preprints.org > engineering > automotive engineering > doi: 10.20944/preprints202306.0287.v1

Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Version 1 : Received: 5 June 2023 / Approved: 5 June 2023 / Online: 5 June 2023 (09:15:40 CEST)

3D object detection is essential for an accurate and reliable autonomous driving system. Currently, the methods used by the state-of-the-art two-stage detectors are not flexible enough and their fea-ture extraction capabilities are very limited to cope effectively with the disorder and irregularity of point clouds. In this paper, we combine the advantages of both PV-RCNN and PAConv (Position Adaptive Convolution) to create a completely new network, FANet, in order to overcome the ir-regularity and disorder of point clouds. The convolution in our network builds convolutional ker-nels from a basic weight matrix, whose combined coefficients are learned adaptively by LearnNet from relative points. This network allows for flexible modeling of complex spatial variations and geometric structures in the 3D point cloud, enabling better extraction of point cloud features and producing high-quality 3D proposal boxes. Compared to other methods, FANet is superior in terms of 3D object detection accuracy. Extensive experiments on the KITTI dataset have shown a signif-icant improvement in our approach.

autonomous driving; object detection; Position Adaptive Convolution; FANet

Engineering, Automotive Engineering

* All users must log in before leaving a comment