Programming language

Philosophy

Artificial intelligence

Set (abstract data type)

Geometry

Object detection

Code (set theory)

Remote sensing

Feature (linguistics)

Lidar

Geology

Point cloud

Pattern recognition (psychology)

Mathematics

Memory footprint

Image (mathematics)

Geography

Operating system

Computer science

Geodesy

Minimum bounding box

Orientation (vector space)

Benchmark (surveying)

Linguistics

Feature extraction

Object (grammar)

Computer vision

We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region proposal network (RPN) and a second stage detector network. The proposed RPN uses a novel architecture capable of performing multimodal feature fusion on high resolution feature maps to generate reliable 3D object proposals for multiple object classes in road scenes. Using these proposals, the second stage detection network performs accurate oriented 3D bounding box regression and category classification to predict the extents, orientation, and classification of objects in 3D space. Our proposed architecture is shown to produce state of the art results on the KITTI 3D object detection benchmark [1] while running in real time with a low memory footprint, making it a suitable candidate for deployment on autonomous vehicles. Code is available at: https://github.com/kujason/avod.

Joint 3D Proposal Generation and Object Detection from View Aggregation