Version 1
: Received: 1 September 2022 / Approved: 5 September 2022 / Online: 5 September 2022 (13:03:00 CEST)
How to cite:
Alaba, S.; Ball, J. WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving. Preprints2022, 2022090060. https://doi.org/10.20944/preprints202209.0060.v1
Alaba, S.; Ball, J. WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving. Preprints 2022, 2022090060. https://doi.org/10.20944/preprints202209.0060.v1
Alaba, S.; Ball, J. WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving. Preprints2022, 2022090060. https://doi.org/10.20944/preprints202209.0060.v1
APA Style
Alaba, S., & Ball, J. (2022). WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving. Preprints. https://doi.org/10.20944/preprints202209.0060.v1
Chicago/Turabian Style
Alaba, S. and John Ball. 2022 "WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving" Preprints. https://doi.org/10.20944/preprints202209.0060.v1
Abstract
3D object detection is crucial for autonomous driving to understand the driving environment. Since the pooling operation causes information loss in the standard CNN, we have designed a wavelet multiresolution analysis-based 3D object detection network without a pooling operation. Additionally, instead of using a single filter like the standard convolution, we use the lower-frequency and higher-frequency coefficients as a filter. These filters capture more relevant parts than a single filter, enlarging the receptive field. The model comprises a discrete wavelet transform (DWT) and an inverse wavelet transform (IWT) with skip connections to encourage feature reuse for contrasting and expanding layers. The IWT enriches the feature representation by fully recovering the lost details during the downsampling operation. Element-wise summation is used for the skip connections to decrease the computational burden. We train the model for the Haar and Daubechies (Db4) wavelets. The two-level wavelet decomposition result shows that we can build a lightweight model without losing significant performance. The experimental results on the KITTI’s BEV and 3D evaluation benchmark show our model outperforms the Pointpillars base model by up to 14 \% while reducing the number of trainable parameters. Code will be released.
Keywords
Autonomous Driving; Deep Learning; LIDAR Data; Wavelets; 3D Object Detection
Subject
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
