Xiaomao Li

Dr. Xiaomao Li

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
9 October 2020 in Autonomous Robots
Verified
Journal Article
Closed access
PDF file
BZBo Zhou
Bo Zhou
YHYi He
Yi He
KQKun Qian
Kun Qian
XMXudong Ma
Xudong Ma
XLXiaomao Li
Xiaomao Li

24 February 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
WXWeiping Xiao
Weiping Xiao
YPYan Peng
Yan Peng
CLChang Liu
Chang Liu
JGJiantao Gao
Jiantao Gao
YWYiqiang Wu
Yiqiang Wu
XLXiaomao Li
Xiaomao Li
Accurately detecting multi-class objects in a single pass is critical but challenging for real-world autonomous driving scenarios. Several single-class anchor-based methods have recently achieved the state-of-the-art performance in the car category, but when extending to multi-class detection tasks, their performance on small objects ( i.e ., pedestrians and cyclists) is limited. We find that the core problem that causes this phenomenon lies in the unbalanced sample quality and the classification objective. To address this problem, we proposed a single-model multi-class 3D object detector with balanced sample assignment and objective, named BSAODet. Specifically, the quality-balanced sample assignment (QBSA) is introduced to dynamically collect stable high-quality samples for each class according to the predicted sample performance and geometric constraints. In conjunction with the QBSA, the class-balanced classification objective (CBCO) performs instance-wise label normalization and weighting on positive samples, preventing the model from biasing toward objects with more samples. Extensive experiments on the popular KITTI dataset, the latest large-scale ONCE dataset, and the challenging Waymo Open Dataset show that our method steadily improves the performance of current state-of-the-art detectors by 2–7 mAP in pedestrians and cyclists while maintaining competitiveness in cars. Moreover, our best model achieves 66.31 mAP on three classes, outperforming all published LiDAR-only detectors on the KITTI benchmark.

11 January 2024 in IEEE Journal of Oceanic Engineering
Verified
Journal Article
Closed access
FLFei Li
Fei Li
XLXiaomao Li
Xiaomao Li
YPYan Peng
Yan Peng
BLBin Li
Bin Li
YZYang Zhai
Yang Zhai
Underwater images typically exhibit color distortion and poor visibility due to light absorption and scattering. Currently, existing methods always overcompensate for degraded color and contrast due to a lack of adaptation, which results in an unnatural appearance and contrast loss. This article combines the merits of conventional color transfer technology and dehazing to improve underwater image quality while addressing the aforementioned problems. Specifically, a maximum information transfer method that does not require a reference image to adaptively correct the color of an input image is first proposed. Built on maximizing contrast while minimizing contrast loss, an adaptive full dynamic range mapping (AFDRM) strategy is then proposed to guide dehazing to restore the visibility. Our method can produce vivid results without introducing over enhancement and is applicable to a variety of underwater environments. Furthermore, with our sufficient and reasonable proof, our method is extended and applied to low-light image enhancement (LLIE) by fine-tuning parameters in this article. Extensive experiments demonstrate that our method achieves superior color correction and contrast enhancement, as well as remarkable performance in underwater applications and low-light scenes, even for foggy images taken at nighttime and daytime.

3 June 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
CWChengwei Wei
Chengwei Wei
YBYunfei Bai
Yunfei Bai
CLChang Liu
Chang Liu
YZYuhe Zhu
Yuhe Zhu
CWCaiju Wang
Caiju Wang
XLXiaomao Li
Xiaomao Li
Underwater object detection based on side-scan sonar (SSS) suffers from a lack of finely annotated data. This study aims to avoid the laborious task of annotation by achieving unsupervised underwater object detection through domain-adaptive object detection (DAOD). In DAOD, there exists a conflict between feature transferability and discriminability, suppressing the detection performance. To address this challenge, a domain collaborative bridging detector (DCBD) including intra-domain consistency constraint (IDCC) and domain collaborative bridging (DCB), is proposed. On one hand, previous static domain labels in adversarial-based methods hinder the domain discriminator from discerning subtle intra-domain discrepancies, thus decreasing feature transferability. IDCC addresses this by introducing contrastive learning to refine intra-domain similarity. On the other hand, DAOD encourages the feature extractor to extract domain-invariant features, overlooking potential discriminative signals embedded within domain attributes. DCB addresses this by complementing domain-invariant features with domain-relevant information, thereby bolstering feature discriminability. The feasibility of DCBD is validated using unlabeled underwater shipwrecks as a case study. Experiments show that our method achieves accuracy comparable to fully supervised methods in unsupervised SSS detection (92.16% AP50 and 98.50% recall), and achieves 52.6% AP50 on the famous benchmark dataset Foggy Cityscapes, exceeding the original state-of-the-art by 4.5%.

9 April 2022 in Journal of Intelligent & Robotic Systems
Verified
Journal Article
Closed access
PDF file
BZBo Zhou
Bo Zhou
YHYi He
Yi He
WHWenchao Huang
Wenchao Huang
XYXiang Yu
Xiang Yu
FFFang Fang
Fang Fang
XLXiaomao Li
Xiaomao Li

Verified
Journal Article
Open access
PDF file
JGJiantao Gao
Jiantao Gao
JZJingting Zhang
Jingting Zhang
Chang LiuChang Liu
Chang Liu
XLXiaomao Li
Xiaomao Li
YPYan Peng
Yan Peng
Water segmentation is essential for the autonomous driving system of unmanned surface vehicles (USVs), which provides reliable navigation for making safety decisions. However, existing methods have only used monocular images as input, which often suffer from the changes in illumination and weather. Compared with monocular images, LiDAR point clouds can be collected independently of ambient light and provide sufficient 3D information but lack the color and texture that images own. Thus, in this paper, we propose a novel camera-LiDAR cross-modality fusion water segmentation method, which combines the data characteristics of the 2D image and 3D LiDAR point cloud in water segmentation for the first time. Specifically, the 3D point clouds are first supplemented with 2D color and texture information from the images and then distinguished into water surface points and non-water points by the early 3D cross-modality segmentation module. Subsequently, the 3D segmentation results and features are fed into the late 2D cross-modality segmentation module to perform 2D water segmentation. Finally, the 2D and 3D water segmentation results are fused for the refinement by an uncertainty-aware cross-modality fusion module. We further collect, annotate and present a novel Cross-modality Water Segmentation (CMWS) dataset to validate our proposed method. To the best of our knowledge, this is the first water segmentation dataset for USVs in inland waterways consisting of images and corresponding point clouds. Extensive experiments on the CMWS dataset demonstrate that our proposed method can significantly improve image-only-based methods, achieving improvements in accuracy and MaxF of approximately 2% for all the image-only-based methods.