Deep Learning-Based Multi-class 3D Objects Classification Using Digital Holographic Complex Images

2021 ◽  
pp. 443-448
Author(s):  
R. N. Uma Mahesh ◽  
B. Lokesh Reddy ◽  
Anith Nelleri
Keyword(s):  
Deep Learning ◽  
3D Objects ◽  
Complex Images

scholarly journals A Survey on Various Available Object Detection Models and Application In Automatic License Plate Detection

2021 ◽  
Vol 23 (06) ◽  
pp. 47-57
Author(s):  
Aditya Kulkarni ◽  
◽  
Manali Munot ◽  
Sai Salunkhe ◽  
Shubham Mhaske ◽  
...  
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Image Databases ◽  
License Plate ◽  
Learning Models ◽  
Python Language ◽  
Performance Accuracy ◽  
License Plate Detection ◽  
Bounding Boxes ◽  
Complex Images

With the development in technologies right from serial to parallel computing, GPU, AI, and deep learning models a series of tools to process complex images have been developed. The main focus of this research is to compare various algorithms(pre-trained models) and their contributions to process complex images in terms of performance, accuracy, time, and their limitations. The pre-trained models we are using are CNN, R-CNN, R-FCN, and YOLO. These models are python language-based and use libraries like TensorFlow, OpenCV, and free image databases (Microsoft COCO and PAS-CAL VOC 2007/2012). These not only aim at object detection but also on building bounding boxes around appropriate locations. Thus, by this review, we get a better vision of these models and their performance and a good idea of which models are ideal for various situations.

scholarly journals MLMT-CNN for object detection and segmentation in multi-layer and multi-spectral images

2021 ◽  
Vol 33 (1) ◽  
Author(s):  
Majedaldein Almahasneh ◽  
Adeline Paiement ◽  
Xianghua Xie ◽  
Jean Aboudarham
Keyword(s):  
Deep Learning ◽  
Active Regions ◽  
Magnetic Resonance Images ◽  
Supervised Machine Learning ◽  
Training Strategy ◽  
Learning Framework ◽  
3D Objects ◽  
Main Challenge ◽  
Spatial Configurations ◽  
Bounding Boxes

AbstractPrecisely localising solar Active Regions (AR) from multi-spectral images is a challenging but important task in understanding solar activity and its influence on space weather. A main challenge comes from each modality capturing a different location of the 3D objects, as opposed to typical multi-spectral imaging scenarios where all image bands observe the same scene. Thus, we refer to this special multi-spectral scenario as multi-layer. We present a multi-task deep learning framework that exploits the dependencies between image bands to produce 3D AR localisation (segmentation and detection) where different image bands (and physical locations) have their own set of results. Furthermore, to address the difficulty of producing dense AR annotations for training supervised machine learning (ML) algorithms, we adapt a training strategy based on weak labels (i.e. bounding boxes) in a recursive manner. We compare our detection and segmentation stages against baseline approaches for solar image analysis (multi-channel coronal hole detection, SPOCA for ARs) and state-of-the-art deep learning methods (Faster RCNN, U-Net). Additionally, both detection and segmentation stages are quantitatively validated on artificially created data of similar spatial configurations made from annotated multi-modal magnetic resonance images. Our framework achieves an average of 0.72 IoU (segmentation) and 0.90 F1 score (detection) across all modalities, comparing to the best performing baseline methods with scores of 0.53 and 0.58, respectively, on the artificial dataset, and 0.84 F1 score in the AR detection task comparing to baseline of 0.82 F1 score. Our segmentation results are qualitatively validated by an expert on real ARs.

scholarly journals Research on Identification of Road Features from Point Cloud Data Using Deep Learning

2021 ◽  
Vol 15 (3) ◽  
pp. 274-289
Author(s):  
Yoshimasa Umehara ◽  
Yoshinori Tsukada ◽  
Kenji Nakamura ◽  
Shigenori Tanaka ◽  
Koki Nakahata ◽  
...  
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Three Dimensional ◽  
Measurement Technology ◽  
Depth Information ◽  
Point Cloud Data ◽  
Laser Measurement ◽  
Cloud Data ◽  
3D Objects ◽  
Efficient Management

Laser measurement technology has progressed significantly in recent years, and diverse methods have been developed to measure three-dimensional (3D) objects within environmental spaces in the form of point cloud data. Although such point cloud data are expected to be used in a variety of applications, such data do not possess information on the specific features represented by the points, making it necessary to manually select the target features. Therefore, the identification of road features is essential for the efficient management of point cloud data. As a technology for identifying features from the point cloud data of road spaces, in this research, we propose a method for automatically dividing point cloud data into units of features and identifying features from projected images with added depth information. We experimentally verified that the proposed method accurately identifies and extracts such features.

