2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)最新文献_第4页

FR-HDNet: Faster RCNN based Haze Detection Network for Image Dehazing FR-HDNet:基于RCNN的更快的图像去雾检测网络

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092202

Teena Sharma, Bhanu Teja Nalla, N. Verma, S. Vasikarla

{"title":"FR-HDNet: Faster RCNN based Haze Detection Network for Image Dehazing","authors":"Teena Sharma, Bhanu Teja Nalla, N. Verma, S. Vasikarla","doi":"10.1109/AIPR57179.2022.10092202","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092202","url":null,"abstract":"Image dehazing plays a major role in several vision- based applications aiming to improve image quality to obtain rich textural information. This paper proposes a methodology to retain textural information after image enhancement for vision- based algorithms. The objective is first to detect the hazy regions in a hazy input image and then perform dehazing on these detected regions. This results in retaining the texture of haze- free regions and an enhanced view of hazy regions. In the first part of the proposed framework, a Faster RCNN-based haze detection network named FR-HDNet is proposed to identify the hazy regions in an input hazy image. In the second part, the detected hazy regions are dehazed. This results in an enhanced image optimally equipped with features that could aid vision- based algorithms. Finally, the enhanced dehazed image is fed into an object detection network. The experiments to validate the performance of the proposed framework are done on several benchmarked datasets like natural hazy benchmarked images frequently used in the literature, synthetic hazy images, indoor Synthetic Objective Testing Set (SOTS) images from REalistic Single Image DEhazing (RESIDE) dataset, outdoor SOTS images from RESIDE dataset, and real-world synthetic hazy images of Hybrid Subjective Testing Set (HSTS) from RESIDE dataset. The performance measures used to evaluate the quality of dehazed images are Peak Signal to Noise Ratio (PSNR) and Structural SIMilarity (SSIM) index; and Lightness Order Error (LOE) and Naturalness Image Quality Evaluator (NIQE) as no- reference image quality metrics. The effectiveness of the proposed framework is compared with several benchmarked state-of-the- art dehazing methods. The comparison demonstrated that the proposed framework enhances image quality and results in better performance.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129679618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adversarial Examples in Self-Driving: A Review of Available Datasets and Attacks 自动驾驶中的对抗性示例:对可用数据集和攻击的回顾

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092221

Mohammad R. Alam, C. Ward

{"title":"Adversarial Examples in Self-Driving: A Review of Available Datasets and Attacks","authors":"Mohammad R. Alam, C. Ward","doi":"10.1109/AIPR57179.2022.10092221","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092221","url":null,"abstract":"Autonomous vehicles rely on computer vision models for perception, which have been shown to be vulnerable to adversarial attacks. These attacks pose various risks from reducing user confidence in the technology to directly influencing the technology to make a particular action [1]. Research in adversarial machine learning (ML) has led to increased awareness of ML’s vulnerabilities to such attacks and strategies to mitigate their effects and enhance ML generalizability [1]. Although there exists a dataset for assessing a computer vision model’s efficacy against adversarial attacks in the real-world [2], there is no such dataset for benchmarking computer vision algorithms for autonomous vehicles. This effort is a preliminary study on publicly available datasets for self-driving applications through the lens of adversarial ML. We include a discussion of attacks that have been performed in this space. From black-box to white-box attacks, the more knowledge is available to the adversary, the more they can leverage to employ the attack [1]. Adversaries are fully capable of utilizing the publicly available datasets to test their own black-box attacks [3], [4]. Adversarial examples can be useful in both enhancing algorithm resilience to these attacks through inclusion in training [5] as well as for use in benchmarking current approaches against the attacks [2]. Building resilient autonomy in transportation will require mitigation of any vulnerabilities, especially those from potential adversaries. This survey of datasets and attacks on self-driving vehicles is a first step in developing a dataset of adversarial attacks in this domain. The dataset can assist current and future computer vision research in self-driving to benchmark algorithm effectiveness against such attacks in the real-world.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116396825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Toward CNN Architectures for Image Detection 面向图像检测的CNN架构

