Point cloud classification based on transformer

Wu, Xianfeng; Liu, Xinyi; Wang, Junfei; Lai, Zhongyuan; Zhou, Jing; Liu, Xia

doi:10.1016/j.compeleceng.2022.108413

Cited by 5 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A deep neural network called PointNet receives 3D point cloud data directly as input. Due to its great stability and computational efficiency, PointNet has emerged as one of the most popular point cloud categorization algorithms for practical applications [7]. A dynamic graph convolutional neural network (DGCNN) point-wise deep learning approach was created and deployed for 3D point cloud classification, extending its classification applicability from indoor scenarios to aerial point cloud data.…”

Section: Related Workmentioning

confidence: 99%

Convolutional Neural Network Model for Stratification of LiDAR 3D Point Cloud Data

PL,

2024

Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security,

View full text Add to dashboard Cite

Analysis of the 3D LiDAR point cloud data is the fundamental for computer vision and robotics, with potential applications ranging from object detection to scene understanding. In this proposed work, introduced an approach that leverages the power of contrastive learning combined with self-supervised learning for feature extraction from the LiDAR 3D point cloud data. On-the-fly extensions to include rotation on invariance of 3D point cloud data, jitter adding noise in coordinates of point cloud data, and displacement and shear to improve model robustness and invariance to geometric transformations. Each data point is paired with two extensions to form positive pairs and facilitating the contrastive learning. The focus of proposed method is to implement the point cloud feature learning layer, specifically on DynamicEdgeConv. This layer uses the parameter 'k' to identify nearest neighbors in 3D point cloud data that together create a subgraph, facilitating improved feature learning. Applying enhancements during training is important that ensures the adaptability of model to real-world data fluctuations. Evaluation results determines the efficacy of proposed approach and that shows that significant improvements in clustering performance and outlier detection accuracy compared to common methods. This work has advances of the state of self-supervised learning of LiDAR 3D point cloud data, but also paves the way for more robust 3D object detection, scene understanding, and applications in the fields of robotics.

show abstract

Section: Related Workmentioning

confidence: 99%

Convolutional Neural Network Model for Stratification of LiDAR 3D Point Cloud Data

PL,

2024

Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security,

View full text Add to dashboard Cite

show abstract

“…Simultaneously, it overcomes the drawbacks of large transformer parameters and limited inference speed while inheriting their high accuracy. 35,36 Therefore, the GETNet model achieves a balance between accuracy and computational efficiency. From the input-output perspective, our approach remains highly competitive.…”

Section: Data Fusion Performancementioning

confidence: 99%

“…This may be attributed to GETNet inheriting the advantages of the moderate memory and low processor consumption of GhostNet. Simultaneously, it overcomes the drawbacks of large transformer parameters and limited inference speed while inheriting their high accuracy 35,36 . Therefore, the GETNet model achieves a balance between accuracy and computational efficiency.…”

Section: Experiments and Analysismentioning

confidence: 99%

Electronic eye and electronic tongue data fusion combined with a GETNet model for the traceability and detection of Astragalus

Jin,

Wang,

et al. 2024

J Sci Food Agric

View full text Add to dashboard Cite

BackgroundAstragalus is a widely used traditional Chinese medicine material that is easily confused due to its quality, price and other factors derived from different origins. This article describes a novel method for the rapid tracing and detection of Astragalus via the joint application of an electronic tongue (ET) and an electronic eye (EE) combined with a lightweight CNN‐transformer model. First, ET and EE systems are employed to measure the taste fingerprints and appearance images of different Astragalus samples, respectively. Three spectral transform methods, the Markov transition field (MTF), short‐time Fourier transform (STFT) and recurrence plot (RP), are utilized to convert the ET signals into 2D spectrograms. Then, the obtained ET spectrograms are fused with the EE image to obtain multimodal information. A lightweight hybrid model, termed GETNet, is designed to achieve pattern recognition for the Astragalus fusion information. The proposed model employs an improved transformer module and an improved Ghost bottleneck as its backbone network, complementarily utilizing the benefits of CNN and transformer architectures for local and global feature representation. Furthermore, the Ghost bottleneck is further optimized using a channel attention technique, which boosts the model's feature extraction effectiveness.ResultsThe experiments indicate that the proposed data fusion strategy based on ET and EE devices has better recognition accuracy than that attained with independent sensing devices.ConclusionThe proposed method achieves a high precision (99.1%) and recall (99.1%) values, providing a novel approach for rapidly identifying the origin of Astragalus, and it holds great promise for applications involving other types of Chinese herbal medicines.This article is protected by copyright. All rights reserved.

show abstract

SEGANet: 3D object detection with shape-enhancement and geometry-aware network

Zhou

Lai

et al. 2023

Computers and Electrical Engineering

View full text Add to dashboard Cite

Point cloud classification based on transformer

Cited by 5 publications

References 3 publications

Convolutional Neural Network Model for Stratification of LiDAR 3D Point Cloud Data

Convolutional Neural Network Model for Stratification of LiDAR 3D Point Cloud Data

Electronic eye and electronic tongue data fusion combined with a GETNet model for the traceability and detection of Astragalus

SEGANet: 3D object detection with shape-enhancement and geometry-aware network

Contact Info

Product

Resources

About