ECDNet: Efficient siamese convolutional network for real-time small object change detection from ground vehicles

Sander Klomp, Dennis van de Wouw, Peter de With

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

1 Citation (Scopus)
41 Downloads (Pure)

Abstract

Change detection from ground vehicles has various applications, such as the detection of roadside Improvised Explosive Devices (IEDs). Although IEDs are hidden, they are often accompanied by visible markers, which can be any kind of object. Because of this, any suspicious change in the environment compared to an earlier moment in time, should be detected. Little work has been published to solve this ill-posed problem using deep learning. This paper shows the feasibility of applying convolutional neural networks (CNNs) to HD video, to accurately predict the presence and location of such markers in real time. The network is trained for the detection of pixel-level changes in HD video, compared to an earlier reference recording. We investigate Siamese CNNs in combination with an encoder-decoder architecture and introduce a modified double-margin contrastive loss function, to achieve pixel-level change detection results. Our dataset consists of seven pairs of challenging real-world recordings with geo-tagged test objects. The proposed network architecture is capable of comparing two images of 1920×1440 pixels in 150 ms on a GTX1080Ti GPU. The proposed network significantly outperforms state-of-the-art networks and algorithms on our dataset in terms of F-1 score, on average by 0.28.
Original languageEnglish
Title of host publicationElectronic Imaging
Subtitle of host publicationIntelligent Robotics and Industrial Applications using Computer Vision 2019
PublisherIS&T
Number of pages7
DOIs
Publication statusPublished - 13 Jan 2019
EventElectronic Imaging: Intelligent Robotics and Industrial Applications using Computer Vision 2019 - Hyatt Regency San Francisco Airport, Burlingame, United States
Duration: 13 Jan 201917 Jan 2019

Conference

ConferenceElectronic Imaging
CountryUnited States
CityBurlingame
Period13/01/1917/01/19

Keywords

  • CNN
  • Change Detection
  • Contrastive Loss
  • Convolutional Neural Network
  • Encoder Decoder Network
  • Siamese Network

Fingerprint

Dive into the research topics of 'ECDNet: Efficient siamese convolutional network for real-time small object change detection from ground vehicles'. Together they form a unique fingerprint.

Cite this