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092233

S. Israel, J. Irvine, Ieuan M. Israel

{"title":"Toward CNN Architectures for Image Detection","authors":"S. Israel, J. Irvine, Ieuan M. Israel","doi":"10.1109/AIPR57179.2022.10092233","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092233","url":null,"abstract":"Currently, convolutional neural networks (CNNs) drive the state-of-the-art for object detection and classification in imagery. Pre-trained models exist with hundreds of million computational artificial neurons to classify images into hundreds of different classes. However, most image characterization problems, detection and classification, require the discrimination across only a handful of classes. By focusing our training to the limited class list, we expect dramatically improved discrimination with lower resource costs. Ideally, these networks are trained using smaller datasets and needed far fewer computational neurons. As researchers focus more on the detection paradigm, the expected smaller, nimbler models that balance performance optimization between correctness and throughput. Our previous studies matched image quality with convolutional neural network parameters to develop strategies for automating orchestrated collection based upon information needs. Our current study extends those goals in two directions: 1. incorporate hidden layer depth; and 2. incorporate different number of output classes. In this study, we trained multiple CNNs and varied their window sizes, hidden layers, latent space dimensions, and output classes. The images were acquired from the rare planes database and have a variable size between 100 and 400 pixels on a side. The number of classes varied from 2 to 8. The images contain synthetic targets that are visually separable from the background. The outcome from these and previous experiments is to identify candidate parameters that enable more efficient image search models.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115581384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting COVID-19 from Chest X-ray Images using a New Deep Learning Architecture 使用新的深度学习架构从胸部x射线图像预测COVID-19

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092231

Zakariya A. Oraibi, Safaa Albasri

{"title":"Predicting COVID-19 from Chest X-ray Images using a New Deep Learning Architecture","authors":"Zakariya A. Oraibi, Safaa Albasri","doi":"10.1109/AIPR57179.2022.10092231","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092231","url":null,"abstract":"The spread of coronavirus disease in late 2019 caused huge damage to human lives and forced a chaos in health care systems around the globe. Early diagnosis of this disease can help separate patients from healthy people. Therefore, precise COVID-19 detection is necessary to prevent the spread of this virus. Many artificial intelligent technologies for example deep learning models have been applied successfully for this task by employing chest X-ray images. In this paper, we propose to classify chest X-ray images using a new end-to-end convolutional neural network model. This new model consists of six convolutional blocks. Each block consists of one convolutional layer, one ReLU layer, and one max-pooling layer. The new model was applied on a challenging imbalanced COVID19 dataset of 5000 images, divided into two classes, COVID and Non-COVID. In experiments, the input image is first resized to 256×256×3 before being fed to the model. Two metrics were used to test our new model: sensitivity and specificity. A sensitivity rate of 97% was achieved along with a specificity rate of 99.32%. These results are promising when compared to other deep learning models applied on the same dataset.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130779141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generative Adversarial Networks for Vehicle Transformation in Overhead and Satellite Imagery 基于生成对抗网络的高架和卫星图像车辆变换

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092222

Michael J. Reale, Preston Nichols, Ethan Schneider, Morgan Bishop, Maria Scalzo-Cornacchia

{"title":"Generative Adversarial Networks for Vehicle Transformation in Overhead and Satellite Imagery","authors":"Michael J. Reale, Preston Nichols, Ethan Schneider, Morgan Bishop, Maria Scalzo-Cornacchia","doi":"10.1109/AIPR57179.2022.10092222","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092222","url":null,"abstract":"The ability to create and detect synthetic video is becoming critically important to scene understanding. Techniques for synthetic manipulation and augmentation of data increases diversity within available datasets, while not requiring laborious labeling efforts. That is, the ability to create synthetic video can enable augmentation of small realistic datasets on which to further train Artificial Intelligence and Machine Learning (AI/ML) algorithms. Thus, it may be desirable to convert images of vehicles in satellite and overhead imagery to other varieties of vehicles. In this work, we leverage generative adversarial networks to transform cars into trucks (and vice versa). We leverage an attention-based masking approach that assists the network in transformation of the object and not background. In addition, we demonstrate the benefits of numerous data augmentation procedures, including presenting a new artificial dataset of vehicles from an aerial perspective and introducing novel augmentation techniques appropriate for our network architectures. Experiments are conducted for this unique application on both real and artificial datasets with state-of-the-art results.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114309176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Post-Disaster Damage Detection using Aerial Footage: Visual Question Answering (VQA) Case Study 使用航拍影像进行灾后破坏检测:视觉问答(VQA)案例研究

