OmniPD: One-Step Person Detection in Top-View Omnidirectional Indoor Scenes

AbstractWe propose a one-step person detector for topview omnidirectional indoor scenes based on convolutional neural networks (CNNs). While state of the art person detectors reach competitive results on perspective images, missing CNN architectures as well as training data that follows the distortion of omnidirectional images makes current approaches not applicable to our data. The method predicts bounding boxes of multiple persons directly in omnidirectional images without perspective transformation, which reduces overhead of pre- and post-processing and enables realtime performance. The basic idea is to utilize transfer learning to fine-tune CNNs trained on perspective images with data augmentation techniques for detection in omnidirectional images. We fine-tune two variants of Single Shot MultiBox detectors (SSDs). The first one uses Mobilenet v1 FPN as feature extractor (moSSD). The second one uses ResNet50 v1 FPN (resSSD). Both models are pre-trained on Microsoft Common Objects in Context (COCO) dataset. We fine-tune both models on PASCAL VOC07 and VOC12 datasets, specifically on class person. Random 90-degree rotation and random vertical flipping are used for data augmentation in addition to the methods proposed by original SSD. We reach an average precision (AP) of 67.3%with moSSD and 74.9%with resSSD on the evaluation dataset. To enhance the fine-tuning process, we add a subset of HDA Person dataset and a subset of PIROPO database and reduce the number of perspective images to PASCAL VOC07. The AP rises to 83.2% for moSSD and 86.3% for resSSD, respectively. The average inference speed is 28 ms per image for moSSD and 38 ms per image for resSSD using Nvidia Quadro P6000. Our method is applicable to other CNN-based object detectors and can potentially generalize for detecting other objects in omnidirectional images.

Download Full-text

LS-Net: fast single-shot line-segment detector

Machine Vision and Applications ◽

10.1007/s00138-020-01138-6 ◽

2020 ◽

Vol 32 (1) ◽

Author(s):

Van Nhan Nguyen ◽

Robert Jenssen ◽

Davide Roverso

Keyword(s):

Obstacle Avoidance ◽

Line Segment ◽

Data Augmentation ◽

Power Line ◽

Training Data ◽

Power Lines ◽

Single Shot ◽

Physically Based ◽

Augmentation Techniques ◽

Physically Based Rendering

Abstract In unmanned aerial vehicle (UAV) flights, power lines are considered as one of the most threatening hazards and one of the most difficult obstacles to avoid. In recent years, many vision-based techniques have been proposed to detect power lines to facilitate self-driving UAVs and automatic obstacle avoidance. However, most of the proposed methods are typically based on a common three-step approach: (i) edge detection, (ii) the Hough transform, and (iii) spurious line elimination based on power line constrains. These approaches not only are slow and inaccurate but also require a huge amount of effort in post-processing to distinguish between power lines and spurious lines. In this paper, we introduce LS-Net, a fast single-shot line-segment detector, and apply it to power line detection. The LS-Net is by design fully convolutional, and it consists of three modules: (i) a fully convolutional feature extractor, (ii) a classifier, and (iii) a line segment regressor. Due to the unavailability of large datasets with annotations of power lines, we render synthetic images of power lines using the physically based rendering approach and propose a series of effective data augmentation techniques to generate more training data. With a customized version of the VGG-16 network as the backbone, the proposed approach outperforms existing state-of-the-art approaches. In addition, the LS-Net can detect power lines in near real time. This suggests that our proposed approach has a promising role in automatic obstacle avoidance and as a valuable component of self-driving UAVs, especially for automatic autonomous power line inspection.

Download Full-text

Building Damage Detection from Post-Event Aerial Imagery Using Single Shot Multibox Detector

Applied Sciences ◽

10.3390/app9061128 ◽

2019 ◽

Vol 9 (6) ◽

pp. 1128 ◽

Cited By ~ 12

Author(s):

