Mapping Surface Winds on Mars from the Global Distribution of Barchan Dunes Employing an Instance Segmentation Neural Network

The surface of Mars is riddled with dunes that form by accumulating sand particles that are carried by the wind. Since dune geometry and orientation adjust in response to prevailing wind conditions, the morphometrics of dunes can reveal information about the winds that formed them. Previous studies inferred the prevailing local wind direction from the orientation of dunes by manually analyzing spacecraft imagery. However, building a global map remained challenging, as manual detection of individual dunes over the entire Martian surface is impractical. Here, we employ Mask R-CNN, a state-of-the-art instance segmentation neural network, to detect and analyze isolated barchan dunes on a global scale. We prepared a training dataset by extracting Mars Context Camera (CTX) scenes of dune fields from a global CTX mosaic, as identified in the global dune-fields catalog. Images were cropped and standardized to a resolution of 832x832 pixels, and labeled using Labelbox&#8217;s online instance segmentation platform. Image augmentation and weight decay were employed to prevent overfitting during training. By inspecting 100 sample images from the validation database, we find that the network correctly identified ~86% of the isolated dunes, falsely identifying one feature as a barchan dune in a single image.After dune outlines are detected, they are automatically analyzed to extract the dominant-wind and net sand-flux directions using traditional computer vision techniques. We expect our future surface-wind dataset to serve as a constraint for atmospheric global circulation models to help predict weather events for upcoming in situ mission as well as shed new light on the recent climate history of Mars.

Download Full-text

Learning from Synthetic Dataset for Crop Seed Instance Segmentation

10.1101/866921 ◽

2019 ◽

Author(s):

Yosuke Toda ◽

Fumio Okura ◽

Jun Ito ◽

Satoshi Okada ◽

Toshinori Kinoshita ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Large Scale ◽

Synthetic Data ◽

Seed Morphology ◽

Training Data ◽

Training Dataset ◽

Labor Costs ◽

Data Annotation ◽

Instance Segmentation

Incorporating deep learning in the image analysis pipeline has opened the possibility of introducing precision phenotyping in the field of agriculture. However, to train the neural network, a sufficient amount of training data must be prepared, which requires a time-consuming manual data annotation process that often becomes the limiting step. Here, we show that an instance segmentation neural network (Mask R-CNN) aimed to phenotype the barley seed morphology of various cultivars, can be sufficiently trained purely by a synthetically generated dataset. Our attempt is based on the concept of domain randomization, where a large amount of image is generated by randomly orienting the seed object to a virtual canvas. After training with such a dataset, performance based on recall and the average Precision of the real-world test dataset achieved 96% and 95%, respectively. Applying our pipeline enables extraction of morphological parameters at a large scale, enabling precise characterization of the natural variation of barley from a multivariate perspective. Importantly, we show that our approach is effective not only for barley seeds but also for various crops including rice, lettuce, oat, and wheat, and thus supporting the fact that the performance benefits of this technique is generic. We propose that constructing and utilizing such synthetic data can be a powerful method to alleviate human labor costs needed to prepare the training dataset for deep learning in the agricultural domain.

Download Full-text

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.10.ipas-180 ◽

2020 ◽

Vol 2020 (10) ◽

pp. 181-1-181-7

Author(s):

Takahiro Kudo ◽

Takanori Fujisawa ◽

Takuro Yamaguchi ◽

Masaaki Ikehara

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Architecture ◽

Large Scale ◽

Blind Deconvolution ◽

Training Dataset ◽

Image Deconvolution ◽

Classic Problem ◽

Key Points ◽

Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Download Full-text

Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

Scientific Reports ◽

10.1038/s41598-020-78129-0 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Young-Gon Kim ◽

Sungchul Kim ◽

Cristina Eunbee Cho ◽

In Hye Song ◽

Hee Jin Lee ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Frozen Section ◽

Medical Center ◽

External Validation ◽

Model Performance ◽

Classification Model ◽

Training Dataset

AbstractFast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

Download Full-text

Orchard Mapping with Deep Learning Semantic Segmentation

Sensors ◽

10.3390/s21113813 ◽

2021 ◽

Vol 21 (11) ◽

pp. 3813

Author(s):

Athanasios Anagnostis ◽

Aristotelis C. Tagarakis ◽

Dimitrios Kateris ◽

Vasileios Moysiadis ◽

Claus Grøn Sørensen ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Semantic Segmentation ◽

Automated Detection ◽

Aerial Images ◽

Training Dataset ◽

Field Boundary ◽

Different Seasons ◽

Detection And Localization ◽

Different Levels

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.

Download Full-text

Deep neural network-based detection and segmentation of intracranial aneurysms on 3D rotational DSA

Interventional Neuroradiology ◽

10.1177/15910199211000956 ◽

2021 ◽

pp. 159101992110009

Author(s):

Xinke Liu ◽

Junqiang Feng ◽

Zhenzhou Wu ◽

Zhonghao Neo ◽

Chengcheng Zhu ◽

...

