eduzhai > Applied Sciences > Engineering >

RUHSNet 3D Object Detection Using Lidar Data in Real Time

  • Save

... pages left unread,continue reading

Document pages: 10 pages

Abstract: In this work, we address the problem of 3D object detection from point clouddata in real time. For autonomous vehicles to work, it is very important forthe perception component to detect the real world objects with both highaccuracy and fast inference. We propose a novel neural network architecturealong with the training and optimization details for detecting 3D objects inpoint cloud data. We compare the results with different backbone architecturesincluding the standard ones like VGG, ResNet, Inception with our backbone. Alsowe present the optimization and ablation studies including designing anefficient anchor. We use the Kitti 3D Birds Eye View dataset for benchmarkingand validating our results. Our work surpasses the state of the art in thisdomain both in terms of average precision and speed running at > 30 FPS. Thismakes it a feasible option to be deployed in real time applications includingself driving cars.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×