Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
An Efficient Detection Framework for Aerial Imagery Based on Uniform Slicing Window
Published in Remote Sensing, 2023
Drone object detection faces numerous challenges such as dense clusters with overlapping, scale diversity, and long-tail distributions. Utilizing tiling inference through uniform sliding window is an effective way of enlarging tiny objects and meanwhile efficient for real-world applications. However, merely partitioning input images may result in heavy truncation and an unexpected performance drop in large objects. Therefore, in this work, we strive to develop an improved tiling detection framework with both competitive performance and high efficiency. First, we formulate the tiling inference and training pipeline with a mixed data strategy. To avoid truncation and handle objects at all scales, we simultaneously perform global detection on the original image and local detection on corresponding sub-patches, employing appropriate patch settings. Correspondingly, the training data includes both original images and the patches generated by random online anchor-cropping, which can ensure the effectiveness of patches and enrich the image scenarios. Furthermore, a scale filtering mechanism is applied to assign objects at diverse scales to global and local detection tasks to keep the scale invariance of a detector and obtain optimal fused predictions. As most of the additional operations are performed in parallel, the tiling inference remains highly efficient. Additionally, we devise two augmentations customized for tiling detection to effectively increase valid annotations, which can generate more challenging drone scenarios and simulate the practical cluster with overlapping, especially for rare categories. Comprehensive experiments on both public drone benchmarks and our customized real-world images demonstrate that, in comparison to other drone detection frameworks, the proposed tiling framework can significantly improve the performance of general detectors in drone scenarios with lower additional computational costs.
Recommended citation: Yang, X.; Song, Y.; Zhou, Y.; Liao, Y.; Yang, J.; Huang, J.; Huang, Y.; Bai, Y. An Efficient Detection Framework for Aerial Imagery Based on Uniform Slicing Window. Remote Sens. 2023, 15, 4122.
Download Paper
Multispectral Sample Augmentation and Illumination Guidance for RGB-T Object Detection by MMDetection Framework
Published in 2024 International Conference on Computer Network and Cloud Computing (CNCC 2024), 2024
Multispectral object detection technology has important application prospects in the fields of autonomous driving and so on. Conventional multispectral object detection algorithm rely solely on deep neural networks to learn multispectral image sample information, lacking the guidance of prior knowledge, and not fully utilizing infrared, visible, and other spectral information, resulting in decreased accuracy of object detection in complex scenes. To address this problem, this paper proposes an object detection algorithm based on infrared visible sample augmentation and illumination guidance. The algorithm adopts the MMDetection framework and extracts multispectral object features based on a designed sample augmentation method based on the fusion of positive and negative samples in multispectral images. Based on a designed adaptive weight allocation method guided by illumination, it enhances the algorithm’s adaptability to the lighting environment. Finally, through the design of a multi-task loss function, it achieves high-precision and robust object detection in complex scenes.
Recommended citation: Jinqi Yang, Xin Yang, Yizhao Liao, Jinxiang Huang, Hongyu He, Erfan Zhang, Ya Zhou, Yong Song*. Multispectral Sample Augmentation and Illumination Guidance for RGB-T Object Detection by MMDetection Framework[C]. 2024 4th International Conference on Laser, Optics and Optoelectronic Technology.
Download Paper
Light Siamese Network for Long-Term Onboard Aerial Tracking
Published in IEEE Transactions on Geoscience and Remote Sensing, 2024
The scarce onboard computational resources and real-time demand restrict the deployment of aerial trackers with sophisticated structures and customized operators. Meanwhile, aerial trackers need updating modules to adapt to continuous appearance variations in real-world long-term (LT) scenarios. However, frequent updating will introduce noisy templates and lead to tracking drifts and efficiency drops. Therefore, in this work, we develop a lightweight and highly efficient Siamese tracker for LT onboard aerial tracking applications. First, we build a compact, plain, and deployment-friendly Siamese network based on re-parameterization (Rep) as the baseline short-term (ST) tracker. Furthermore, we propose a tracking-specific decoupled knowledge distillation (KD) guided by strict teachers to unleash the appearance representation potential of the feature extractor without extra inference cost. Specifically, before distillation, the teacher conducts qualification verification to avoid misguiding the student. Then, hard negative background regions are mined and decoupled with the target region, encouraging the student to focus more on similar distractors and informative areas. Finally, to realize efficient and high-confidence LT tracking, we design two extensions and incorporate them into the boosted ST tracker: an initial-template-driven template updater with a corresponding pair-generating strategy to alleviate appearance pollution, and a confidence estimating branch to determine whether to update. Extensive results on large-scale drone benchmarks indicate that our proposed tracker significantly outperforms state-of-the-art (SOTA) aerial trackers. Real-world tests on our customized drone-captured LT dataset also validate its favorable practicability with a real-time speed of 44 fps on the Lynix KA200 chip.
Recommended citation: X. Yang, J. Huang, Y. Liao, Y. Song, Y. Zhou and J. Yang, "Light Siamese Network for Long-Term Onboard Aerial Tracking," in IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-15, 2024.
Download Paper
RDR-KD: A Knowledge Distillation Detection Framework for Drone Scenes
Published in IEEE Geoscience and Remote Sensing Letters, 2024
Drone object detection (DOD) with real-time deployment is a research hotspot. On the one hand, the performance of tiny object detection is closely related to the ground detection capability of the drone platform. Existing methods are keen on designing complex networks to enhance the accuracy of tiny objects, which significantly increases computational costs. On the other hand, the limited drone hardware resources urgently require lightweight models for deployment. To address the dilemma of balancing detection accuracy and computational efficiency, we propose a regenerated-decoupled-responsive knowledge distillation (RDR-KD) framework specifically for drone scenes. First, we design the Regenerated Distillation and the Decoupled Distillation to fully transfer the tiny object feature information from the teacher model to the student model. Meanwhile, we devise the logit-based Responsive Distillation based on focal loss and efficient intersection over union (EIoU) to alleviate class imbalance. Finally, we conduct extensive experiments on the VisDrone2019 dataset. The experimental results demonstrate that the proposed RDR-KD framework improves AP and AP_S of the student model by 3.3% and 2.9% respectively, which outperforms other state-of-the-art distillation frameworks.
Recommended citation: J. Huang, H. Chang, X. Yang, Y. Liu, S. Liu and Y. Song, "RDR-KD: A Knowledge Distillation Detection Framework for Drone Scenes," in IEEE Geoscience and Remote Sensing Letters, vol. 21, pp. 1-5, 2024
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.