Unsupervised Domain Adaptation for Nighttime Aerial Tracking

03/20/2022
by   Junjie Ye, et al.
0

Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications. This work instead develops a novel unsupervised domain adaptation framework for nighttime aerial tracking (named UDAT). Specifically, a unique object discovery approach is provided to generate training patches from raw nighttime tracking videos. To tackle the domain discrepancy, we employ a Transformer-based bridging layer post to the feature extractor to align image features from both domains. With a Transformer day/night feature discriminator, the daytime tracking model is adversarially trained to track at night. Moreover, we construct a pioneering benchmark namely NAT2021 for unsupervised domain adaptive nighttime tracking, which comprises a test set of 180 manually annotated tracking sequences and a train set of over 276k unlabelled nighttime tracking frames. Exhaustive experiments demonstrate the robustness and domain adaptability of the proposed framework in nighttime aerial tracking. The code and benchmark are available at https://github.com/vision4robotics/UDAT.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

page 8

research
01/25/2023

Tracking Different Ant Species: An Unsupervised Domain Adaptation Framework and a Dataset for Multi-object Tracking

Tracking individuals is a vital part of many experiments conducted to un...
research
12/06/2017

Stretching Domain Adaptation: How far is too far?

While deep learning has led to significant advances in visual recognitio...
research
12/14/2014

Unsupervised Domain Adaptation with Feature Embeddings

Representation learning is the dominant technique for unsupervised domai...
research
10/12/2019

Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation

Recent works on domain adaptation exploit adversarial training to obtain...
research
12/01/2022

CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection

Domain adaptation for Cross-LiDAR 3D detection is challenging due to the...
research
07/07/2022

EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022: Team HNU-FPV Technical Report

In this report, we present the technical details of our submission to th...
research
04/05/2023

Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial Video

This paper presents an unsupervised approach that leverages raw aerial v...

Please sign up or login with your details

Forgot password? Click here to reset