Evaluating faster-RCNN and YOLOv3 for target detection in multi-sensor data

Anwaar Ul-Haq, Asim Khan, Randall W Robinson

Research output: Book chapter/Published conference paperConference paper

Abstract

Intelligent and autonomous systems like driverless cars are seeking the capability to navigatearound at any time of the day and night. Therefore, it is vital to have the capability to reliablydetect objects to predict any situation. One way to capture such imagery is through multisensordata like FLIR (Forward Looking Infrared) and visible cameras. Contemporary deep objectdetectors like YOLOv3 (You Look Once Only) [1] and Faster-RCNN (Faster Region basedConvolu- tional Neural Networks) [2] are well-trained for daytime images. However, noperformance evaluation is available against multi-sensor data. In this paper, we argue thatdiverse contextual multi-sensor data and transform learning can optimise the performance ofdeep object detectors to detect objects around the clock. We explore how contextual multisensor data can play a pivotal role in modelling and recognizing objects especially at night. Forthis purpose, we have proposed the use of contextual data fusion on available training databefore training these deep detectors. We show that such enhancement significantly increasesthe performance of deep learning based object detectors
Original languageEnglish
Title of host publicationStatistics for Data Science and Policy Analysis
Publication statusPublished - 2020
EventThe 2nd Applied Statistics and Policy Analysis Conference: ASPAC2019 - Charles Sturt University, Wagga Wagga, Australia
Duration: 05 Sep 201906 Sep 2019
http://csusap.csu.edu.au/~azrahman/ASPAC2019/
http://csusap.csu.edu.au/~azrahman/ASPAC2019/Program%20draft.pdf?attredirects=0&d=1 (program)
http://csusap.csu.edu.au/~azrahman/ASPAC2019/ASPAC2019_Refereed_Book%20of%20Abstracts.pdf?attredirects=0&d=1 (book of abstracts)
https://ebookcentral.proquest.com/lib/CSUAU/detail.action?docID=6152166 (proceedings)

Conference

ConferenceThe 2nd Applied Statistics and Policy Analysis Conference
Abbreviated titleEffective policy through the use of big data, accurate estimates and modern computing tools and statistical modelling
CountryAustralia
CityWagga Wagga
Period05/09/1906/09/19
OtherProceedings due for publication May 2020 https://www.springer.com/gp/book/9789811517341
Internet address

Fingerprint Dive into the research topics of 'Evaluating faster-RCNN and YOLOv3 for target detection in multi-sensor data'. Together they form a unique fingerprint.

  • Cite this

    Ul-Haq, A., Khan, A., & Robinson, R. W. (2020). Evaluating faster-RCNN and YOLOv3 for target detection in multi-sensor data. In Statistics for Data Science and Policy Analysis