Point Cloud Completion of Foot Shape from a Single Depth Map for Fit Matching Using Deep Learning View Synthesis

2017 ◽  
Author(s):  
John Zelek ◽  
Nolan Lunscher
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Depth Map ◽  
View Synthesis

scholarly journals Food Volume Estimation Based on Deep Learning View Synthesis from a Single Depth Map

Nutrients ◽  
2018 ◽  
Vol 10 (12) ◽  
pp. 2005 ◽  
Author(s):  
Frank Lo ◽  
Yingnan Sun ◽  
Jianing Qiu ◽  
Benny Lo
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Point Cloud ◽  
Volume Estimation ◽  
Assessment System ◽  
View Synthesis ◽  
Depth Image ◽  
3D Point Cloud ◽  
Viewing Angle ◽  
3D Point Clouds

An objective dietary assessment system can help users to understand their dietary behavior and enable targeted interventions to address underlying health problems. To accurately quantify dietary intake, measurement of the portion size or food volume is required. For volume estimation, previous research studies mostly focused on using model-based or stereo-based approaches which rely on manual intervention or require users to capture multiple frames from different viewing angles which can be tedious. In this paper, a view synthesis approach based on deep learning is proposed to reconstruct 3D point clouds of food items and estimate the volume from a single depth image. A distinct neural network is designed to use a depth image from one viewing angle to predict another depth image captured from the corresponding opposite viewing angle. The whole 3D point cloud map is then reconstructed by fusing the initial data points with the synthesized points of the object items through the proposed point cloud completion and Iterative Closest Point (ICP) algorithms. Furthermore, a database with depth images of food object items captured from different viewing angles is constructed with image rendering and used to validate the proposed neural network. The methodology is then evaluated by comparing the volume estimated by the synthesized 3D point cloud with the ground truth volume of the object items.

scholarly journals Foot Depth Map Point Cloud Completion using Deep Learning with Residual Blocks

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
Nolan Lunscher ◽  
John Zelek
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Depth Map ◽  
3D Scanning ◽  
Training Time ◽  
Shoe Size ◽  
Learning Technique ◽  
Footwear Fit ◽  
And Training

Fit is extremely important in footwear as fit largely determines performanceand comfort. Current footwear fit estimation mainly usesonly shoe size, which is extremely limited in characterizing theshape of a foot or the shape of a shoe. 3D scanning presents asolution to this, where a foot shape can be captured and virtuallyfit with shoe models. Traditional 3D scanning techniques have theirown complications however, stemming from their need to collectviews covering all aspects of an object. In this work we explore adeep learning technique to compete a foot scan point cloud frominformation contained in a single depth map view. We examine thebenefits of implementing residual blocks in architectures for this application,and find that they can improve accuracies while reducingmodel size and training time.

scholarly journals Three-Dimensional Inundation Mapping Using UAV Image Segmentation and Digital Surface Model

2021 ◽  
Vol 10 (3) ◽  
pp. 144
Author(s):  
Asmamaw A Gebrehiwot ◽  
Leila Hashemi-Beni
Keyword(s):  
Deep Learning ◽  
Water Depth ◽  
Water Surface ◽  
Point Cloud ◽  
Depth Map ◽  
Depth Estimation ◽  
Surface Model ◽  
Topographic Data ◽  
Inundation Depth ◽  
Uav Images

Flood occurrence is increasing due to the expansion of urbanization and extreme weather like hurricanes; hence, research on methods of inundation monitoring and mapping has increased to reduce the severe impacts of flood disasters. This research studies and compares two methods for inundation depth estimation using UAV images and topographic data. The methods consist of three main stages: (1) extracting flooded areas and create 2D inundation polygons using deep learning; (2) reconstructing 3D water surface using the polygons and topographic data; and (3) deriving a water depth map using the 3D reconstructed water surface and a pre-flood DEM. The two methods are different at reconstructing the 3D water surface (stage 2). The first method uses structure from motion (SfM) for creating a point cloud of the area from overlapping UAV images, and the water polygons resulted from stage 1 is applied for water point cloud classification. While the second method reconstructs the water surface by intersecting the water polygons and a pre-flood DEM created using the pre-flood LiDAR data. We evaluate the proposed methods for inundation depth mapping over the Town of Princeville during a flooding event during Hurricane Matthew. The methods are compared and validated using the USGS gauge water level data acquired during the flood event. The RMSEs for water depth using the SfM method and integrated method based on deep learning and DEM were 0.34m and 0.26m, respectively.

