WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving

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.

Deep Learning-Based Image 3-D Object Detection for Autonomous Driving: Review

“…Although 3D object detection using camera images has shown significant performance improvement due to the rapid growth of DL, there are still issues to be solved for reliable and robust driving, such as driving in bad weather or at night. The camera sensor is rich in color and texture and inexpensive, but it cannot measure the distance from long range, cannot withstand bad weather, and does not give direct 3D information [14], [42]. 3D sensors, such as LiDAR and radar, provide 3D information about the driving environment and objects.…”

“…The elevation and roll angles are considered zero. This encoding method is further adopted by pointpillars [41], WCNN3D [42], and monocular 3d [24]. This technique is widely used in 3D object detection.…”

Image Classification using Different Machine Learning Techniques

“…In addition to the classification task, object detection works, such as [2], [3], [4], [5], [6], [7], [8], [9] used the convolutional network to get better performance over traditional machine learning. Various regularization and optimization techniques are used for the training.…”