scholarly journals Evaluation of deep learning algorithms for semantic segmentation of car parts

2021 ◽  
Author(s):  
Kitsuchart Pasupa ◽  
Phongsathorn Kittiworapanya ◽  
Napasin Hongngern ◽  
Kuntpong Woraratpanya
Keyword(s):  
Deep Learning ◽  
Evaluation System ◽  
Learning Algorithms ◽  
Weather Conditions ◽  
Semantic Segmentation ◽  
Smart Device ◽  
Data Set ◽  
Basic Part ◽  
Left And Right ◽  
Instance Segmentation

AbstractEvaluation of car damages from an accident is one of the most important processes in the car insurance business. Currently, it still needs a manual examination of every basic part. It is expected that a smart device will be able to do this evaluation more efficiently in the future. In this study, we evaluated and compared five deep learning algorithms for semantic segmentation of car parts. The baseline reference algorithm was Mask R-CNN, and the other algorithms were HTC, CBNet, PANet, and GCNet. Runs of instance segmentation were conducted with those five algorithms. HTC with ResNet-50 was the best algorithm for instance segmentation on various kinds of cars such as sedans, trucks, and SUVs. It achieved a mean average precision at 55.2 on our original data set, that assigned different labels to the left and right sides and 59.1 when a single label was assigned to both sides. In addition, the models from every algorithm were tested for robustness, by running them on images of parts, in a real environment with various weather conditions, including snow, frost, fog and various lighting conditions. GCNet was the most robust; it achieved a mean performance under corruption, mPC = 35.2, and a relative degradation of performance on corrupted data, compared to clean data (rPC), of 64.4%, when left and right sides were assigned different labels, and mPC = 38.1 and rPC = $$69.6\%$$ 69.6 % when left- and right-side parts were considered the same part. The findings from this study may directly benefit developers of automated car damage evaluation system in their quest for the best design.

scholarly journals Semantic segmentation of PolSAR image data using advanced deep learning model

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rajat Garg ◽  
Anil Kumar ◽  
Nikunj Bansal ◽  
Manish Prateek ◽  
Shashi Kumar
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Urban Area ◽  
Urban Areas ◽  
Learning Algorithms ◽  
Semantic Segmentation ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Deep Learning Model

AbstractUrban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.

scholarly journals InstantDL: an easy-to-use deep learning pipeline for image segmentation and classification

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Dominik Jens Elias Waibel ◽  
Sayedali Shetab Boushehri ◽  
Carsten Marr
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Specific Problem ◽  
State Of The Art ◽  
Image Data ◽  
Semantic Segmentation ◽  
Parameter Tuning ◽  
Cellular Processes ◽  
Minimal Effort ◽  
Instance Segmentation

Abstract Background Deep learning contributes to uncovering molecular and cellular processes with highly performant algorithms. Convolutional neural networks have become the state-of-the-art tool to provide accurate and fast image data processing. However, published algorithms mostly solve only one specific problem and they typically require a considerable coding effort and machine learning background for their application. Results We have thus developed InstantDL, a deep learning pipeline for four common image processing tasks: semantic segmentation, instance segmentation, pixel-wise regression and classification. InstantDL enables researchers with a basic computational background to apply debugged and benchmarked state-of-the-art deep learning algorithms to their own data with minimal effort. To make the pipeline robust, we have automated and standardized workflows and extensively tested it in different scenarios. Moreover, it allows assessing the uncertainty of predictions. We have benchmarked InstantDL on seven publicly available datasets achieving competitive performance without any parameter tuning. For customization of the pipeline to specific tasks, all code is easily accessible and well documented. Conclusions With InstantDL, we hope to empower biomedical researchers to conduct reproducible image processing with a convenient and easy-to-use pipeline.

scholarly journals AUTOMATED MARINE OIL SPILL DETECTION USING DEEP LEARNING INSTANCE SEGMENTATION MODEL

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 1271-1276
Author(s):  
S. T. Yekeen ◽  
A.-L. Balogun
Keyword(s):  
Deep Learning ◽  
Oil Spill ◽  
Semantic Segmentation ◽  
Learning Models ◽  
Marine Oil ◽  
Conventional Machine ◽  
Feature Pyramid ◽  
Model Training ◽  
Instance Segmentation ◽  
Better Than