Yundong Li ◽

Wei Hu ◽

Han Dong ◽

Xueyan Zhang

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Hurricane Sandy ◽

Training Data ◽

Aerial Images ◽

Detection Methods ◽

Single Shot ◽

Data Set ◽

Augmentation Strategies ◽

Post Disaster

Using aerial cameras, satellite remote sensing or unmanned aerial vehicles (UAV) equipped with cameras can facilitate search and rescue tasks after disasters. The traditional manual interpretation of huge aerial images is inefficient and could be replaced by machine learning-based methods combined with image processing techniques. Given the development of machine learning, researchers find that convolutional neural networks can effectively extract features from images. Some target detection methods based on deep learning, such as the single-shot multibox detector (SSD) algorithm, can achieve better results than traditional methods. However, the impressive performance of machine learning-based methods results from the numerous labeled samples. Given the complexity of post-disaster scenarios, obtaining many samples in the aftermath of disasters is difficult. To address this issue, a damaged building assessment method using SSD with pretraining and data augmentation is proposed in the current study and highlights the following aspects. (1) Objects can be detected and classified into undamaged buildings, damaged buildings, and ruins. (2) A convolution auto-encoder (CAE) that consists of VGG16 is constructed and trained using unlabeled post-disaster images. As a transfer learning strategy, the weights of the SSD model are initialized using the weights of the CAE counterpart. (3) Data augmentation strategies, such as image mirroring, rotation, Gaussian blur, and Gaussian noise processing, are utilized to augment the training data set. As a case study, aerial images of Hurricane Sandy in 2012 were maximized to validate the proposed method’s effectiveness. Experiments show that the pretraining strategy can improve of 10% in terms of overall accuracy compared with the SSD trained from scratch. These experiments also demonstrate that using data augmentation strategies can improve mAP and mF1 by 72% and 20%, respectively. Finally, the experiment is further verified by another dataset of Hurricane Irma, and it is concluded that the paper method is feasible.

Download Full-text

Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

Diagnostics ◽

10.3390/diagnostics11061052 ◽

2021 ◽

Vol 11 (6) ◽

pp. 1052

Author(s):

Leang Sim Nguon ◽

Kangwon Seo ◽

Jung-Hyun Lim ◽

Tae-Jun Song ◽

Sung-Hyun Cho ◽

...

Keyword(s):

Decision Making ◽

Deep Learning ◽

Network Model ◽

Endoscopic Ultrasonography ◽

Data Augmentation ◽

Clinical Information ◽

Training Data ◽

Fine Tuning ◽

Cystic Neoplasm ◽

Cystic Neoplasms

Mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN) account for a large portion of solitary pancreatic cystic neoplasms (PCN). In this study we implemented a convolutional neural network (CNN) model using ResNet50 to differentiate between MCN and SCN. The training data were collected retrospectively from 59 MCN and 49 SCN patients from two different hospitals. Data augmentation was used to enhance the size and quality of training datasets. Fine-tuning training approaches were utilized by adopting the pre-trained model from transfer learning while training selected layers. Testing of the network was conducted by varying the endoscopic ultrasonography (EUS) image sizes and positions to evaluate the network performance for differentiation. The proposed network model achieved up to 82.75% accuracy and a 0.88 (95% CI: 0.817–0.930) area under curve (AUC) score. The performance of the implemented deep learning networks in decision-making using only EUS images is comparable to that of traditional manual decision-making using EUS images along with supporting clinical information. Gradient-weighted class activation mapping (Grad-CAM) confirmed that the network model learned the features from the cyst region accurately. This study proves the feasibility of diagnosing MCN and SCN using a deep learning network model. Further improvement using more datasets is needed.

Download Full-text

Artificial Intelligence, 3D Documentation, and Rock Art—Approaching and Reflecting on the Automation of Identification and Classification of Rock Art Images

Journal of Archaeological Method and Theory ◽

10.1007/s10816-021-09518-6 ◽

2021 ◽

Author(s):

Christian Horn ◽

Oscar Ivarsson ◽

Cecilia Lindhé ◽

Rich Potter ◽

Ashely Green ◽

...

Keyword(s):

Artificial Intelligence ◽

Bronze Age ◽

Data Augmentation ◽

Rock Art ◽

Training Data ◽

Future Research ◽

Rock Surface ◽

Southern Scandinavia ◽

Bounding Boxes

AbstractRock art carvings, which are best described as petroglyphs, were produced by removing parts of the rock surface to create a negative relief. This tradition was particularly strong during the Nordic Bronze Age (1700–550 BC) in southern Scandinavia with over 20,000 boats and thousands of humans, animals, wagons, etc. This vivid and highly engaging material provides quantitative data of high potential to understand Bronze Age social structures and ideologies. The ability to provide the technically best possible documentation and to automate identification and classification of images would help to take full advantage of the research potential of petroglyphs in southern Scandinavia and elsewhere. We, therefore, attempted to train a model that locates and classifies image objects using faster region-based convolutional neural network (Faster-RCNN) based on data produced by a novel method to improve visualizing the content of 3D documentations. A newly created layer of 3D rock art documentation provides the best data currently available and has reduced inscribed bias compared to older methods. Several models were trained based on input images annotated with bounding boxes produced with different parameters to find the best solution. The data included 4305 individual images in 408 scans of rock art sites. To enhance the models and enrich the training data, we used data augmentation and transfer learning. The successful models perform exceptionally well on boats and circles, as well as with human figures and wheels. This work was an interdisciplinary undertaking which led to important reflections about archaeology, digital humanities, and artificial intelligence. The reflections and the success represented by the trained models open novel avenues for future research on rock art.

