IPOD: Intensive Point-based Object Detector for Point Cloud

Abstract

We present a novel 3D object detection framework, named IPOD, based on raw point cloud. It seeds object proposal for each point, which is the basic element. This paradigm provides us with high recall and high fidelity of information, leading to a suitable way to process point cloud data. We design an end-to-end trainable architecture, where features of all points within a proposal are extracted from the backbone network and achieve a proposal feature for final bounding inference. These features with both context information and precise point cloud coordinates yield improved performance. We conduct experiments on KITTI dataset, evaluating our performance in terms of 3D object detection, Bird's Eye View (BEV) detection and 2D object detection. Our method accomplishes new state-of-the-art , showing great advantage on the hard set.

References in corpus (3)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• DSSD : Deconvolutional Single Shot Detector
• PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

Cited by in corpus (28)

• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
• A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services
• Semantics for Robotic Mapping, Perception and Interaction: A Survey
• StarNet: Targeted Computation for Object Detection in Point Clouds
• 3DSSD: Point-based 3D Single Stage Object Detector
• Deep Learning for 3D Point Clouds: A Survey
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection
• Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision
• HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
• Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
• Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detection
• Multi-Modal 3D Object Detection in Autonomous Driving: a Survey
• IoU Loss for 2D/3D Object Detection
• Streaming Object Detection for 3-D Point Clouds
• 3D Object Detection From LiDAR Data Using Distance Dependent Feature Extraction
• Cross-Modality 3D Object Detection
• 3D-MAN: 3D Multi-frame Attention Network for Object Detection
• MLOD: A multi-view 3D object detection based on robust feature fusion method
• Unsupervised Object Detection with LiDAR Clues
• Adaptive and Azimuth-Aware Fusion Network of Multimodal Local Features for 3D Object Detection
• Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds
• R-AGNO-RPN: A LIDAR-Camera Region Deep Network for Resolution-Agnostic Detection
• Stereo Frustums: A Siamese Pipeline for 3D Object Detection
• RoIFusion: 3D Object Detection from LiDAR and Vision