Abstract. This study developed a novel deep learning oil spill instance segmentation model using Mask-Region-based Convolutional Neural Network (Mask R-CNN) model which is a state-of-the-art computer vision model. A total of 2882 imageries containing oil spill, look-alike, ship, and land area after conducting different pre-processing activities were acquired. These images were subsequently sub-divided into 88% training and 12% for testing, equating to 2530 and 352 images respectively. The model training was conducted using transfer learning on a pre-trained ResNet 101 with COCO data as a backbone in combination with Feature Pyramid Network (FPN) architecture for the extraction of features at 30 epochs with 0.001 learning rate. The model’s performance was evaluated using precision, recall, and F1-measure which shows a higher performance than other existing models with value of 0.964, 0.969 and 0.968 respectively. As a specialized task, the study concluded that the developed deep learning instance segmentation model (Mask R-CNN) performs better than conventional machine learning models and semantic segmentation deep learning models in detection and segmentation of marine oil spill.

scholarly journals Research on Multi-Object Sorting System Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6238
Author(s):  
Hongyan Zhang ◽  
Huawei Liang ◽  
Tao Ni ◽  
Lingtao Huang ◽  
Jinsong Yang
Keyword(s):  
Deep Learning ◽  
Target Detection ◽  
Training Model ◽  
Normal Vector ◽  
Data Set ◽  
Integrated Network ◽  
Object Sorting ◽  
Sorting System ◽  
Rotating Target ◽  
Instance Segmentation

As a complex task, robot sorting has become a research hotspot. In order to enable robots to perform simple, efficient, stable and accurate sorting operations for stacked multi-objects in unstructured scenes, a robot multi-object sorting system is built in this paper. Firstly, the training model of rotating target detection is constructed, and the placement state of five common objects in unstructured scenes is collected as the training set for training. The trained model is used to obtain the position, rotation angle and category of the target object. Then, the instance segmentation model is constructed, and the same data set is made, and the instance segmentation network model is trained. Then, the optimized Mask R-CNN instance segmentation network is used to segment the object surface pixels, and the upper surface point cloud is extracted to calculate the normal vector. Then, the angle obtained by the normal vector of the upper surface and the rotation target detection network is fused with the normal vector to obtain the attitude of the object. At the same time, the grasping order is calculated according to the average depth of the surface. Finally, after the obtained object posture, category and grasping sequence are fused, the performance of the rotating target detection network, the instance segmentation network and the robot sorting system are tested on the established experimental platform. Based on this system, this paper carried out an experiment on the success rate of object capture in a single network and an integrated network. The experimental results show that the multi-object sorting system based on deep learning proposed in this paper can sort stacked objects efficiently, accurately and stably in unstructured scenes.

scholarly journals MIScnn: a framework for medical image segmentation with convolutional neural networks and deep learning

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Dominik Müller ◽  
Frank Kramer
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Medical Image ◽  
Cross Validation ◽  
Data Augmentation ◽  
Semantic Segmentation ◽  
Medical Image Segmentation ◽  
Tumor Segmentation ◽  
Data Set ◽  
Public Data

Abstract Background The increased availability and usage of modern medical imaging induced a strong need for automatic medical image segmentation. Still, current image segmentation platforms do not provide the required functionalities for plain setup of medical image segmentation pipelines. Already implemented pipelines are commonly standalone software, optimized on a specific public data set. Therefore, this paper introduces the open-source Python library MIScnn. Implementation The aim of MIScnn is to provide an intuitive API allowing fast building of medical image segmentation pipelines including data I/O, preprocessing, data augmentation, patch-wise analysis, metrics, a library with state-of-the-art deep learning models and model utilization like training, prediction, as well as fully automatic evaluation (e.g. cross-validation). Similarly, high configurability and multiple open interfaces allow full pipeline customization. Results Running a cross-validation with MIScnn on the Kidney Tumor Segmentation Challenge 2019 data set (multi-class semantic segmentation with 300 CT scans) resulted into a powerful predictor based on the standard 3D U-Net model. Conclusions With this experiment, we could show that the MIScnn framework enables researchers to rapidly set up a complete medical image segmentation pipeline by using just a few lines of code. The source code for MIScnn is available in the Git repository: https://github.com/frankkramer-lab/MIScnn.

scholarly journals InstantDL - An easy-to-use deep learning pipeline for image segmentation and classification

2020 ◽  
Author(s):  
Dominik Waibel ◽  
Sayedali Shetab Boushehri ◽  
Carsten Marr
Keyword(s):  
Deep Learning ◽  
Specific Problem ◽  
State Of The Art ◽  
Image Data ◽  
Semantic Segmentation ◽  
Parameter Tuning ◽  
Biomedical Image ◽  
Cellular Processes ◽  
Minimal Effort ◽  
Instance Segmentation

