Deep residual neural network based PointNet for 3D object part segmentation

Li, Bin; Zhang, Yonghan; Sun, Fuqiang

doi:10.1007/s11042-020-09609-8

Cited by 7 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recognition based on image classification is mainly divided into six steps: preprocessing, window sliding, feature extraction, feature selection, feature classification, and postprocessing [12]. The process of the first three steps is the same as the template matching-based method.…”

Section: Methodsmentioning

confidence: 99%

Target Recognition Technology of Multimedia Platform Based on a Convolutional Neural Network

Liu

Zhang²

2022

Advances in Multimedia

View full text Add to dashboard Cite

With the rapid development of the Internet, network media, as a new form of information dissemination, has penetrated into people’s daily life. In recent years, with the rapid transformation of Chinese social structure and the rise of self-media platforms, various social contradictions have been highlighted in the form of online public opinion. Especially on online multimedia platforms, the spread of online public opinion is more rapid, which can easily lead to social hotspots. In order to effectively supervise the public opinion information on the Internet, it is necessary to identify the target of the information on the multimedia platform and effectively screen the information, so as to control the network public opinion in the development stage. Aiming at the above problems, we propose a multitarget retrieval method based on a convolutional neural network, which uses multitarget detection algorithm to locate multitarget regions and extract regional features and uses cosine distance as a similarity measure for multitarget recognition. In view of the slow feature extraction speed of VGG model, a lightweight mobile network model is proposed to replace the original VGG model on the mobile phone to reduce the retrieval time and realize the recognition of specific targets on the multimedia platform, and it is applied to the verification of image recognition on the multimedia platform. The results show that the algorithm proposed in this paper has great advantages in multitarget recognition tasks.

show abstract

Section: Methodsmentioning

confidence: 99%

Target Recognition Technology of Multimedia Platform Based on a Convolutional Neural Network

Liu

Zhang²

2022

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…However, the high variability of a point cloud is a challenge. In the latest research [32][33][34], high variability was ameliorated by extracting global and local features. In a word, to relieve the problems of the disorder and inhomogeneity of point clouds, deep learning must be improved in the direction of obtaining local information and marking datasets.…”

Section: B the Methods Of Deep Learningmentioning

confidence: 99%

MLFNet- Point Cloud Semantic Segmentation Convolution Network Based on Multi-Scale Feature Fusion

et al. 2021

View full text Add to dashboard Cite

The project was funded by jinan science and technology bureau and undertaken by QiluUniversity of Technology(Shandong Academy of Sciences),Machine vision-based online intelligentsegmentation of foreign objects in liquids is implemented.2019GXRC067. ABSTRACTIn the semantic segmentation of a point cloud, if the spatial structure correlation between the input features and coordinates are not fully considered, a semantic segmentation error can occur. We propose a method of spatial convolution that makes full use of the characteristics of a multiscale spatial structure by combining local and global features. We call this method MLFNet. We also propose a multiscale feature framework. First, the point cloud is simplified by obtaining the weighted farthest point (by down-sampling combined with farthest-point sampling and the weighted average). The near-near domain of each sampling point is then obtained by a KK octant search (an octant search optimized by the knearest neighbor and a custom threshold), and feature information is obtained. The feature information is added to the subsequent multilayer perceptron, and fusion of local context information is achieved. Finally, the fusion features in multiple directions are maximally pooled. Our method was tested on self-made datasets and other standard basic datasets (ModelNet40, ShapeNet, and Stanford large-scale 3D indoor spaces (S3DIS) data). The accuracy of segmentation was 0.937 in our dataset; two percentage points higher than the latest deep learning method. Also, our method obtained a mean intersection over a union of 0.867 in ShapeNet, which was 0.3 percentage points higher than the latest PointGrid. The accuracy on S3DIS was 0.8153, which was three percentage points higher than the latest spatial aggregation net. The results of semantic segmentation verified the superiority of the proposed method.

show abstract

“…Residuals connection is critical for SR. e SR image can be achieved by adding the output of the model and the residuals (the LR images), where the residuals connection can transfer the low-frequency information of the LR image to the end of the model directly [13,14], while the model only needs to generate the small amount of high-frequency information.…”

Section: Relate Workmentioning

confidence: 99%

An Improved Feedback Network Superresolution on Camera Lens Images for Blind Superresolution

Wang

2021

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Most of the recent advances in image superresolution (SR) assume that the blur kernel during downsampling is predefined (e.g., Bicubic or Gaussian kernel), but it is a difficult task to make it suitable for all the realistic images. In this paper, we propose an Improved Superresolution Feedback Network (ISRFN) which is designed free to predefine the downsampling blur kernel by dealing with real-world HR-LR image pairs directly without downsampling process. We propose ISRFN by modifying the layers and network structures of the famous Superresolution Feedback Network (SRFBN). We trained the ISRFN with the Camera Lens Database named City100, which produced the HR and LR on the same lens, respectively, free for downsampling, so our proposed ISRFN is free to estimate the blur kernel. Due to different camera lens (smartphone and DSLR) databases, we perform two series of experiments under two camera lenses-based City100 databases, respectively, to choose the optimum network structures; experiments make it clear that different camera lens-based databases have different optimum network structures. We also compare our two ISRFNs with the state-of-the-art algorithms on performance; experiments show that our proposed ISRFN outperforms other state-of-the-art algorithms.

show abstract

Deep residual neural network based PointNet for 3D object part segmentation

Cited by 7 publications

References 30 publications

Target Recognition Technology of Multimedia Platform Based on a Convolutional Neural Network

Target Recognition Technology of Multimedia Platform Based on a Convolutional Neural Network

MLFNet- Point Cloud Semantic Segmentation Convolution Network Based on Multi-Scale Feature Fusion

An Improved Feedback Network Superresolution on Camera Lens Images for Blind Superresolution

Contact Info

Product

Resources

About