IntPred: flexible, fast, and accurate object detection for autonomous driving systems
View/Open
Cita com:
hdl:2117/185832
Document typeConference report
Defense date2020
PublisherAssociation for Computing Machinery (ACM)
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder
ProjectSuPerCom - Sustainable Performance for High-Performance Embedded Computing Systems (EC-H2020-772773)
COMPUTACION DE ALTAS PRESTACIONES VII (MINECO-TIN2015-65316-P)
RYC-2013-14717 (MINECO-RYC-2013-14717)
COMPUTACION DE ALTAS PRESTACIONES VII (MINECO-TIN2015-65316-P)
RYC-2013-14717 (MINECO-RYC-2013-14717)
Abstract
Deep Neural-Network (DNN) based Object Detection is one of the most important and time-consuming stages of Autonomous Driving software in cars. In non-critical domains, the performance and energy requirements of object detection can be reduced at the cost of accuracy in the detected objects. This is not the case in a critical domain like automotive, for which a delicate balance between performance/energy overheads and accuracy of object detection must be found. We propose IntPred to achieve such a balance by leveraging on the fact that, with high frame rates, objects do not move significantly across frames. IntPred tailors object interpolation for the case of object detection in autonomous driving frameworks, in line with approaches devised for other domains, thus heavily reducing the performance requirements of full-fledged DNN-based object prediction. IntPred results in comparable accuracy to the original object detection, while saving more than 70% of the computations. The latter allows using lower-performance and cheaper platforms resulting in saving energy and reducing heat dissipation: for instance, in an NVIDIA Jetson TX2 platform, specific for autonomous driving systems, our technique increases the frame processing rate by 4.6x. IntPred also allows consolidating additional applications onto the same platform.
CitationTabani, H. [et al.]. IntPred: flexible, fast, and accurate object detection for autonomous driving systems. A: ACM Symposium on Applied Computing. "The 35th Annual ACM Symposium on Applied Computing: Brno, Czech Republic, March 30-April 3, 2020". Association for Computing Machinery (ACM), 2020, p. 564-571.
ISBN978-1-4503-6866-7
Publisher versionhttps://dl.acm.org/doi/10.1145/3341105.3373918
Collections
Files | Description | Size | Format | View |
---|---|---|---|---|
postprint-IntPred.pdf | 3,036Mb | View/Open |