Borrow From Anywhere: Pseudo Multi-Modal Object Detection in Thermal Imagery

@article{Devaguptapu2019BorrowFA,
  title={Borrow From Anywhere: Pseudo Multi-Modal Object Detection in Thermal Imagery},
  author={Chaitanya Devaguptapu and Ninad Akolekar and Manuj M Sharma and V. Balasubramanian},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2019},
  pages={1029-1038}
}
Can we improve detection in the thermal domain by borrowing features from rich domains like visual RGB? In this paper, we propose a pseudo-multimodal object detector trained on natural image domain data to help improve the performance of object detection in thermal images. We assume access to a large-scale dataset in the visual RGB domain and relatively smaller dataset (in terms of instances) in the thermal domain, as is common today. We propose the use of well-known image-to-image translation… Expand
Robust pedestrian detection in thermal imagery using synthesized images
Task-Conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery
Multispectral Domain Invariant Image for Retrieval-based Place Recognition
Every Feature Counts: An Improved One-Stage Detector in Thermal Imagery
Multi-Person Pose Estimation Using Thermal Images
Bottom-up and Layerwise Domain Adaptation for Pedestrian Detection in Thermal Images
Self-training Guided Adversarial Domain Adaptation For Thermal Imagery
...
1
2
3
...

References

SHOWING 1-10 OF 45 REFERENCES
Multispectral pedestrian detection: Benchmark dataset and baseline
Deep object classification in low resolution LWIR imagery via transfer learning
  • By
  • Computer Science
  • 2017
Fully Convolutional Region Proposal Networks for Multispectral Person Detection
Multi-spectral pedestrian detection based on accumulated object proposal with fully convolutional networks
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Microsoft COCO: Common Objects in Context
Multispectral Deep Neural Networks for Pedestrian Detection
Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness
Single-Shot Refinement Neural Network for Object Detection
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
...
1
2
3
4
5
...