Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving

Abstract

In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted from 2D images, our method solves this problem in the reconstructed 3D space in order to exploit 3D contexts explicitly. To this end, we first leverage a stand-alone module to transform the input data from 2D image plane to 3D point clouds space for a better input representation, then we perform the 3D detection using PointNet backbone net to obtain objects 3D locations, dimensions and orientations. To enhance the discriminative capability of point clouds, we propose a multi-modal feature fusion module to embed the complementary RGB cue into the generated point clouds representation. We argue that it is more effective to infer the 3D bounding boxes from the generated 3D scene space (i.e., X,Y, Z space) compared to the image plane (i.e., R,G,B image plane). Evaluation on the challenging KITTI dataset shows that our approach boosts the performance of state-of-the-art monocular approach by a large margin.

arXiv commentTo appear in ICCV'19

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Feature Pyramid Networks for Object Detection
• Deep Continuous Fusion for Multi-Sensor 3D Object Detection
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• Deep Learning for Generic Object Detection: A Survey

Cited by in corpus (4)

• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection
• DSGN: Deep Stereo Geometry Network for 3D Object Detection
• ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection