3D Object Detection Using Scale Invariant and Feature Reweighting Networks

Abstract

3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real scenes. In this paper, we present a new network architecture which focuses on utilizing the front view images and frustum point clouds to generate 3D detection results. On the one hand, a PointSIFT module is utilized to improve the performance of 3D segmentation. It can capture the information from different orientations in space and the robustness to different scale shapes. On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module. This module reweights channel features and estimates the 3D bounding boxes more effectively. Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. The experimental results illustrate that our method achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse.

arXiv commentThe Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)

References in corpus (6)

• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• Vehicle Detection from 3D Lidar Using Fully Convolutional Network
• Joint 3D Proposal Generation and Object Detection from View Aggregation
• PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation

Cited by in corpus (4)

• Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review
• Feature Reweighting for EEG-based Motor Imagery Classification
• Fast Object Classification and Meaningful Data Representation of Segmented Lidar Instances
• A re-calibration method for object detection with multi-modal alignment bias in autonomous driving