Show simple item record

dc.contributor.authorFarooq, A
dc.contributor.authorJia, X
dc.contributor.authorHu, J
dc.contributor.authorZhou, J
dc.date.accessioned2020-04-02T02:15:06Z
dc.date.available2020-04-02T02:15:06Z
dc.date.issued2019
dc.identifier.isbn9781728152943
dc.identifier.issn2158-6276
dc.identifier.doi10.1109/WHISPERS.2019.8920832
dc.identifier.urihttp://hdl.handle.net/10072/392922
dc.description.abstractWeed identification and classification are essential and challenging tasks for site-specific weed control. Object-based image analysis making use of spatial information is adopted in this study for the weed classification because the spectral similarity between the weeds and crop is high. With the availability of a wide range of sensors, it is likely to capture weed imagery at various altitudes and with different specifications of the sensor. In this paper, we propose a novel method using transfer learning to deal with multi-resolution images from various sensors via Convolutional Neural Networks (CNN). CNN trained for a typical image data set and the trained weights are transferred to other data sets of different resolutions. In this way, the new data sets can be classified by fine-tuning the network using a small number of training samples, which reduces the need of big data to train the model. To avoid over-fitting during the fine-tuning, small deep learning architecture is proposed and investigated using the parameters of the initial layers of pre-trained model. The sizes of training samples are investigated for their impact on the performance of fine-tuning. Experiments were conducted with field data, which show that the proposed method outperforms the direct training method in terms of recognition accuracy and computation cost.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherIEEE
dc.relation.ispartofconferencename10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS 2019)
dc.relation.ispartofconferencetitleWorkshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
dc.relation.ispartofdatefrom2019-09-24
dc.relation.ispartofdateto2019-09-26
dc.relation.ispartoflocationAmsterdam, Netherlands
dc.relation.ispartofvolume2019-September
dc.relation.urihttp://purl.org/au-research/grants/ARC/IH180100002
dc.relation.grantIDIH180100002
dc.relation.fundersARC
dc.subject.fieldofresearchArtificial Intelligence and Image Processing
dc.subject.fieldofresearchcode0801
dc.titleKnowledge Transfer via Convolution Neural Networks for Multi-Resolution Lawn Weed Classification
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationFarooq, A; Jia, X; Hu, J; Zhou, J, Knowledge Transfer via Convolution Neural Networks for Multi-Resolution Lawn Weed Classification, Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing, 2019, 2019-September
dc.date.updated2020-04-02T02:14:12Z
gro.hasfulltextNo Full Text
gro.griffith.authorZhou, Jun


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record