MGMing Gao

Ming Gao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ming Gao has a total of 68 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • LVMSOD: Lightweight Visual Mamba Small Object Detection for Autonomous Vehicles

    by Yao Fu, Ming Gao, Yinlin Wang, Xin Deng, Yang Li, Manjiang Hu, Yougang Bian, Rongjun Ding

    The application of object detection in industrial transportation has witnessed substantial advancements, yielding significant enhancements in both safety and efficiency. While Transformer-based detectors have demonstrated remarkable success in object detection for autonomous driving, their quadratic computational complexity and limited small object perception capabilities remain significant challenges. To address these limitations, we propose a lightweight visual Mamba small object detection (LVMSOD) method, a novel selective state space model (SSM) designed for small object detection (SOD) task. The proposed framework employs a multilevel cascade of dual-layer nested Mamba modules to comprehensively capture contextual information across different scales, coupled with a hierarchical feature fusion strategy to enhance multiscale feature integration for improved SOD. The LVMSOD framework incorporates two key components to enhance feature representation: visual Mamba detection (VDM) block that preserves fine-grained image details and lightweight gated multilayer perceptron (LGMLP) designed to model local feature dependencies efficiently. Furthermore, we propose an optimized feature extraction mechanism employing depthwise and pointwise convolutions with distribution factors, significantly reducing computational overhead while maintaining detection accuracy. Comprehensive evaluations on benchmark datasets demonstrate the effectiveness of our approach, achieving mAP@0.5 scores of 93.3% on KITTI and 45.3% on VisDrone while maintaining superior computational efficiency. These results highlight the potential of LVMSOD for efficient and accurate SOD.


  • Top Cited Papers

    Criticality Assessment Model for Intelligent Vehicle Test Scenario Based on Interactive Field Feature and Hypergraph Learning

    by Yinzi Huang, Bing Zhu, Jian Zhao, Jiayi Han, Dongjian Song, Peixing Zhang, Shizheng Jia, Ming Gao

    Scenario-based testing is an important part in intelligent vehicle (IV) development. The data volume of collected test scenarios is extremely large, and directly using all collected scenarios to test IVs will lead to extremely low testing efficiency. To solve this problem, a criticality assessment model (CAM) for IV test scenario based on interactive field feature (IFF) and hypergraph learning is proposed to quantify the test scenario criticality to improve the test efficiency. The IFF is constructed based on the potential field-based method to integrally consider the multidimensional coupling of scenario elements. In addition, the interaction between the fields generated by the ego vehicle and the driving environment is modeled based on Delaunay triangulation discretization method to accurately quantify the driving environment risk to the ego vehicle. The node and hyperedge of the hypergraph are used to model the individual dynamic evolution and group interaction characteristics of vehicles, respectively. Subsequently, a hypergraph learning network is constructed to extract features from the built hypergraph, IFF and traffic elements. Finally, the effectiveness, reasonableness and accuracy validation experiments are designed to validate the proposed CAM. Ablation experiment results show that the proposed IFF and hypergraph learning network enhance the CAM accuracy. The reasonableness validation results show that the proposed CAM can better find critical test scenarios than time-to-collision and time-head-way methods. The accuracy of the proposed CAM is compared through four real validation scenarios in the proving ground. The comparison results show that the proposed CAM can accurately output the quantified test scenario criticality.


  • MOAT: Multi-Scale Group Interaction Transformer for Trajectory Prediction in Crowded Scenes

    by Ming Gao, Tong Wang, Yinlin Wang, Guotao Xie, Chi Ding, Yougang Bian

    Predicting pedestrian trajectories in complex environments presents a significant challenge for autonomous driving systems, primarily due to the intricate social interactions among pedestrians and their surrounding groups. Existing methods often struggle to fully capture the impact of group behavior on individual movement. To address these limitations, we propose the Multi-scale Group Interaction Transformer (MOAT) for pedestrian trajectory prediction in high-density, complex scenarios. Our approach introduces a dynamic group interaction module (DGIM) that clusters pedestrians based on proximity, determined by a distance matrix of neighboring pedestrians. In constructing interaction representations, we go beyond traditional features like speed, distance, and direction by incorporating crowd density, thus providing a more comprehensive understanding of group dynamics. To effectively process these features, we employ a multi-branch attention fusion (MBAF) module, which independently analyzes each feature set to capture the unique dynamics and density characteristics of each group and their varying effects on the target pedestrian. These spatial features are then combined with temporal information, allowing our model to account for both spatial and temporal dependencies. Additionally, we leverage a multi-scale Transformer to adaptively partition input trajectories, enhancing the model’s ability to capture dynamic patterns across various scales. Extensive evaluations on benchmark datasets show that our approach consistently outperforms state-of-the-art methods in terms of both prediction accuracy and robustness.


