Road Anomaly Detection by Partial Image Reconstruction with Segmentation Coupling

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00354693" target="_blank" >RIV/68407700:21230/21:00354693 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICCV48922.2021.01536" target="_blank" >https://doi.org/10.1109/ICCV48922.2021.01536</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCV48922.2021.01536" target="_blank" >10.1109/ICCV48922.2021.01536</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Road Anomaly Detection by Partial Image Reconstruction with Segmentation Coupling

Popis výsledku v původním jazyce

We present a novel approach to the detection of unknownobjects in the context of autonomous driving. The problemis formulated as anomaly detection, since we assume thatthe unknown stuff or object appearance cannot be learned.To that end, we propose a reconstruction module that can beused with many existing semantic segmentation networks,and that is trained to recognize and reconstruct road (driv-able) surface from a small bottleneck. We postulate thatpoor reconstruction of the road surface is due to areas thatare outside of the training distribution, which is a strong in-dicator of an anomaly. The road structural similarity erroris coupled with the semantic segmentation to incorporateinformation from known classes and produce final per-pixelanomaly scores. The proposed JSR-Net was evaluated onfour datasets, Lost-and-found, Road Anomaly, Road Obsta-cles, and FishyScapes, achieving state-of-art performanceon all, reducing the false positives significantly, while typ-ically having the highest average precision for wide rangeof operation points.

Název v anglickém jazyce

Road Anomaly Detection by Partial Image Reconstruction with Segmentation Coupling

Popis výsledku anglicky

We present a novel approach to the detection of unknownobjects in the context of autonomous driving. The problemis formulated as anomaly detection, since we assume thatthe unknown stuff or object appearance cannot be learned.To that end, we propose a reconstruction module that can beused with many existing semantic segmentation networks,and that is trained to recognize and reconstruct road (driv-able) surface from a small bottleneck. We postulate thatpoor reconstruction of the road surface is due to areas thatare outside of the training distribution, which is a strong in-dicator of an anomaly. The road structural similarity erroris coupled with the semantic segmentation to incorporateinformation from known classes and produce final per-pixelanomaly scores. The proposed JSR-Net was evaluated onfour datasets, Lost-and-found, Road Anomaly, Road Obsta-cles, and FishyScapes, achieving state-of-art performanceon all, reducing the false positives significantly, while typ-ically having the highest average precision for wide rangeof operation points.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ICCV2021: Proceedings of the International Conference on Computer Vision

ISBN

978-1-6654-2812-5

ISSN

1550-5499

e-ISSN

2380-7504

Počet stran výsledku

10

Strana od-do

15651-15660

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Montreal

Datum konání akce

11. 10. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—