Intelligent 3D Objects Classification for Vehicular Ad Hoc Network Based on Lidar and Deep Learning Approaches

2021 ◽  
pp. 1-10
Author(s):  
Pedro Henrique Feijo de Sousa ◽  
Jefferson Silva Almeida ◽  
Elene Firmeza Ohata ◽  
Fabricio Gonzalez Nogueira ◽  
Bismark Claure Torrico ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
Vehicular Ad Hoc Network ◽  
Learning Approaches ◽  
3D Objects

scholarly journals Deep Learning-Based Point Upsampling for Edge Enhancement of 3D-Scanned Data and Its Application to Transparent Visualization

2021 ◽  
Vol 13 (13) ◽  
pp. 2526
Author(s):  
Weite Li ◽  
Kyoko Hasegawa ◽  
Liang Li ◽  
Akihiro Tsukamoto ◽  
Satoshi Tanaka
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
3D Structure ◽  
Point Clouds ◽  
Edge Point ◽  
Point Distribution ◽  
3D Objects ◽  
Combined Use ◽  
Edge Points

Large-scale 3D-scanned point clouds enable the accurate and easy recording of complex 3D objects in the real world. The acquired point clouds often describe both the surficial and internal 3D structure of the scanned objects. The recently proposed edge-highlighted transparent visualization method is effective for recognizing the whole 3D structure of such point clouds. This visualization utilizes the degree of opacity for highlighting edges of the 3D-scanned objects, and it realizes clear transparent viewing of the entire 3D structures. However, for 3D-scanned point clouds, the quality of any edge-highlighting visualization depends on the distribution of the extracted edge points. Insufficient density, sparseness, or partial defects in the edge points can lead to unclear edge visualization. Therefore, in this paper, we propose a deep learning-based upsampling method focusing on the edge regions of 3D-scanned point clouds to generate more edge points during the 3D-edge upsampling task. The proposed upsampling network dramatically improves the point-distributional density, uniformity, and connectivity in the edge regions. The results on synthetic and scanned edge data show that our method can improve the percentage of edge points more than 15% compared to the existing point cloud upsampling network. Our upsampling network works well for both sharp and soft edges. A combined use with a noise-eliminating filter also works well. We demonstrate the effectiveness of our upsampling network by applying it to various real 3D-scanned point clouds. We also prove that the improved edge point distribution can improve the visibility of the edge-highlighted transparent visualization of complex 3D-scanned objects.

scholarly journals Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding

2021 ◽  
Author(s):  
Hsien-Yu Meng ◽  
Zhenyu Tang ◽  
Dinesh Manocha
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Sound Propagation ◽  
Learning Algorithm ◽  
Acoustic Scattering ◽  
Dynamic Scenes ◽  
Discrete Laplacian ◽  
3D Objects ◽  
Geometric Objects ◽  
Arbitrary Objects

We present a novel geometric deep learning method to compute the acoustic scattering properties of geometric objects. Our learning algorithm uses a point cloud representation of objects to compute the scattering properties and integrates them with ray tracing for interactive sound propagation in dynamic scenes. We use discrete Laplacian-based surface encoders and approximate the neighborhood of each point using a shared multi-layer perceptron. We show that our formulation is permutation invariant and present a neural network that computes the scattering function using spherical harmonics. Our approach can handle objects with arbitrary topologies and deforming models, and takes less than 1ms per object on a commodity GPU. We have analyzed the accuracy and perform validation on thousands of unseen 3D objects and highlight the benefits over other point-based geometric deep learning methods. To the best of our knowledge, this is the first real-time learning algorithm that can approximate the acoustic scattering properties of arbitrary objects with high accuracy.

Sign in / Sign up

Export Citation Format

Share Document