Shengjian Bai

Shengjian Bai

Auto-generated profile, based on publicly available information

Shengjian Bai

National University of Defense Technology

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 March 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
PSPeng Sun
Peng Sun
YZYongbin Zheng
Yongbin Zheng
WWWenqi Wu
Wenqi Wu
WXWanying Xu
Wanying Xu
SBShengjian Bai
Shengjian Bai
XLXiaoping Lu
Xiaoping Lu
Arbitrary-oriented object detection in remote sensing optical images is an emerging yet challenging task due to the diversity of the visual appearance of objects. Although considerable progress has been made, existing methods often suffer from insufficient positive samples and critical feature misalignment caused by objects with considerable diversity. In this paper, we propose a critical feature learning (CFL) method to address the above issues. First, to obtain a more accurate location, we introduce the spatial transform to model the rotating bounding box regression and construct a spatial transform selection (STS) strategy, which is used to implement dynamic sample selection metrics to guarantee sufficient positive samples. Then, we propose a scale-controlled smooth L 1 loss (SC-Loss) to change the form of regression loss function based on the statistics of proposals so that the training can focus more on high-quality samples. Finally, to capture critical features, we propose a critical feature sampling (CFS) module to perform location refinement of classification feature samples to extract accurate features. Comprehensive and extensive experimental results based on three benchmarks, DOTA, FAIR1M-1.0, and HRSC2016, demonstrate that the proposed method is superior to existing methods in terms of accuracy and effectiveness.

1 August 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JYJiansong Yang
Jiansong Yang
YZYongbin Zheng
Yongbin Zheng
WXWanying Xu
Wanying Xu
PSPeng Sun
Peng Sun
SBShengjian Bai
Shengjian Bai
Deep learning-based template matching in remote sensing has received increasing research attention. Existing anchor box-based and anchor-free methods often suffer from low template localization accuracy in the presence of multimodal, nonrigid deformation and occlusion. To address this problem, we transform the template matching task into a center-point localization task for the first time and propose an end-to-end template matching method based on a novel fully convolutional Siamese network. Furthermore, we propose an adaptive shrinkage cross-correlation scheme, which improves the precision of template localization and alleviates the impact of background clutter without adding any parameters. We also design a scheme that leverages keypoint information to assist in locating the template center, thereby enhancing the precision of template localization. We construct a multimodal template matching dataset to verify the performance of the method in dealing with differences in view, scale, rotation and occlusion in practical application scenarios. Extensive experiments on a public dataset, OTB, the proposed dataset, as well as a remote sensing dataset, SEN1-2, demonstrate that our method achieves state-of-the-art performance.

4 March 2025
Verified
Book Chapter
Closed access
PDF file
RXRui Xu
Rui Xu
BXBing Xie
Bing Xie
XGXueqiang Gu
Xueqiang Gu
SBShengjian Bai
Shengjian Bai

10 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
PSPeng Sun
Peng Sun
YZYongbin Zheng
Yongbin Zheng
WWWenqi Wu
Wenqi Wu
WXWanying Xu
Wanying Xu
SBShengjian Bai
Shengjian Bai
Arbitrary-oriented object detection is a relatively emerging but challenging task. Although remarkable progress has been made, there still remain many unsolved issues due to the large diversity of patterns in orientation, scale, aspect ratio, and visual appearance of objects in aerial images. Most of the existing methods adopt a coarse-grained fixed label assignment strategy and suffer from the inconsistency between the classification score and localization accuracy. First, to align the metric inconsistency between sample selection and regression loss calculation caused by fixed IoU strategy, we introduce affine transformation to evaluate the quality of samples and propose a distance-based label assignment strategy. The proposed metric-aligned selection (MAS) strategy can dynamically select samples according to the shape and rotation characteristic of objects. Second, to further address the inconsistency between classification and localization, we propose a critical feature sampling (CFS) module, which performs localization refinement on the sampling location for classification task to extract critical features accurately. Third, we present a scale-controlled smooth $L_1$ loss (SC-Loss) to adaptively select high quality samples by changing the form of regression loss function based on the statistics of proposals during training. Extensive experiments are conducted on four challenging rotated object detection datasets DOTA, FAIR1M-1.0, HRSC2016, and UCAS-AOD. The results show the state-of-the-art accuracy of the proposed detector.

2 March 2025
Verified
Book Chapter
Closed access
PDF file
WXWanying Xu
Wanying Xu
DYDongxu Yang
Dongxu Yang
YZYongbin Zheng
Yongbin Zheng
PSPeng Sun
Peng Sun
SBShengjian Bai
Shengjian Bai