  • Hybrid Matching Teacher Framework for Cross-Domain Visual Detection Transformer

    by Xiaowei Wang, Jinhui Suo, Yang Li, Ming Gao, Peiwen Jiang, Pengwen Dai

    Object detection is a critical component of autonomous vehicle perception systems. However, domain shifts between training environments and real-world scenarios often degrade detector performance. Cross-domain object detection aims to adapt detectors to unlabeled target domains utilizing only labeled source data. Recent popular cross-domain object detection methods employ the mean teacher framework, which uses pseudo-labels generated by the teacher model to guide training on unlabeled real-world data. Despite its effectiveness, continuous training with noisy pseudo-labels leads to abnormal performance degradation in the later stages of training. To address this issue, we propose a novel Hybrid Matching Teacher (HMT) framework for cross-domain visual detection transformers, which enhances cross-domain knowledge transfer across pseudo-label generation, filtering, and training processes. Specifically, we design a Feature Sparse Alignment (FSA) module to adapt DETR tokens and queries, generate domain-adaptive weights to initialize the teacher-student models, and mitigate the inherent initial source bias in the teacher model. Next, a Localization-aware Pseudo-label Filtering (LPF) module ensures high-quality pseudo-labels by considering the consistency between localization and classification tasks. Furthermore, to improve the efficiency of pseudo-label training, the Cross-view Hybrid Matching (CHM) module introduces an auxiliary matching branch to increase the number of positive queries that match with pseudo-labels. Extensive experiments demonstrate that our approach achieves state-of-the-art performance, outperforming previous benchmarks by 3.1%, 8.5%, and 4.4% in adverse weather, diverse scenes, and synthetic-to-real, respectively.


  • Roadside Visual Sensor Deployment in Urban Networks Considering Vehicle Control Boundary

    by Qing Xu, Li Zeng, Ming Gao, Zhengye Lu, Guotao Xie

    Reasonable deployment of roadside perception sensors is important for Intelligent and Connected Vehicles. This paper proposes a novel roadside camera deployment method that considers control security boundary. We firstly establish a roadside camera geometry model to determine an object’s presence within the perception domain. Then, a novel camera localization error model is developed, relating allowable localization errors to maximum camera perception range. Then, by integrating vehicle lateral and longitudinal control models, an analysis framework for allowable error is introduced to define the control error boundaries for assisting in determining the maximal perception range. Subsequently, based on the camera geometry model and considering allowable localization errors, an equivalent camera group model is constructed by using greedy search method for multiple identical roadside cameras, which aims to achieve a wider longitudinal field of view. Lastly, leveraging the camera group model, a dynamic programming optimization method is employed to deploy roadside camera in a flexible decision pattern along road centerline. And the effectiveness of our works is validated through a joint simulation experiment on real-world road network. The results show that the proposed camera group model can achieve optimal sensor deployment under the premise of ensuring the safety of vehicle’s control performance.


  • DiffWT: Diffusion-Based Pedestrian Trajectory Prediction With Time-Frequency Wavelet Transform

    by Xin Chen, Li Zeng, Ming Gao, Chi Ding, Yougang Bian

    Accurate pedestrian trajectory prediction is a crucial task for ensuring the safety of autonomous driving. However, most of the existing methods only model pedestrian trajectories in the spatial-temporal domain, which results in a lack of analysis of motion at different scales. In this work, we propose a framework based on wavelet transform and diffusion model, which is called DiffWT. Different from previous approaches, our method employs a discrete wavelet transform (DWT) to perform time-frequency analysis of trajectories. The high-frequency component of the DWT indicates local motion details of the trajectory, while the low-frequency one represents overall motion trends. Secondly, we propose a trajectory decoder comprising a conditional diffusion model and a cross-constrained bi-directional trajectory generator (C2Bid). The diffusion model generates the distribution of implicit pedestrian behaviors by taking the multi-scale motion behaviors as conditions. Furthermore, the C2Bid module is designed as a cross-constrained bi-directional structure to decode behavioral distribution into multimodal trajectories. This trajectory decoder can generate precise distribution of trajectories and reduce accumulation of prediction errors. Extensive experimental results on the ETH/UCY and the Stanford drone datasets (SDD) demonstrate that our method achieves better performance as well as higher efficiency compared to other state-of-the-art approaches.