AbstractMotivationDeep learning contributes to uncovering and understanding molecular and cellular processes with highly performant image computing algorithms. Convolutional neural networks have become the state-of-the-art tool to provide accurate, consistent and fast data processing. However, published algorithms mostly solve only one specific problem and they often require expert skills and a considerable computer science and machine learning background for application.ResultsWe have thus developed a deep learning pipeline called InstantDL for four common image processing tasks: semantic segmentation, instance segmentation, pixel-wise regression and classification. InstantDL enables experts and non-experts to apply state-of-the-art deep learning algorithms to biomedical image data with minimal effort. To make the pipeline robust, we have automated and standardized workflows and extensively tested it in different scenarios. Moreover, it allows to assess the uncertainty of predictions. We have benchmarked InstantDL on seven publicly available datasets achieving competitive performance without any parameter tuning. For customization of the pipeline to specific tasks, all code is easily accessible.Availability and ImplementationInstantDL is available under the terms of MIT licence. It can be found on GitHub: https://github.com/marrlab/[email protected]

scholarly journals Compound2DeNovoDrugPropMax –a novel programmatic tool incorporating deep learning and in silico methods for automated bio-activity discovery for any compound of interest

2021 ◽  
Author(s):  
Ben Geoffrey A S ◽  
Rafal Madaj ◽  
Akhil Sanker ◽  
Pavan Preetham Valluri ◽  
Harshmeet Singh
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
In Silico ◽  
Drug Target ◽  
Learning Algorithms ◽  
Network Data ◽  
Ligand Interaction ◽  
Data Set ◽  
Target Interaction ◽  
Pubchem Compound

Network data is composed of nodes and edges. Successful application of machine learning/deep learning algorithms on network data to make node classification and link prediction have been shown in the area of social networks through which highly customized suggestions are offered to social<br>network users. Similarly one can attempt the use of machine learning/deep learning algorithms on biological network data to generate predictions of scientific usefulness. In the presented work, compound-drug target interaction network data set from bindingDB has been used to train deep learning neural network and a multi class classification has been implemented to classify PubChem compound queried by the user into class labels of PBD IDs. This way target interaction prediction for PubChem compounds is carried out using deep learning. The user is required to input the PubChem Compound ID (CID) of the compound the user wishes to gain information about its predicted biological activity and the tool outputs the RCSB PDB IDs of the predicted drug target interaction for the input CID. Further the tool also optimizes the compound of interest of the user toward drug likeness properties through a deep learning based structure optimization with a deep learning based<br>drug likeness optimization protocol. The tool also incorporates a feature to perform automated In Silico modelling for the compounds and the predicted drug targets to uncover their protein-ligand interaction profiles. The program is hosted, supported and maintained at the following GitHub repository<div><br></div>https://github.com/bengeof/Compound2DeNovoDrugPropMax<br>

scholarly journals Convolutional Neural Network-Based Instance Segmentation Algorithm to Acquire Quantitative Criteria of Early Mouse Development

2018 ◽  
Author(s):  
Yuta Tokuoka ◽  
Takahiro G Yamada ◽  
Noriko F Hiroi ◽  
Tetsuya J Kobayashi ◽  
Kazuo Yamagata ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Three Dimensional ◽  
Semantic Segmentation ◽  
Critical Issue ◽  
Segmentation Algorithm ◽  
Embryonic Cells ◽  
Mouse Development ◽  
Instance Segmentation

AbstractIn embryology, image processing methods such as segmentation are applied to acquiring quantitative criteria from time-series three-dimensional microscopic images. When used to segment cells or intracellular organelles, several current deep learning techniques outperform traditional image processing algorithms. However, segmentation algorithms still have unsolved problems, especially in bioimage processing. The most critical issue is that the existing deep learning-based algorithms for bioimages can perform only semantic segmentation, which distinguishes whether a pixel is within an object (for example, nucleus) or not. In this study, we implemented a novel segmentation algorithm, based on deep learning, which segments each nucleus and adds different labels to the detected objects. This segmentation algorithm is called instance segmentation. Our instance segmentation algorithm, implemented as a neural network, which we named QCA Net, substantially outperformed 3D U-Net, which is the best semantic segmentation algorithm that uses deep learning. Using QCA Net, we quantified the nuclear number, volume, surface area, and center of gravity coordinates during the development of mouse embryos. In particular, QCA Net distinguished nuclei of embryonic cells from those of polar bodies formed in meiosis. We consider that QCA Net can greatly contribute to bioimage segmentation in embryology by generating quantitative criteria from segmented images.

Sign in / Sign up

Export Citation Format

Share Document