3D-MAN: 3D Multi-frame Attention Network for Object Detection
Citations Over TimeTop 10% of 2021 papers
Abstract
3D object detection is an important module in autonomous driving and robotics. However, many existing methods focus on using single frames to perform 3D detection, and do not fully utilize information from multiple frames. In this paper, we present 3D-MAN: a 3D multi-frame attention network that effectively aggregates features from multiple perspectives and achieves state-of-the-art performance on Waymo Open Dataset. 3D-MAN first uses a novel fast single-frame detector to produce box proposals. The box proposals and their corresponding feature maps are then stored in a memory bank. We design a multi-view alignment and aggregation module, using attention networks, to extract and aggregate the temporal features stored in the memory bank. This effectively combines the features coming from different perspectives of the scene. We demonstrate the effectiveness of our approach on the large-scale complex Waymo Open Dataset, achieving state-of-the-art results compared to published single-frame and multi-frame methods.
Related Papers
- → Experimental study of a vehicle detector with an AMR sensor(2004)60 cited
- → Design and optimization of a novel 3D detector: The 3D-open-shell-electrode detector(2018)6 cited
- Design of optimized V-detector algorithm with higher detection efficiency(2010)
- Analysis and Research of Detector Types of Spectrum Analyzer(2010)
- → Chapter 1 The Selection of the Appropriate Detector(1977)