AA3DNet: Attention Augmented Real Time 3D Object Detection

by   abhinavsagar, et al.

In this work, we address the problem of 3D object detection from point cloud data in real time. For autonomous vehicles to work, it is very important for the perception component to detect the real world objects with both high accuracy and fast inference. We propose a novel neural network architecture along with the training and optimization details for detecting 3D objects using point cloud data. We present anchor design along with custom loss functions used in this work. A combination of spatial and channel wise attention module is used in this work. We use the Kitti 3D Birds Eye View dataset for benchmarking and validating our results. Our method surpasses previous state of the art in this domain both in terms of average precision and speed running at > 30 FPS. Finally, we present the ablation study to demonstrate that the performance of our network is generalizable. This makes it a feasible option to be deployed in real time applications like self driving cars.


page 2

page 8


Learning to Detect 3D Objects from Point Clouds in Real Time

In this work, we address the problem of 3D object detection from point c...

Fast-Image2Point: Towards Real-Time Point Cloud Reconstruction of a Single Image using 3D Supervision

A key question in the problem of 3D reconstruction is how to train a mac...

Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data

Real-time accurate detection of three-dimensional (3D) objects is a fund...

DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization

In this work, we propose a novel two-stage framework for the efficient 3...

Real-Time Pothole Detection Using Deep Learning

Roads are connecting line between different places, and used daily. Road...

Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds

Accurate detection of 3D objects is a fundamental problem in computer vi...

PillarAcc: Sparse PointPillars Accelerator for Real-Time Point Cloud 3D Object Detection on Edge Devices

3D object detection using point cloud (PC) data is vital for autonomous ...

Code Repositories


Code for the paper AA3DNet: Attention Augmented Real Time 3D Object Detection

view repo

Please sign up or login with your details

Forgot password? Click here to reset