PointLAE: A Point Cloud Semantic Segmentation Neural Network via Multifeature Aggregation for Large-Scale Application

Jiang, Li; Liu, Jinhao

doi:10.1155/2022/9433661

Cited by 4 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Figure 13, ref. [40] exhibits superior overall performance, but our method achieves a higher level of recognition for different living trees across all datasets.…”

Section: Comparison With Similar Methodologiesmentioning

confidence: 93%

See 1 more Smart Citation

PointDMS: An Improved Deep Learning Neural Network via Multi-Feature Aggregation for Large-Scale Point Cloud Segmentation in Smart Applications of Urban Forestry Management

Li,

Liu

2023

Forests

View full text Add to dashboard Cite

Background: The development of laser measurement techniques is of great significance in forestry monitoring and park management in smart cities. It provides many conveniences for improving landscape planning efficiency and strengthening digital construction. However, capturing 3D point clouds in large-scale landscape environments is a complex task that generates massive amounts of unstructured data with characteristics such as randomness, rotational invariance, sparsity, and serious barriers. Methods: To improve the processing efficiency of intelligent devices for massive point clouds, we propose a novel deep learning neural network based on a multi-feature aggregation strategy. This network is designed to divide 3D laser point clouds in complex large-scale scenarios. Firstly, we utilize multiple terrestrial laser sensors to collect a large amount of data in open scenes such as parks, streets, and forests in urban environments. These data are integrated into a practical database called DMSdataset, which contains different information variables, densities, and dimensions. Then, an automatic block integrated with a multi-feature extractor is constructed to pre-process the unstructured point cloud data and standardize the datasets. Finally, a novel semantic segmentation framework called PointDMS is designed using 3D convolutional deep networks. PointDMS achieves a better segmentation performance of point clouds with a lightweight parameter structure. Here, “D” stands for deep network, “M” stands for multi-feature, and “S” stands for segmentation. Results: Extensive experiments on self-built datasets show that the proposed PointDMS achieves similar or better performance in point cloud segmentation compared to other methods. The overall identification accuracy of the proposed model is up to 93.5%, which is a 14% increase. Particularly for living wood objects, the average identification accuracy is up to 88.7%, which is, at least, an 8.2% increase. These results effectively prove that PointDMS is beneficial for 3D point cloud processing, division, and mining applications in urban forest environments. It demonstrates good robustness and generalization.

show abstract

“…In Figure 13, ref. [40] exhibits superior overall performance, but our method achieves a higher level of recognition for different living trees across all datasets.…”

Section: Comparison With Similar Methodologiesmentioning

confidence: 93%

“…Among these studies, the authors of study [13], study [12], and study [40] demonstrate the overall accuracy of their work, with their methods performing well. However, our method holds a relative advantage in large scenes.…”

Section: Comparison With Similar Methodologiesmentioning

confidence: 99%

PointDMS: An Improved Deep Learning Neural Network via Multi-Feature Aggregation for Large-Scale Point Cloud Segmentation in Smart Applications of Urban Forestry Management

Li,

Liu

2023

Forests

View full text Add to dashboard Cite

show abstract

“…The overall accuracy reaches 83.25%, showcasing significant advancements in the recognition of standing trees compared to other algorithms. Specifically, there is an 11% improvement compared to pointLAE [39], as well as a 2% increase in accuracy for shrub identification. Considering performance, the pointDMM algorithm with k = 10 is recommended for small-scale forestry scenes, such as individual tree surveys.…”

Section: Compare Pointdmm With Other Algorithmsmentioning

confidence: 93%

“…The overall accuracy reaches 83.25%, showcasing significant advancements in the recognition of standing trees compared to other algorithms. Specifically, there is an 11% improvement compared to pointLAE [39], as well For the DMM-1 dataset, as shown in Figure 12, the point cloud classification performance for individual trees is not satisfactory when selecting k = 1000. This could be attributed to the large scale of the dataset, which makes it challenging to capture the local geometric features of single-tree scenes.…”

