Longjie Ye
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
Research Subjects
Longjie Ye has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Wen Xiao
School of Geography and Information Engineering, China University of Geosciences, Wuhan, China
2 shared publications - Ka Zhang
Key Laboratory of Virtual Geographic Environment, Ministry of Education, Nanjing Normal University, Nanjing 210023, China
1 shared publication - Qihao Weng
The Hong Kong Polytechnic University
1 shared publication Shan Zhang
Key Laboratory of Virtual Geographic Environment, School of Geography, Nanjing Normal University, Nanjing, China
1 shared publicationXia Tao
Key Laboratory of Virtual Geographic Environment, School of Geography, Nanjing Normal University, Nanjing, China
1 shared publicationYaqin Zhou
Key Laboratory of Virtual Geographic Environment, School of Geography, Nanjing Normal University, Nanjing, China
1 shared publication
Latest Publications
- 18 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-19
Supervoxel-Based Instance Segmentation of Pole-Like Facilities From Mobile Laser Scanning Data Using Pyramid Cascaded Fisher Vector Modeling
Efficient and automatic object recognition in road scenes plays an essential role in smart city applications such as autonomous driving and intelligent infrastructure. As an important component of road scenes, pole-like facilities (PLFs) have been challenging to recognize high-definition road mapping. To achieve the automatic recognition of PLFs from cluttered mobile laser scanning data, a novel instance segmentation method is proposed. First, candidate poles are detected by supervoxel-based histogram analysis from partitioned off-ground point clouds. Then, instance segmentation of PLFs are achieved through a constrained hierarchical region growing algorithm based on voxeled point clouds. Finally, a pyramid cascaded Fisher Vector (FV) modeling and Random Forest classifier is applied to classify the delineated pole-like road facilities into six predefined categories namely, trees, traffic signs, traffic lights, lamps, bare poles, and other objects. The proposed method is tested on three datasets collected in street scenes with different types of road facilities and point densities. Results demonstrate our method can effectively achieve instance segmentation of PLFs in complex road environments. The proposed method outperformed state-of-the-art for PLF detection in correctness (93.5%), completeness (95.3%), and quality (88.81%). Besides, the proposed method achieved satisfactory results for instance-level semantic segmentation with an average F1 score of 90.2%, demonstrating the effectiveness of geometric information enhancement in the designed FV coding approach.
- 18 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-19
Supervoxel-Based Instance Segmentation of Pole-Like Facilities From Mobile Laser Scanning Data Using Pyramid Cascaded Fisher Vector Modeling
Efficient and automatic object recognition in road scenes plays an essential role in smart city applications such as autonomous driving and intelligent infrastructure. As an important component of road scenes, pole-like facilities (PLFs) have been challenging to recognize high-definition road mapping. To achieve the automatic recognition of PLFs from cluttered mobile laser scanning data, a novel instance segmentation method is proposed. First, candidate poles are detected by supervoxel-based histogram analysis from partitioned off-ground point clouds. Then, instance segmentation of PLFs are achieved through a constrained hierarchical region growing algorithm based on voxeled point clouds. Finally, a pyramid cascaded Fisher Vector (FV) modeling and Random Forest classifier is applied to classify the delineated pole-like road facilities into six predefined categories namely, trees, traffic signs, traffic lights, lamps, bare poles, and other objects. The proposed method is tested on three datasets collected in street scenes with different types of road facilities and point densities. Results demonstrate our method can effectively achieve instance segmentation of PLFs in complex road environments. The proposed method outperformed state-of-the-art for PLF detection in correctness (93.5%), completeness (95.3%), and quality (88.81%). Besides, the proposed method achieved satisfactory results for instance-level semantic segmentation with an average F1 score of 90.2%, demonstrating the effectiveness of geometric information enhancement in the designed FV coding approach.
- Open Access
- 26 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-17
A Dual Attention Neural Network for Airborne LiDAR Point Cloud Semantic Segmentation
With the development of airborne light detection and ranging (LiDAR) technology, it has become a common and efficient way to collect large-scale 3-D spatial information. However, efficient and automatic semantic segmentation of LiDAR data, in the form of 3-D point clouds, remains a persistent challenge. To address this, a dual attention neural network (DA-Net) is proposed, consisting of two different blocks, namely, augmented edge representation (AER) and elevation attentive pooling (EAP). First, the AER can adaptively represent local orientation and position, thereby effectively enhancing geometric information. Second, the captured local features of centroid points are utilized to further encode discriminative features using the EAP with the learned attention scores. Finally, a location homogeneity (LH) module is devised to explore the long-range relationship in an encoder–decoder network. Benefiting from the dual attention module, geometric information hidden in unorganized point clouds can be effectively propagated. Besides, the LH forces the network to pay attention to the semantic consistency of elevated objects, which facilitates both point- and object-level point cloud semantic segmentation for scene understanding. A benchmark dataset is used to assess the proposed method, which achieves an overall accuracy of 85.98% and an average F1 score of 72.31%. In addition, comparisons with other latest deep learning methods on the 2019 Data Fusion Contest dataset further demonstrate the robustness and generalization ability of the proposed method.
- 26 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-17
Open AccessA Dual Attention Neural Network for Airborne LiDAR Point Cloud Semantic Segmentation
With the development of airborne light detection and ranging (LiDAR) technology, it has become a common and efficient way to collect large-scale 3-D spatial information. However, efficient and automatic semantic segmentation of LiDAR data, in the form of 3-D point clouds, remains a persistent challenge. To address this, a dual attention neural network (DA-Net) is proposed, consisting of two different blocks, namely, augmented edge representation (AER) and elevation attentive pooling (EAP). First, the AER can adaptively represent local orientation and position, thereby effectively enhancing geometric information. Second, the captured local features of centroid points are utilized to further encode discriminative features using the EAP with the learned attention scores. Finally, a location homogeneity (LH) module is devised to explore the long-range relationship in an encoder–decoder network. Benefiting from the dual attention module, geometric information hidden in unorganized point clouds can be effectively propagated. Besides, the LH forces the network to pay attention to the semantic consistency of elevated objects, which facilitates both point- and object-level point cloud semantic segmentation for scene understanding. A benchmark dataset is used to assess the proposed method, which achieves an overall accuracy of 85.98% and an average F1 score of 72.31%. In addition, comparisons with other latest deep learning methods on the 2019 Data Fusion Contest dataset further demonstrate the robustness and generalization ability of the proposed method.