Keyword(s):

Neural Network ◽

Intracranial Aneurysms ◽

Training Dataset ◽

Maximum Diameter ◽

Free Response ◽

Final Model ◽

Test Dataset ◽

Segmentation Accuracy ◽

Froc Analysis ◽

Aneurysm Detection

Objective Accurate diagnosis and measurement of intracranial aneurysms are challenging. This study aimed to develop a 3D convolutional neural network (CNN) model to detect and segment intracranial aneurysms (IA) on 3D rotational DSA (3D-RA) images. Methods 3D-RA images were collected and annotated by 5 neuroradiologists. The annotated images were then divided into three datasets: training, validation, and test. A 3D Dense-UNet-like CNN (3D-Dense-UNet) segmentation algorithm was constructed and trained using the training dataset. Diagnostic performance to detect aneurysms and segmentation accuracy was assessed for the final model on the test dataset using the free-response receiver operating characteristic (FROC). Finally, the CNN-inferred maximum diameter was compared against expert measurements by Pearson’s correlation and Bland-Altman limits of agreement (LOA). Results A total of 451 patients with 3D-RA images were split into n = 347/41/63 training/validation/test datasets, respectively. For aneurysm detection, observed FROC analysis showed that the model managed to attain a sensitivity of 0.710 at 0.159 false positives (FP)/case, and 0.986 at 1.49 FP/case. The proposed method had good agreement with reference manual aneurysmal maximum diameter measurements (8.3 ± 4.3 mm vs. 7.8 ± 4.8 mm), with a correlation coefficient r = 0.77, small bias of 0.24 mm, and LOA of -6.2 to 5.71 mm. 37.0% and 77% of diameter measurements were within ±1 mm and ±2.5 mm of expert measurements. Conclusions A 3D-Dense-UNet model can detect and segment aneurysms with relatively high accuracy using 3D-RA images. The automatically measured maximum diameter has potential clinical application value.

Download Full-text

Prediction of Bead Geometry with Changing Welding Speed Using Artificial Neural Network

Materials ◽

10.3390/ma14061494 ◽

2021 ◽

Vol 14 (6) ◽

pp. 1494

Author(s):

Ran Li ◽

Manshu Dong ◽

Hongming Gao

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Welding Speed ◽

Gas Metal Arc Welding ◽

Welding Process ◽

Training Dataset ◽

Welding Parameters ◽

Bead Geometry ◽

Bead Width ◽

Artificial Neural

Bead size and shape are important considerations for industry design and quality detection. It is hard to deduce an appropriate mathematical model for predicting the bead geometry in a continually changing welding process due to the complex interrelationship between different welding parameters and the actual bead. In this paper, an artificial neural network model for predicting the bead geometry with changing welding speed was developed. The experiment was performed by a welding robot in gas metal arc welding process. The welding speed was stochastically changed during the welding process. By transient response tests, it was indicated that the changing welding speed had a spatial influence on bead geometry, which ranged from 10 mm backward to 22 mm forward with certain welding parameters. For this study, the input parameters of model were the spatial welding speed sequence, and the output parameters were bead width and reinforcement. The bead geometry was recognized by polynomial fitting of the profile coordinates, as measured by a structured laser light sensor. The results showed that the model with the structure of 33-6-2 had achieved high accuracy in both the training dataset and test dataset, which were 99% and 96%, respectively.

Download Full-text

Development of in-house fully residual deep convolutional neural network-based segmentation software for the male pelvic CT

Radiation Oncology ◽

10.1186/s13014-021-01867-6 ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Hideaki Hirashima ◽

Mitsuhiro Nakamura ◽

Pascal Baillehache ◽

Yusuke Fujimoto ◽

Shota Nakagawa ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Volumetric Modulated Arc Therapy ◽

