ABSTRACT
This challenge is divided into two stages: qualification and final competition. We will acquire regular image data and need to perform detection on images with a fisheye effect. The approach described in this context begins by taking the original images and transforming them to mimic fisheye effect images for training. Furthermore, this challenge imposes limitations on computational resources, so striking a balance between accuracy and speed is a crucial aspect. In this paper, we asserted that our approach for this competition can achieve high performance with just one epoch of training. In summary, we achieved the top position among 24 participating teams in the qualification competition and secured the fourth position among the 11 successful submitted teams in the final competition. The corresponding source code will be available at: One-Epoch Training for Object Detection in Fisheye Images.
- Chun-Hao Chao, Pin-Lun Hsu, Hung-Yi Lee, and Yu-Chiang Frank Wang. 2020. Self-supervised deep learning for fisheye image rectification. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2248–2252.Google ScholarCross Ref
- Xun Cheng and Jianbo Yu. 2020. RetinaNet with difference channel attention and adaptively spatial feature fusion for steel surface defect detection. IEEE Transactions on Instrumentation and Measurement 70 (2020), 1–11.Google Scholar
- Ekin D Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, and Quoc V Le. 2018. Autoaugment: Learning augmentation policies from data. arXiv preprint arXiv:1805.09501 (2018).Google Scholar
- Zhihao Duan, Ozan Tezcan, Hayato Nakamura, Prakash Ishwar, and Janusz Konrad. 2020. Rapid: rotation-aware people detection in overhead fisheye images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 636–637.Google ScholarCross Ref
- Siqi Fan. 2018. Conversion Tool for FishEye Dataset. https://github.com/leofansq/Tools_KITTI2FishEyeGoogle Scholar
- Munkhjargal Gochoo, Munkh-Erdene Otgonbold, Erkhembayar Ganbold, Jun-Wei Hsieh, Ming-Ching Chang, Ping-Yang Chen, Byambaa Dorj, Hamad Al Jassmi, Ganzorig Batnasan, Fady Alnajjar, 2023. FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5304–5312.Google ScholarCross Ref
- Aran Komatsuzaki. 2019. One epoch is all you need. arXiv preprint arXiv:1906.06669 (2019).Google Scholar
- Brett Koonce and Brett Koonce. 2021. EfficientNet. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization (2021), 109–123.Google ScholarCross Ref
- Oded Krams and Nahum Kiryati. 2017. People detection in top-view fisheye imaging. In 2017 14th IEEE international conference on advanced video and signal based surveillance (AVSS). IEEE, 1–6.Google ScholarCross Ref
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012).Google Scholar
- Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740–755.Google ScholarCross Ref
- Zhiqiu Lin, Jin Sun, Abe Davis, and Noah Snavely. 2020. Visual chirality. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12295–12303.Google ScholarCross Ref
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer, 21–37.Google Scholar
- I-chan Lo, Kuang-tsu Shih, and Homer H Chen. 2018. Image stitching for dual fisheye cameras. In 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 3164–3168.Google Scholar
- Yen-Sok Poon, Chih-Chun Lin, Yu-Hsuan Liu, and Chih-Peng Fan. 2022. YOLO-based deep learning design for in-cabin monitoring system with fisheye-lens camera. In 2022 IEEE International Conference on Consumer Electronics (ICCE). IEEE, 1–4.Google ScholarCross Ref
- Hazem Rashed, Eslam Mohamed, Ganesh Sistu, Varun Ravi Kumar, Ciarán Eising, Ahmad El-Sallab, and SK Yogamani. 2020. FisheyeYOLO: Object detection on fisheye cameras for autonomous driving. In Proceedings of the Machine Learning for Autonomous Driving NeurIPS 2020 Virtual Workshop, Virtual, Vol. 11.Google Scholar
- Hazem Rashed, Eslam Mohamed, Ganesh Sistu, Varun Ravi Kumar, Ciaran Eising, Ahmad El-Sallab, and Senthil Yogamani. 2021. Generalized object detection on fisheye cameras for autonomous driving: Dataset, representations and baseline. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2272–2280.Google ScholarCross Ref
- Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105–6114.Google Scholar
- Shengbang Tong, Yubei Chen, Yi Ma, and Yann Lecun. 2023. EMP-SSL: Towards Self-Supervised Learning in One Training Epoch. arXiv preprint arXiv:2304.03977 (2023).Google Scholar
- wufish | NYCU PAIR Labs. 2022. iVS-Dataset. https://pairlabs.nycu.edu.tw:52959/?p=28Google Scholar
- Senthil Yogamani, Ciaran Hughes, Jonathan Horgan, Ganesh Sistu, Padraig Varley, Derek O’Dea, Michal Uricar, Stefan Milz, Martin Simon, Karl Amende, Christian Witt, Hazem Rashed, Sumanth Chennupati, Sanjaya Nayak, Saquib Mansoor, Xavier Perrotton, and Patrick Perez. 2019. WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/ICCV.2019.00940Google ScholarCross Ref
Index Terms
- One-Epoch Training for Object Detection in Fisheye Images
Recommendations
Training object detectors from few weakly-labeled and many unlabeled images
Highlights- A novel method to train detector by few weakly-labeled images and lots of unlabeled images.
AbstractWeakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training ...
Few training data for Objection Detection
EITCE '20: Proceedings of the 2020 4th International Conference on Electronic Information Technology and Computer EngineeringDeep learning method of object detection has achieved excellent results, but most of the object detection network training processes are supervised learning. The performance improvement is driven by a large amount of annotation data to drive deeper and ...
On rendering synthetic images for training an object detector
We propose a novel approach to generating synthetic training data.We introduce detector-specific similarity measures between real and synthetic images.We show that the choice of the similarity measure relies on the features used by the detector.We have ...
Comments