YLYansha Lu

Yansha Lu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yansha Lu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Semantic Map Construction Under Complex Weather Scenarios

    by Hui Liu, Minhang Liu, Faliang Chang, Chunsheng Liu, Yansha Lu

    Semantic maps provide information on road elements, which is crucial for ensuring driving safety. However, previous methods mostly focus on normal weather conditions, neglecting the challenges of scene feature extraction caused by image degradation in complex weather scenarios. To address these challenges, we propose a Normal weather scene-guided Complex weather scene Map Construction Network (NCMC-Net). Firstly, we propose a scene Feature Sharing Module (FSM) based on the complement learning mechanism. This module alternately updates the shared feature pool with features from normal and complex weather scenes during two training stages. Secondly, we design a Feature Refinement Module (FRM) based on the channel attention mechanism to adjust the intensity of multi-channel features selectively. The two modules facilitate the extraction of optimal complex weather scene features guided by features from normal weather scenes. Experimental results on the complex weather scene dataset nuScenes-W validate our model’s performance.


  • SynergyPose: Synergy Enhanced Feature and Projection Decoupling for 6-D Pose Estimation

    by Hengqiang Huan, Faliang Chang, Chunsheng Liu, Wenqian Wang, Yansha Lu, Dexin Wang

    Estimating the 6D pose of texture-sparse objects is critical in vision-guided robotic manipulation and measurement. Existing single-RGB-based methods typically rely on multiple intermediate representations to improve accuracy, which increases computational and annotation costs. Alternatively, adopting a singular representation can mitigate these issues but it still suffers from feature scarcity, resulting in unreliable intermediate representation and pose estimation accuracy. Embracing these challenges, we propose a novel single-RGB-based framework named SynergyPose, which achieves accurate pose estimation of texture-sparse objects using only one intermediate representation. SynergyPose consists of three innovative components: Geometric Enhancer (GEer), Coordinate Projection Decoupling (CPD), and Consistency Constraint Loss (CCLoss). Specifically, we design a novel clustering branch based on feature aggregation and allocation within GEer, which synergistically extracts complementary features with a convolution branch to enhance feature representation. Based on the inter-projection coordinate consistency, we propose the CPD to capture the geometry of the object from different projection planes, which implicitly introduces multiple constraints to accurately calculate the dense correspondence without relying on other representations. Afterwards, CCLoss enforces coordinate consistency between the projection planes, explicitly introducing an additional constraint. Extensive experiments demonstrate the effectiveness of SynergyPose, which achieves competitive results on four BOP benchmark datasets.


  • Camera-Based Online Vectorized HD Map Construction With Incomplete Observation

    by Hui Liu, Faliang Chang, Chunsheng Liu, Yansha Lu, Minhang Liu

    Camera-based online map construction focuses on learning map elements from surround-view images. Distinguished with previous methods that rely on complete observations, we explore a new map construction problem under incomplete observations where one or more perspectives of the surround-view are missing due to camera damage or occlusion. Incomplete observations lead to inferior performance and may even result in failure. Map construction based on incomplete observations faces two challenges: supplementing missing perspective features and reducing the complexity of high-dimensional feature learning. To address these issues, we propose a novel Panoramic Observation Prior Network (POP-Net). Firstly, based on the observation switch training mechanism, we propose a Panoramic Learning Module (PL-Module). It establishes a learnable panoramic feature space, facilitating the extraction of panoramic features from incomplete observations, thus supplementing missing perspective features. Secondly, based on the feature decomposition mechanism, we design a Panoramic Decomposition-Aggregation Operation (PDA-Operation), which decomposes high-dimensional panoramic features into low-dimensional local scene features. This allows limited local scene features to represent diverse panoramic features, alleviating computational and memory burdens of high-dimensional feature learning. Experimental results demonstrate that our method surpasses existing approaches under incomplete observation scenarios.


  • Egocentric Vulnerable Road Users Trajectory Prediction With Incomplete Observation

    by Hui Liu, Chunsheng Liu, Faliang Chang, Yansha Lu, Minhang Liu

    Vulnerable Road Users (VRUs) trajectory prediction aims to analyze the future movements of pedestrians and cyclists for intelligent driving. Most previous methods just focus on VRUs trajectory prediction using idealized complete observations, and rare consider occlusions and tracking losses. Focus on the incomplete observation problem, we propose a novel Observation Store and Query Fusion Network (OSQF-Net), for VRUs trajectory prediction with incomplete observation. Firstly, based on the external memory bank mechanism and complete-incomplete observation joint training strategy, a Memory Bank-based Feature Store and Query Module (MSQ-Module) is proposed to extract complete motion features, from disrupted motion patterns caused by incomplete observation. Subsequently, based on temporal extraction and attention mechanism, a Spatio-Temporal Fusion Module (STF-Module) is proposed to effectively fuse the pseudo-complete motion features and incomplete motion features in both spatial and temporal dimensions. Finally, with these two modules and a CVAE network, the OSQF-Net can generate a latent space with complete motion patterns, which guides future trajectory prediction. Experimental results demonstrate that OSQF-Net achieves superior prediction performance and real-time inference capability for egocentric VRUs trajectory prediction, under both complete and incomplete observation scenarios.


