, we depart from this paradigm and propose an efficient novel end-to-end framework named PowerBEV, which differs in several design choices aimed at reducing the inherent redundancy in previous methods. First, rather than predicting the future in an auto-regressive fashion, PowerBEV uses a parallel, multi-scale module built from lightweight 2D convolutional networks. Second, we show that segmentation and centripetal backward flow are sufficient for prediction, simplifying previous multi-task objectives by eliminating redundant output modalities. Building on this output representation, we propose a simple, flow warping-based post-processing approach which produces more stable instance associations across time. Through this lightweight yet powerful design, PowerBEV outperforms state-of-the-art baselines on the NuScenes Dataset and poses an alternative paradigm for BEV instance prediction. We made our code publicly available at: https://github.com/EdwardLeeLPZ/PowerBEV.
28
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
Center-based 3D Object Detection and Tracking
Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl · 2021 · 1.9K citations
PIXOR: Real-time 3D Object Detection from Point Clouds
Bin Yang, Wenjie Luo, Raquel Urtasun · 2018 · 1.3K citations