Download Full-text

A review: preprocessing techniques and data augmentation for sentiment analysis

Computational Social Networks ◽

10.1186/s40649-020-00080-x ◽

2021 ◽

Vol 8 (1) ◽

Author(s):

Huu-Thanh Duong ◽

Tram-Anh Nguyen-Thi

Keyword(s):

Machine Learning ◽

Sentiment Analysis ◽

Supervised Learning ◽

Data Augmentation ◽

Original Data ◽

Training Data ◽

Unseen Data ◽

Augmentation Techniques ◽

User Intervention

AbstractIn literature, the machine learning-based studies of sentiment analysis are usually supervised learning which must have pre-labeled datasets to be large enough in certain domains. Obviously, this task is tedious, expensive and time-consuming to build, and hard to handle unseen data. This paper has approached semi-supervised learning for Vietnamese sentiment analysis which has limited datasets. We have summarized many preprocessing techniques which were performed to clean and normalize data, negation handling, intensification handling to improve the performances. Moreover, data augmentation techniques, which generate new data from the original data to enrich training data without user intervention, have also been presented. In experiments, we have performed various aspects and obtained competitive results which may motivate the next propositions.

Download Full-text

GaitSense: Towards Ubiquitous Gait-Based Human Identification with Wi-Fi

ACM Transactions on Sensor Networks ◽

10.1145/3466638 ◽

2022 ◽

Vol 18 (1) ◽

pp. 1-24

Author(s):

Yi Zhang ◽

Yue Zheng ◽

Guidong Zhang ◽

Kun Qian ◽

Chen Qian ◽

...

Keyword(s):

Data Augmentation ◽

Gait Recognition ◽

Wearable Sensors ◽

Human Identification ◽

Training Data ◽

Identification Accuracy ◽

Identification System ◽

Gait Patterns ◽

Training Samples ◽

Augmentation Techniques

Gait, the walking manner of a person, has been perceived as a physical and behavioral trait for human identification. Compared with cameras and wearable sensors, Wi-Fi-based gait recognition is more attractive because Wi-Fi infrastructure is almost available everywhere and is able to sense passively without the requirement of on-body devices. However, existing Wi-Fi sensing approaches impose strong assumptions of fixed user walking trajectories, sufficient training data, and identification of already known users. In this article, we present GaitSense , a Wi-Fi-based human identification system, to overcome the above unrealistic assumptions. To deal with various walking trajectories and speeds, GaitSense first extracts target specific features that best characterize gait patterns and applies novel normalization algorithms to eliminate gait irrelevant perturbation in signals. On this basis, GaitSense reduces the training efforts in new deployment scenarios by transfer learning and data augmentation techniques. GaitSense also enables a distinct feature of illegal user identification by anomaly detection, making the system readily available for real-world deployment. Our implementation and evaluation with commodity Wi-Fi devices demonstrate a consistent identification accuracy across various deployment scenarios with little training samples, pushing the limit of gait recognition with Wi-Fi signals.

Download Full-text

Insufficient Data Can Also Rock! Learning to Converse Using Smaller Data with Augmentation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33016698 ◽

2019 ◽

Vol 33 ◽

pp. 6698-6705

Author(s):

Juntao Li ◽

Lisong Qiu ◽

Bo Tang ◽

Dongmin Chen ◽

Dongyan Zhao ◽

...

Keyword(s):

Data Augmentation ◽

Network Models ◽

Generative Models ◽

Training Data ◽

Insufficient Data ◽

Dialogue System ◽

Neural Network Models ◽

Augmentation Techniques ◽

Training Pair ◽

Existing Data

Recent successes of open-domain dialogue generation mainly rely on the advances of deep neural networks. The effectiveness of deep neural network models depends on the amount of training data. As it is laboursome and expensive to acquire a huge amount of data in most scenarios, how to effectively utilize existing data is the crux of this issue. In this paper, we use data augmentation techniques to improve the performance of neural dialogue models on the condition of insufficient data. Specifically, we propose a novel generative model to augment existing data, where the conditional variational autoencoder (CVAE) is employed as the generator to output more training data with diversified expressions. To improve the correlation of each augmented training pair, we design a discriminator with adversarial training to supervise the augmentation process. Moreover, we thoroughly investigate various data augmentation schemes for neural dialogue system with generative models, both GAN and CVAE. Experimental results on two open corpora, Weibo and Twitter, demonstrate the superiority of our proposed data augmentation model.