  • Self-Supervised Multi-Granularity Graph Attention Network for Vision-Based Driver Fatigue Detection

    by Yiming Huang, Chunsheng Liu, Faliang Chang, Yansha Lu

    Driver fatigue is one of the main causes of traffic accidents. Current vision-based methods for detecting driver fatigue lack robustness in the presence of interfering images, and exhibit insufficient ability to focus on frames containing crucial information. To address these issues, we propose a Self-supervised Multi-granularity Graph Attention Network (SMGA-Net) for driver fatigue detection. The network mainly contains the following contributions: Firstly, with the multi-task self-supervised learning strategy, a novel method called Image Restoration based Self-supervised Learning (IRS-Learning) is proposed to enhance the network's robustness when processing interfering images. Secondly, with the graph attention mechanism, a Multi-head Graph Attention (MG-Attention) module is designed to concentrate on frames that contain crucial information by assigning importance weights to each frame. In addition, a Cross Attention Feature Fusion (CAF-Fusion) method is proposed to adaptively merge the multi-granularity features and emphasize effective information contained therein. Experiments performed on the National TsingHua University Drowsy Driver Detection (NTHU-DDD) dataset show that the proposed SMGA-Net based driver fatigue detection method outperforms the state-of-art methods.


  • Traffic Scenario Understanding and Video Captioning via Guidance Attention Captioning Network

    by Chunsheng Liu, Xiao Zhang, Faliang Chang, Shuang Li, Penghui Hao, Yansha Lu, Yinhai Wang

    Describing a traffic scenario from the driver’s perspective is a challenging process for Advanced Driving Assistance System (ADAS), involving different sub-tasks of detection, tracking, segmentation, etc. Previous methods mainly focus on independent sub-tasks and have difficulties to comprehensively describe the incidents. In this study, this problem is novelly treated as a video captioning task, and a Guidance Attention Captioning Network (GAC-Network) structure is proposed for describing the incidents in a concise single sentence. In GAC-Network, an Attention based Encoder-Decoder Net (AED-Net) is built as the main network; with the temporal spatial attention mechanisms, the AED-Net make it possible to effectively reject the unimportant traffic behaviors and redundant backgrounds. Considering various driving scenarios, the Spatio-Temporal Layer Normalization is used to improve the generalization ability. To generate captions for incidents in driving, the novel Guidance Module is proposed to boost the encoder-decoder model to generate words in a caption, which have better relationship to the past and future words. Because there is no public dataset for captioning of driving scenarios, the Traffic Video Captioning (TVC) dataset is released for the video captioning task in driving scenarios. Experimental results show that the proposed methods can fulfill the captioning task for complex driving scenarios, and achieve higher performance than the methods for comparison, including at least 2.5%, 1.8%, 3.6%, and 13.1% better results on BLEU_1, METEOR, ROUGE_L and CIDEr, respectively.


  • JHPFA-Net: Joint Head Pose and Facial Action Network for Driver Yawning Detection Across Arbitrary Poses in Videos

    by Yansha Lu, Chunsheng Liu, Faliang Chang, Hui Liu, Hengqiang Huan

    Yawning detection is a key means in driver fatigue detection, which suffers difficulties including head poses, facial expressions, illumination variations, occlusions, etc. Yet, most previous methods mainly focus on frontal faces, and are deficient to deal with different facial actions under arbitrary poses in the actual driving environment. In this study, we propose a novel Joint Head Pose and Facial Action Network (JHPFA-Net) for driver yawning detection across arbitrary poses in videos, with three main parts including a Geometric-based Key-frame Selection Module (GK-Module), a Face Frontalization with Warp Attention Module (FF-Module) and a dual-channel classifier for Head Pose $\&$ Facial Action Fusion Module (HF-Module). Firstly, the GK-Module is proposed to extract geometric vectors and to construct a two-stage judgment mechanism, with the purpose of dealing with frame redundancy and improving the efficiency of JHPFA-Net structure. Secondly, distinguished with existing methods, the FF-Module is proposed to synthesize photo-realistic frontal faces, which can be used for capturing the facial actions under arbitrary poses. Finally, the HF-Module is proposed to fuse head pose attributes and facial modalities together, for the purpose of achieving pose-invariant detection and improving accuracy. Extensive experiments show that the proposed JHPFA-Net achieves state-of-the-art results comparing with some representative methods on the public YawDD benchmark, and it performs well in real-time application.


  • Driver Gaze Zone Estimation via Head Pose Fusion Assisted Supervision and Eye Region Weighted Encoding

    by Yirong Yang, Chunsheng Liu, Faliang Chang, Yansha Lu, Hui Liu

    Driver gaze zone estimation is an important task in Advanced Driver Assistance Systems (ADAS), which suffers difficulties including head pose, capture direction, glass occlusion, and real-time requirement, etc. Most previous methods combine face modalities and head pose using concat process, which may result in over-fitting due to the unbalanced dimension. Focusing on gaze zone estimation problems, we propose the Head Pose Fusion Assisted supervision & Eye Region Weighted Encoding ( HP-ERW ) structure, which fuses head pose attribute and face modalities together through spatial attention and Kronecker product mechanisms. Firstly, we introduce a pre-processing module dealing with head pose and face information, with the purpose of extracting input vectors and improving the fusion speed of the HP-ERW structure. Secondly, an Eye Region Weighted Encoding Network (ERW-Net) based on spatial attention is proposed to strengthen the networks perception ability for encoding features. Finally, we propose a dual-channel Head Pose Fusion Network ( HP-Net ) based on the Kronecker product mechanism, with the purpose of fusing head pose and improving the estimation accuracy. Experiments show that the HP-ERW outperforms compared existing methods on several public datasets. The designed ADAS using the proposed method achieves 23.5 fps real-time application with small memory requirement of 4,884 KB.