Learning Multi-View Representation With LSTM for 3-D Shape Recognition and Retrieval

Ma, Chao; Guo, Yulan; Yang, Jungang; An, Wei

doi:10.1109/tmm.2018.2875512

Cited by 154 publications

(80 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is challenging for 3D convolutional neural networks to process very large point clouds and this approach is constrained by the representation power of the feature extraction of 3D target objects. Hence, the strategy of multi-view CNNS [55] was adopted here to render the 3D point clouds of trees into 2D images and then apply 2D convolution nets to classify them. The 2D CNN method is relatively mature and has achieved state-of-the-art performance in some image-based phenotyping tasks, with successful application in tasks such as face recognition [56], crop attribute identification [31] and video-based target tracking [57].…”

Section: Potential Improvementmentioning

confidence: 99%

Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning

Wang

Chen

Cao

et al. 2019

Forests

View full text Add to dashboard Cite

Rubber trees in southern China are often impacted by natural disturbances that can result in a tilted tree body. Accurate crown segmentation for individual rubber trees from scanned point clouds is an essential prerequisite for accurate tree parameter retrieval. In this paper, three plots of different rubber tree clones, PR107, CATAS 7-20-59, and CATAS 8-7-9, were taken as the study subjects. Through data collection using ground-based mobile light detection and ranging (LiDAR), a voxelisation method based on the scanned tree trunk data was proposed, and deep images (i.e., images normally used for deep learning) were generated through frontal and lateral projection transform of point clouds in each voxel with a length of 8 m and a width of 3 m. These images provided the training and testing samples for the faster region-based convolutional neural network (Faster R-CNN) of deep learning. Consequently, the Faster R-CNN combined with the generated training samples comprising 802 deep images with pre-marked trunk locations was trained to automatically recognize the trunk locations in the testing samples, which comprised 359 deep images. Finally, the point clouds for the lower parts of each trunk were extracted through back-projection transform from the recognized trunk locations in the testing samples and used as the seed points for the region’s growing algorithm to accomplish individual rubber tree crown segmentation. Compared with the visual inspection results, the recognition rate of our method reached 100% for the deep images of the testing samples when the images contained one or two trunks or the trunk information was slightly occluded by leaves. For the complicated cases, i.e., multiple trunks or overlapping trunks in one deep image or a trunk appearing in two adjacent deep images, the recognition accuracy of our method was greater than 90%. Our work represents a new method that combines a deep learning framework with point cloud processing for individual rubber tree crown segmentation based on ground-based mobile LiDAR scanned data.

show abstract

Section: Potential Improvementmentioning

confidence: 99%

Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning

Wang

Chen

Cao

et al. 2019

Forests

View full text Add to dashboard Cite

show abstract

“…The reason may be that LSTM has stable performance in terms of gradient disappearance and dependence, as well as its good applicability in the sequence [23]. Thus, it is more suitable for the prediction and evaluation of road traffic safety risks.…”

Section: Figure 6 Comparison Of Rnn and Lstm Assessment Results Of Rmentioning

confidence: 99%

Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network

2020

View full text Add to dashboard Cite

A neural network model based on deep learning is utilized to explore the traffic sign recognition (TSR) and expand the application of deep intelligent learning technology in the field of virtual reality (VR) image recognition, thereby assessing the road traffic safety risks and promoting the construction of intelligent transportation networks. First, a dual-path deep CNN (TDCNN) TSR model is built based on the convolutional neural network (CNN), and the cost function and recognition accuracy are selected as indicators to analyze the training results of the model. Second, the recurrent neural network (RNN) and long-short-term memory (LSTM) RNN are utilized to assess the road traffic safety risks, and the prediction and evaluation effects of them are compared. Finally, the changes in safety risks of road traffic accidents are analyzed based on the two key influencing factors of the number of road intersections and the speed of vehicles traveling. The results show that the learning rate of the network model and the number of hidden neurons in the fully-connected layer directly affect the training results, and there are differences in the choices between the early and late training periods. Compared with RNN, the LSTM network model has higher evaluation accuracy, and its corresponding root square error (RSE) is 0.36. The rational control of the number of intersections and the speed of roads traveled has a significant impact on improving the safety level and promoting road traffic efficiency. The VR image recognition algorithm and safety risk prediction method based on a neural network model positively affect the construction of an intelligent transport network.

show abstract

“…In GPCNN, a hierarchical view-group-shape architecture is proposed, and then all group level descriptors are weighted embedded to generate the shape level descriptor. • CNN+LSTM ( [42]). In CNN+LSTM, the convolutional neural networks (CNNs) are combined with long shortterm memory (LSTM) to exploit the correlative information from multiple views.…”

Section: Competing Methodsmentioning

confidence: 99%

“…The training/testing split setting in ( [40], [30]) is employed. In our experiments, some popular descriptors that are often used in 3D shape retrieval, [42]). The default parameters setting of these methods is used.…”

Section: G Performance Evaluation On Modelnet40 Datasetmentioning

confidence: 99%

Multiple Discrimination and Pairwise CNN for view-based 3D object retrieval

2020

View full text Add to dashboard Cite

With the rapid development and wide application of computer, camera device, network and hardware technology, 3D object (or model) retrieval has attracted widespread attention and it has become a hot research topic in the computer vision domain. Deep learning features already available in 3D object retrieval have been proven to be better than the retrieval performance of hand-crafted features. However, most existing networks do not take into account the impact of multi-view image selection on network training, and the use of contrastive loss alone only forcing the same-class samples to be as close as possible. In this work, a novel solution named Multi-view Discrimination and Pairwise CNN (MDPCNN) for 3D object retrieval is proposed to tackle these issues. It can simultaneously input of multiple batches and multiple views by adding the Slice layer and the Concat layer. Furthermore, a highly discriminative network is obtained by training samples that are not easy to be classified by clustering. Lastly, we deploy the contrastive-center loss and contrastive loss as the optimization objective that has better intra-class compactness and inter-class separability. Large-scale experiments show that the proposed MDPCNN can achieve a significant performance over the state-of-the-art algorithms in 3D object retrieval. 1

show abstract

Learning Multi-View Representation With LSTM for 3-D Shape Recognition and Retrieval

Cited by 154 publications

References 36 publications

Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning

Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning

Image Recognition and Safety Risk Assessment of Traffic Sign Based on Deep Convolution Neural Network

Multiple Discrimination and Pairwise CNN for view-based 3D object retrieval

Contact Info

Product

Resources

About