Download Full-text

MIGAN: Malware Image Synthesis Using GANs

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.330110033 ◽

2019 ◽

Vol 33 ◽

pp. 10033-10034 ◽

Cited By ~ 1

Author(s):

Abhishek Singh ◽

Debojyoti Dutta ◽

Amit Saha

Keyword(s):

Language Processing ◽

Domain Knowledge ◽

Data Augmentation ◽

Image Synthesis ◽

Substantial Improvement ◽

Training Data ◽

Malware Analysis ◽

Training Procedure ◽

Original Dataset ◽

Augmentation Techniques

Majority of the advancement in Deep learning (DL) has occurred in domains such as computer vision, and natural language processing, where abundant training data is available. A major obstacle in leveraging DL techniques for malware analysis is the lack of sufficiently big, labeled datasets. In this paper, we take the first steps towards building a model which can synthesize labeled dataset of malware images using GAN. Such a model can be utilized to perform data augmentation for training a classifier. Furthermore, the model can be shared publicly for community to reap benefits of dataset without sharing the original dataset. First, we show the underlying idiosyncrasies of malware images and why existing data augmentation techniques as well as traditional GAN training fail to produce quality artificial samples. Next, we propose a new method for training GAN where we explicitly embed prior domain knowledge about the dataset into the training procedure. We show improvements in training stability and sample quality assessed on different metrics. Our experiments show substantial improvement on baselines and promise for using such a generative model for malware visualization systems.

Download Full-text

Data set entity recognition based on distant supervision

The Electronic Library ◽

10.1108/el-10-2020-0301 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Pengcheng Li ◽

Qikai Liu ◽

Qikai Cheng ◽

Wei Lu

Keyword(s):

Supervised Learning ◽

Large Scale ◽

Data Augmentation ◽

Scientific Literature ◽

Neural Model ◽

Training Data ◽

Entity Recognition ◽

Data Set ◽

Content Type ◽

Augmentation Techniques

Purpose This paper aims to identify data set entities in scientific literature. To address poor recognition caused by a lack of training corpora in existing studies, a distant supervised learning-based approach is proposed to identify data set entities automatically from large-scale scientific literature in an open domain. Design/methodology/approach Firstly, the authors use a dictionary combined with a bootstrapping strategy to create a labelled corpus to apply supervised learning. Secondly, a bidirectional encoder representation from transformers (BERT)-based neural model was applied to identify data set entities in the scientific literature automatically. Finally, two data augmentation techniques, entity replacement and entity masking, were introduced to enhance the model generalisability and improve the recognition of data set entities. Findings In the absence of training data, the proposed method can effectively identify data set entities in large-scale scientific papers. The BERT-based vectorised representation and data augmentation techniques enable significant improvements in the generality and robustness of named entity recognition models, especially in long-tailed data set entity recognition. Originality/value This paper provides a practical research method for automatically recognising data set entities in scientific literature. To the best of the authors’ knowledge, this is the first attempt to apply distant learning to the study of data set entity recognition. The authors introduce a robust vectorised representation and two data augmentation strategies (entity replacement and entity masking) to address the problem inherent in distant supervised learning methods, which the existing research has mostly ignored. The experimental results demonstrate that our approach effectively improves the recognition of data set entities, especially long-tailed data set entities.

Download Full-text

Data Augmentation and Feature Selection for Automatic Model Recommendation in Computational Physics

Mathematical and Computational Applications ◽

10.3390/mca26010017 ◽

2021 ◽

Vol 26 (1) ◽

pp. 17

Author(s):

Thomas Daniel ◽

Fabien Casenave ◽

Nissrine Akkari ◽

David Ryckelynck

Keyword(s):

Feature Selection ◽

Data Augmentation ◽

Classification Problem ◽

Computational Physics ◽

Training Data ◽

Multilayer Perceptrons ◽

Augmentation Techniques ◽

Physical Fields ◽

Classification Tasks ◽

Selection Of

Classification algorithms have recently found applications in computational physics for the selection of numerical methods or models adapted to the environment and the state of the physical system. For such classification tasks, labeled training data come from numerical simulations and generally correspond to physical fields discretized on a mesh. Three challenging difficulties arise: the lack of training data, their high dimensionality, and the non-applicability of common data augmentation techniques to physics data. This article introduces two algorithms to address these issues: one for dimensionality reduction via feature selection, and one for data augmentation. These algorithms are combined with a wide variety of classifiers for their evaluation. When combined with a stacking ensemble made of six multilayer perceptrons and a ridge logistic regression, they enable reaching an accuracy of 90% on our classification problem for nonlinear structural mechanics.

Download Full-text