Unsupervised object detection via LWIR/RGB translation

Rachael Abbott, Jesus Martinez-del-Rincon, Neil Robertson, Barry Connor

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

1 Citation (Scopus)
283 Downloads (Pure)


In this work, we present two new methods to overcome the lack of annotated long-wavelength infrared (LWIR) databy exploiting the abundance of similar RGB imagery. We introduce a novel unsupervised adaptation to the cycle GANarchitecture for translating non-corresponding LWIR/RGBdatasets. Our ultimate goal is high detection rates in the synthetic RGB/real LWIR imagery using only RGB labelled imagery for training detection algorithms. We translate LWIR imagery to RGB, allowing us to use an RGB trained detection algorithm. We, thereby remove the need for labelled LWIR imagery for training detection algorithms. In addition, we translate RGB to LWIR to fine-tune a network for detection in real LWIR imagery. Experimental results show that our adaption helps to create synthetic RGB imagery with higher detection rates across two different datasets. We also find that combining the synthetic RGB and real LWIR imagery produces higher F1 scores on the RGB trained detection network. Fine-tuning detection networks with synthetic LWIR and testing with real LWIR imagery produce the highest F1 scores.
Original languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition Workshops: Proceedings
Publisher IEEE
Publication statusPublished - 28 Jul 2020
Event16th IEEE Workshop on Perception Beyond the Visible Spectrum - Seatle, United States
Duration: 14 Jun 2020 → …
Conference number: 16


Workshop16th IEEE Workshop on Perception Beyond the Visible Spectrum
Abbreviated titlePBVS
Country/TerritoryUnited States
Period14/06/2020 → …
Internet address


Dive into the research topics of 'Unsupervised object detection via LWIR/RGB translation'. Together they form a unique fingerprint.

Cite this