Rare-class extraction using cascaded pretrained networks applied to crane classification

Sander R. Klomp, Guido Brouwers, R.G.J. Wijnhoven, Peter H.N. de With

Onderzoeksoutput: Bijdrage aan congresPaperAcademic


Overweight vehicles are a common source of pavement and
bridge damage. Especially mobile crane vehicles are often beyond legal per-axle weight limits, carrying their lifting blocks and
ballast on the vehicle instead of on a separate trailer. To prevent
road deterioration, the detection of overweight cranes is desirable
for law enforcement. As the source of crane weight is visible, we
propose a camera-based detection system based on convolutional
neural networks. We iteratively label our dataset to vastly reduce
labeling and extensively investigate the impact of image resolution, network depth and dataset size to choose optimal parameters during iterative labeling. We show that iterative labeling
with intelligently chosen image resolutions and network depths
can vastly improve (up to 70×) the speed at which data can be
labeled, to train classification systems for practical surveillance
applications. The experiments provide an estimate of the optimal amount of data required to train an effective classification
system, which is valuable for classification problems in general.
The proposed system achieves an AUC score of 0.985 for distinguishing cranes from other vehicles and an AUC of 0.92 and 0.77
on lifting block and ballast classification, respectively. The proposed classification system enables effective road monitoring for
semi-automatic law enforcement and is attractive for rare-class
extraction in general surveillance classification problems.
Originele taal-2Engels
Aantal pagina's6
StatusGepubliceerd - 26 jan 2020
EvenementElectronic Imaging 2020: Intelligent Robotics and Industrial Applications using Computer Vision - Hyatt Regency San Francisco Airport, Burlingame, Verenigde Staten van Amerika
Duur: 26 jan 202030 jan 2020


CongresElectronic Imaging 2020
LandVerenigde Staten van Amerika
Internet adres

Vingerafdruk Duik in de onderzoeksthema's van 'Rare-class extraction using cascaded pretrained networks applied to crane classification'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Klomp, S. R., Brouwers, G., Wijnhoven, R. G. J., & de With, P. H. N. (2020). Rare-class extraction using cascaded pretrained networks applied to crane classification. Paper gepresenteerd op Electronic Imaging 2020, Burlingame, Verenigde Staten van Amerika. https://doi.org/10.2352/ISSN.2470-1173.2020.6.IRIACV-049