3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds

Liu, Fangyu; Li, Shuaipeng; Zhang, Liqiang; Zhou, Chenghu; Ye, Rongtian; Wang, Yuebin; Lu, Jiwen

doi:10.1109/iccv.2017.605

Cited by 94 publications

(52 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Specifically, Hu and Yuan [44] suggest that DL-based algorithms can outperform the current methods that are most commonly used for ground return classification. Others have investigated the classification of features in 3D space represented as point clouds [45][46][47].…”

Section: Deep Learningmentioning

confidence: 99%

Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data

2020

View full text Add to dashboard Cite

Modern elevation-determining remote sensing technologies such as light-detection and ranging (LiDAR) produce a wealth of topographic information that is increasingly being used in a wide range of disciplines, including archaeology and geomorphology. However, automated methods for mapping topographic features have remained a significant challenge. Deep learning (DL) mask regional-convolutional neural networks (Mask R-CNN), which provides context-based instance mapping, offers the potential to overcome many of the difficulties of previous approaches to topographic mapping. We therefore explore the application of Mask R-CNN to extract valley fill faces (VFFs), which are a product of mountaintop removal (MTR) coal mining in the Appalachian region of the eastern United States. LiDAR-derived slopeshades are provided as the only predictor variable in the model. Model generalization is evaluated by mapping multiple study sites outside the training data region. A range of assessment methods, including precision, recall, and F1 score, all based on VFF counts, as well as area- and a fuzzy area-based user’s and producer’s accuracy, indicate that the model was successful in mapping VFFs in new geographic regions, using elevation data derived from different LiDAR sensors. Precision, recall, and F1-score values were above 0.85 using VFF counts while user’s and producer’s accuracy were above 0.75 and 0.85 when using the area- and fuzzy area-based methods, respectively, when averaged across all study areas characterized with LiDAR data. Due to the limited availability of LiDAR data until relatively recently, we also assessed how well the model generalizes to terrain data created using photogrammetric methods that characterize past terrain conditions. Unfortunately, the model was not sufficiently general to allow successful mapping of VFFs using photogrammetrically-derived slopeshades, as all assessment metrics were lower than 0.60; however, this may partially be attributed to the quality of the photogrammetric data. The overall results suggest that the combination of Mask R-CNN and LiDAR has great potential for mapping anthropogenic and natural landscape features. To realize this vision, however, research on the mapping of other topographic features is needed, as well as the development of large topographic training datasets including a variety of features for calibrating and testing new methods.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data

2020

View full text Add to dashboard Cite

show abstract

“…Deep RL [36], [38] uses deep artificial neural networks as estimators. Most popularly convoluted neural networks (CNN) or recurrent neural network (RNN), mainly Long short-term memory (LSTM) [39] are used in deep RL. In order to use Qvalue in deep RL, equation 1 is updated to include the network parameters as presented in equation 3, where Φ is the preprocessed equivalent to state s t and θ stands for the parameters in the neural network (weights).…”

Section: B Reinforcement Learningmentioning

confidence: 99%

Altruism and Selfishness in Believable Game Agents: Deep Reinforcement Learning in Modified Dictator Games

Daylamani-Zad

Angelides

2021

IEEE Trans. Games

View full text Add to dashboard Cite

This paper focuses on using Deep Reinforcement Learning, specifically Proximity Policy Optimization to train agents in a social dilemma game, modified Dictator Game, in order to investigate the effect of selfishness and altruism on the believability of the game agents. We present the design and implementation of the training environment, including the reward functions which are based on the findings of established empirical research, with three agent profiles mapped to the three standard Constant Elasticity of Substitution (CES) utility functions, i.e. selfish, perfect substitutes and Leontief which measure different levels of selfishness/altruism. The trained models are validated and then used in a sample game, which is used to evaluate the believability of the three agent profiles using the agent believability metrics. The results indicate that players find altruistic behaviour more believable and consider selfishness less so. Analysis of the results indicate that human-like behaviour resulting from the application of AI evolves from perceived human behaviour rather than the observed. The analysis also indicates that selfishness/altruism may be considered as an extra dimension to be included in the believability metrics.

show abstract

“…3D semantic segmentation [48,2,29,34] and Shape Completion [45,7,4,15] are both active areas in computer vision. 3D segmentation gives semantic labels to observed voxels, while shape completion completes missing voxels.…”

Section: D Semantic Segmentation and Shape Completionmentioning

confidence: 99%

Efficient Semantic Scene Completion Network with Spatial Group Convolution

Zhang

Zhao

Yao³

et al. 2018

Lecture Notes in Computer Science

103

View full text Add to dashboard Cite

We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks. SGC is orthogonal to group convolution, which works on spatial dimensions rather than feature channel dimension. It divides input voxels into different groups, then conducts 3D sparse convolution on these separated groups. As only valid voxels are considered when performing convolution, computation can be significantly reduced with a slight loss of accuracy. The proposed operations are validated on semantic scene completion task, which aims to predict a complete 3D volume with semantic labels from a single depth image. With SGC, we further present an efficient 3D sparse convolutional network, which harnesses a multiscale architecture and a coarse-to-fine prediction strategy. Evaluations are conducted on the SUNCG dataset, achieving state-of-the-art performance and fast speed. Code is available at https://github.com/zjhthu/SGC-Release.git

show abstract

3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds

Cited by 94 publications

References 56 publications

Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data

Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data

Altruism and Selfishness in Believable Game Agents: Deep Reinforcement Learning in Modified Dictator Games

Efficient Semantic Scene Completion Network with Spatial Group Convolution

Contact Info

Product

Resources

About