Intensity Modulated Radiotherapy ◽

Deep Convolutional Neural Network ◽

Training Dataset ◽

Dice Similarity Coefficient ◽

Optimal Model ◽

Pelvic Region ◽

Segmentation Accuracy

Abstract Background This study aimed to (1) develop a fully residual deep convolutional neural network (CNN)-based segmentation software for computed tomography image segmentation of the male pelvic region and (2) demonstrate its efficiency in the male pelvic region. Methods A total of 470 prostate cancer patients who had undergone intensity-modulated radiotherapy or volumetric-modulated arc therapy were enrolled. Our model was based on FusionNet, a fully residual deep CNN developed to semantically segment biological images. To develop the CNN-based segmentation software, 450 patients were randomly selected and separated into the training, validation and testing groups (270, 90, and 90 patients, respectively). In Experiment 1, to determine the optimal model, we first assessed the segmentation accuracy according to the size of the training dataset (90, 180, and 270 patients). In Experiment 2, the effect of varying the number of training labels on segmentation accuracy was evaluated. After determining the optimal model, in Experiment 3, the developed software was used on the remaining 20 datasets to assess the segmentation accuracy. The volumetric dice similarity coefficient (DSC) and the 95th-percentile Hausdorff distance (95%HD) were calculated to evaluate the segmentation accuracy for each organ in Experiment 3. Results In Experiment 1, the median DSC for the prostate were 0.61 for dataset 1 (90 patients), 0.86 for dataset 2 (180 patients), and 0.86 for dataset 3 (270 patients), respectively. The median DSCs for all the organs increased significantly when the number of training cases increased from 90 to 180 but did not improve upon further increase from 180 to 270. The number of labels applied during training had a little effect on the DSCs in Experiment 2. The optimal model was built by 270 patients and four organs. In Experiment 3, the median of the DSC and the 95%HD values were 0.82 and 3.23 mm for prostate; 0.71 and 3.82 mm for seminal vesicles; 0.89 and 2.65 mm for the rectum; 0.95 and 4.18 mm for the bladder, respectively. Conclusions We have developed a CNN-based segmentation software for the male pelvic region and demonstrated that the CNN-based segmentation software is efficient for the male pelvic region.

Download Full-text

Introducing Asymmetry into Interneuron Learning

Neural Computation ◽

10.1162/neco.1995.7.6.1191 ◽

1995 ◽

Vol 7 (6) ◽

pp. 1191-1205 ◽

Cited By ~ 16

Author(s):

Colin Fyfe

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Negative Feedback ◽

Principal Components ◽

Network Architecture ◽

Hebbian Learning ◽

Principal Component ◽

Neural Network Architecture ◽

Weight Decay ◽

Artificial Neural Network Architecture

A review is given of a new artificial neural network architecture in which the weights converge to the principal component subspace. The weights learn by only simple Hebbian learning yet require no clipping, normalization or weight decay. The net self-organizes using negative feedback of activation from a set of "interneurons" to the input neurons. By allowing this negative feedback from the interneurons to act on other interneurons we can introduce the necessary asymmetry to cause convergence to the actual principal components. Simulations and analysis confirm such convergence.

Download Full-text

Automatic Handgun Detection with Deep Learning in Video Surveillance Images

Applied Sciences ◽

10.3390/app11136085 ◽

2021 ◽

Vol 11 (13) ◽

pp. 6085

Author(s):

Jesus Salido ◽

Vanesa Lomas ◽

Jesus Ruiz-Santaquiteria ◽

Oscar Deniz

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Video Surveillance ◽

Automatic Detection ◽

Public Spaces ◽

Detection Methods ◽

Training Dataset ◽

Average Precision ◽

Terrorist Acts

There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a study based on three convolutional neural network (CNN) models applied to the automatic detection of handguns in video surveillance images. It aims to investigate the reduction of false positives by including pose information associated with the way the handguns are held in the images belonging to the training dataset. The results highlighted the best average precision (96.36%) and recall (97.23%) obtained by RetinaNet fine-tuned with the unfrozen ResNet-50 backbone and the best precision (96.23%) and F1 score values (93.36%) obtained by YOLOv3 when it was trained on the dataset including pose information. This last architecture was the only one that showed a consistent improvement—around 2%—when pose information was expressly considered during training.

Download Full-text

Real-Time 3D object detection using improved convolutional neural network based on image-driven point cloud

Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) ◽

10.2174/2352096514666211026142721 ◽

2021 ◽

Vol 14 ◽

Author(s):

Zhiyong Gao ◽

Jianhong Xiang

Keyword(s):

Neural Network ◽

Object Detection ◽

Convolutional Neural Network ◽

Real Time ◽

Point Cloud ◽

Point Clouds ◽

3D Point Cloud ◽

3D Object ◽

3D Object Detection ◽

Instance Segmentation

Background: While detecting the object directly from the 3D point cloud, the natural 3D patterns and invariance of 3D data are often obscure. Objective: In this work, we aimed at studying the 3D object detection from discrete, disordered and sparse 3D point clouds. Methods: The CNN is composed of the frustum sequence module, 3D instance segmentation module S-NET, 3D point cloud transformation module T-NET, and 3D boundary box estimation module E-NET. The search space of the object is determined by the frustum sequence module. The instance segmentation of the point cloud is performed by the 3D instance segmentation module. The 3D coordinates of the object are confirmed by the transformation module and the 3D bounding box estimation module. Results: Evaluated on KITTI benchmark dataset, our method outperforms the state of the art by remarkable margins while having real-time capability. Conclusion: We achieve real-time 3D object detection by proposing an improved convolutional neural network (CNN) based on image-driven point clouds.

Download Full-text