scholarly journals A Hybrid Approach to Industrial Augmented Reality Using Deep Learning-Based Facility Segmentation and Depth Prediction

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 307
Author(s):  
Minseok Kim ◽  
Sung Ho Choi ◽  
Kyeong-Beom Park ◽  
Jae Yeol Lee
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Hybrid Approach ◽  
Prediction Method ◽  
Depth Map ◽  
3D Point Cloud ◽  
Industrial Worker ◽  
Cloud Data ◽  
Depth Prediction ◽  
Physical Objects

Typical AR methods have generic problems such as visual mismatching, incorrect occlusions, and limited augmentation due to the inability to estimate depth from AR images and attaching the AR markers onto physical objects, which prevents the industrial worker from conducting manufacturing tasks effectively. This paper proposes a hybrid approach to industrial AR for complementing existing AR methods using deep learning-based facility segmentation and depth prediction without AR markers and a depth camera. First, the outlines of physical objects are extracted by applying a deep learning-based instance segmentation method to the RGB image acquired from the AR camera. Simultaneously, a depth prediction method is applied to the AR image to estimate the depth map as a 3D point cloud for the detected object. Based on the segmented 3D point cloud data, 3D spatial relationships among the physical objects are calculated, which can assist in solving the visual mismatch and occlusion problems properly. In addition, it can deal with a dynamically operating or a moving facility, such as a robot—the conventional AR cannot do so. For these reasons, the proposed approach can be utilized as a hybrid or complementing function to existing AR methods, since it can be activated whenever the industrial worker requires handing of visual mismatches or occlusions. Quantitative and qualitative analyses verify the advantage of the proposed approach compared with existing AR methods. Some case studies also prove that the proposed method can be applied not only to manufacturing but also to other fields. These studies confirm the scalability, effectiveness, and originality of this proposed approach.

Deep Learning-Based Classification of Large-Scale Airborne LiDAR Point Cloud

2021 ◽  
pp. 1-15
Author(s):  
Mathieu Turgeon-Pelchat ◽  
Samuel Foucher ◽  
Yacine Bouroubi
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Large Scale ◽  
Airborne Lidar

scholarly journals Label3DMaize: toolkit for 3D point cloud data annotation of maize shoots

GigaScience ◽  
2021 ◽  
Vol 10 (5) ◽  
Author(s):  
Teng Miao ◽  
Weiliang Wen ◽  
Yinglun Li ◽  
Sheng Wu ◽  
Chao Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Training Dataset ◽  
Growth Stages ◽  
3D Point Cloud ◽  
Plant Structure ◽  
Data Annotation ◽  
Cloud Data ◽  
Point Cloud Segmentation ◽  
Different Growth Stages

Abstract Background The 3D point cloud is the most direct and effective data form for studying plant structure and morphology. In point cloud studies, the point cloud segmentation of individual plants to organs directly determines the accuracy of organ-level phenotype estimation and the reliability of the 3D plant reconstruction. However, highly accurate, automatic, and robust point cloud segmentation approaches for plants are unavailable. Thus, the high-throughput segmentation of many shoots is challenging. Although deep learning can feasibly solve this issue, software tools for 3D point cloud annotation to construct the training dataset are lacking. Results We propose a top-to-down point cloud segmentation algorithm using optimal transportation distance for maize shoots. We apply our point cloud annotation toolkit for maize shoots, Label3DMaize, to achieve semi-automatic point cloud segmentation and annotation of maize shoots at different growth stages, through a series of operations, including stem segmentation, coarse segmentation, fine segmentation, and sample-based segmentation. The toolkit takes ∼4–10 minutes to segment a maize shoot and consumes 10–20% of the total time if only coarse segmentation is required. Fine segmentation is more detailed than coarse segmentation, especially at the organ connection regions. The accuracy of coarse segmentation can reach 97.2% that of fine segmentation. Conclusion Label3DMaize integrates point cloud segmentation algorithms and manual interactive operations, realizing semi-automatic point cloud segmentation of maize shoots at different growth stages. The toolkit provides a practical data annotation tool for further online segmentation research based on deep learning and is expected to promote automatic point cloud processing of various plants.

Adaptive Deep Learning-based Point Cloud Geometry Coding

2020 ◽  
pp. 1-1
Author(s):  
Andre Guarda ◽  
Nuno Rodrigues ◽  
Fernando Pereira
Keyword(s):  
Deep Learning ◽  
Point Cloud
Sign in / Sign up

Export Citation Format

Share Document