Section: Compare Pointdmm With Other Algorithmsmentioning

confidence: 98%

PointDMM: A Deep-Learning-Based Semantic Segmentation Method for Point Clouds in Complex Forest Environments

Li,

Liu,

Huang

2023

Forests

View full text Add to dashboard Cite

Background. With the advancement of “digital forestry” and “intelligent forestry”, point cloud data have emerged as a powerful tool for accurately capturing three-dimensional forest scenes. It enables the creation and presentation of digital forest systems, facilitates the monitoring of dynamic changes such as forest growth and logging processes, and facilitates the evaluation of forest resource fluctuations. However, forestry point cloud data are characterized by its large volume and the need for time-consuming and labor-intensive manual processing. Deep learning, with its exceptional learning capabilities, holds tremendous potential for processing forestry environment point cloud data. This potential is attributed to the availability of accurately annotated forestry point cloud data and the development of deep learning models specifically designed for forestry applications. Nonetheless, in practical scenarios, conventional direct annotation methods prove to be inefficient and time-consuming due to the complex terrain, dense foliage occlusion, and uneven sparsity of forestry point clouds. Furthermore, directly applying deep learning frameworks to forestry point clouds results in subpar accuracy and performance due to the large size, occlusion, sparsity, and unstructured nature of these scenes. Therefore, the proposal of accurately annotated forestry point cloud datasets and the establishment of semantic segmentation methods tailored for forestry environments hold paramount importance. Methods. A point cloud data annotation method based on single-tree positioning to enhance annotation efficiency was proposed and challenges such as occlusions and sparse distribution in forestry environments were addressed. This method facilitated the construction of a forestry point cloud semantic segmentation dataset, consisting of 1259 scenes and 214.4 billion points, encompassing four distinct categories. The pointDMM framework was introduced, a semantic segmentation framework specifically designed for forestry point clouds. The proposed method first integrates tree features using the DMM module and constructs key segmentation graphs utilizing energy segmentation functions. Subsequently, the cutpursuit algorithm is employed to solve the graph and achieve the pre-segmentation of semantics. The locally extracted forestry point cloud features from the pre-segmentation are comprehensively inputted into the network. Feature fusion is performed using the MLP method of multi-layer features, and ultimately, the point cloud is segmented using the lightweight PointNet. Result. Remarkable segmentation results are demonstrated on the DMM dataset, achieving an accuracy rate of 93% on a large-scale forest environment point cloud dataset known as DMM-3. Compared to other algorithms, the proposed method improves the accuracy of standing tree recognition by 21%. This method exhibits significant advantages in extracting feature information from artificially planted forest point clouds obtained from TLS. It establishes a solid foundation for the automation, intelligence, and informatization of forestry, thereby possessing substantial scientific significance.

show abstract

“…Tis article has been retracted by Hindawi following an investigation undertaken by the publisher [1]. Tis investigation has uncovered evidence of one or more of the following indicators of systematic manipulation of the publication process:…”

mentioning

confidence: 99%

Retracted: PointLAE: A Point Cloud Semantic Segmentation Neural Network via Multifeature Aggregation for Large-Scale Application

2023

Mobile Information Systems

View full text Add to dashboard Cite

PointLAE: A Point Cloud Semantic Segmentation Neural Network via Multifeature Aggregation for Large-Scale Application

Cited by 4 publications

References 29 publications

PointDMS: An Improved Deep Learning Neural Network via Multi-Feature Aggregation for Large-Scale Point Cloud Segmentation in Smart Applications of Urban Forestry Management

PointDMS: An Improved Deep Learning Neural Network via Multi-Feature Aggregation for Large-Scale Point Cloud Segmentation in Smart Applications of Urban Forestry Management

PointDMM: A Deep-Learning-Based Semantic Segmentation Method for Point Clouds in Complex Forest Environments

Retracted: PointLAE: A Point Cloud Semantic Segmentation Neural Network via Multifeature Aggregation for Large-Scale Application

Contact Info

Product

Resources

About