Show simple item record

dc.contributor.authorPerson, Michael
dc.contributor.authorJensen, Mathew
dc.contributor.authorSmith, Anthony O.
dc.contributor.authorGutierrez, Hector
dc.date.accessioned2019-09-18T09:06:46Z
dc.date.available2019-09-18T09:06:46Z
dc.date.copyright5/8/2019 12:00:00 AM
dc.date.issued2019
dc.identifier.issn0022-0434
dc.identifier.otherds_141_07_071017
dc.identifier.urihttp://yetl.yabesh.ir/yetl1/handle/yetl/4259000
dc.description.abstractIn order for autonomous vehicles to safely navigate the road ways, accurate object detection must take place before safe path planning can occur. Currently, general purpose object detection convolutional neural network (CNN) models have the highest detection accuracies of any method. However, there is a gap in the proposed detection frameworks. Specifically, those that provide high detection accuracy necessary for deployment but do not perform inference in realtime, and those that perform inference in realtime but detection accuracy is low. We propose multimodel fusion detection system (MFDS), a sensor fusion system that combines the speed of a fast image detection CNN model along with the accuracy of light detection and range (LiDAR) point cloud data through a decision tree approach. The primary objective is to bridge the tradeoff between performance and accuracy. The motivation for MFDS is to reduce the computational complexity associated with using a CNN model to extract features from an image. To improve efficiency, MFDS extracts complimentary features from the LiDAR point cloud in order to obtain comparable detection accuracy. MFDS is novel by not only using the image detections to aid three-dimensional (3D) LiDAR detection but also using the LiDAR data to jointly bolster the image detections and provide 3D detections. MFDS achieves 3.7% higher accuracy than the base CNN detection model and is able to operate at 10 Hz. Additionally, the memory requirement for MFDS is small enough to fit on the Nvidia Tx1 when deployed on an embedded device.
dc.publisherAmerican Society of Mechanical Engineers (ASME)
dc.titleMultimodal Fusion Object Detection System for Autonomous Vehicles
dc.typeJournal Paper
dc.journal.volume141
dc.journal.issue7
dc.journal.titleJournal of Dynamic Systems, Measurement, and Control
dc.identifier.doi10.1115/1.4043222
dc.journal.fristpage71017
dc.journal.lastpage071017-9
dc.treeJournal of Dynamic Systems, Measurement, and Control:;2019:;volume( 141 ):;issue: 007
dc.contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record