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092229

Rafael De Sa Lowande, A. Mahyari, H. Sevil

引用次数: 0

IoT Anomaly Detection Using a Multitude of Machine Learning Algorithms 使用多种机器学习算法的物联网异常检测

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092209

Maria Balega, Waleed Farag, Soundararajan Ezekiel, Xin-Wen Wu, Alicia Deak, Zaryn Good

{"title":"IoT Anomaly Detection Using a Multitude of Machine Learning Algorithms","authors":"Maria Balega, Waleed Farag, Soundararajan Ezekiel, Xin-Wen Wu, Alicia Deak, Zaryn Good","doi":"10.1109/AIPR57179.2022.10092209","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092209","url":null,"abstract":"The security of IoT (Internet of Things) systems is crucial yet challenging. Anomaly detection can help assess and improve the security of these devices and systems. The detection of anomalous traffic can be performed with the use of machine learning algorithms. Gradient Boosting is a Machine Learning (ML) technique that handles both regression and classification problems and uses decision tree algorithms to produce a prediction model. eXtreme Gradient Boosting (XGBoost) is a unique implementation of Gradient Boosting that has shown very good performance and outcomes in various problems. In this paper, XGBoost’s classification abilities are examined when applied to the adopted IoT-23 dataset to see how well anomalies can be identified and what type of anomaly exists in IoT systems. Moreover, the results obtained from XGBoost are compared to other ML methods including Support Vector Machines (SVM) and Deep Convolutional Neural Networks (DCNN). The classification results were assessed based on accuracy, precision, recall, and various other performance metrics. Our experimental results showed that XGBoost outperformed both SVM and DCNN achieving accuracies up to 99.98%. In addition, XGBoost proved to be the most efficient method with respect to execution time.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127270176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Watermarking for Data Provenance in Object Detection 目标检测中数据来源的水印

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092239

A. Snarski, Walker L. Dimon, Keith Manville, Michael Krumdick

{"title":"Watermarking for Data Provenance in Object Detection","authors":"A. Snarski, Walker L. Dimon, Keith Manville, Michael Krumdick","doi":"10.1109/AIPR57179.2022.10092239","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092239","url":null,"abstract":"Machine Learning (ML) has pervaded almost every industry including banking, autonomous vehicles, healthcare, retail, and defense. Effective use of ML can be a huge competitive advantage, and performance of an ML model is dependent on massive, well-constructed, annotated datasets used for training. These datasets are often sensitive and contain proprietary data. They can be costly to collect and require subject matter experts to annotate. Thus, annotated datasets are regarded as highly valuable intellectual property that must be protected. The owners of a proprietary training dataset need the ability to track its use in the wild to safeguard their intellectual property. We propose a novel methodology for object detection dataset traceability through ‘watermarking’ the training data. This watermark is embedded into object instances within a training dataset, which the model then learns. We design the watermark such that the model is sensitive to its presence within an image, even after the model is fine-tuned on another task. Additionally, the watermark is designed for negligible model performance fluctuations when compared to identical models trained on non-watermarked data. We demonstrate the effectiveness of our technique on multiple object detection model architectures, and conclude that this methodology can provide a means to effectively track dataset usage.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125410939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Wildland Fire Detection and Monitoring using a Drone-collected RGB/IR Image Dataset 利用无人机采集的RGB/IR图像数据集进行野火探测和监测

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-10-11 DOI: 10.1109/AIPR57179.2022.10092208

Xiwen Chen, Bryce Hopkins, Hongya Wang, Leo O’Neill, F. Afghah, A. Razi, P. Fulé, J. Coen, E. Rowell, Adam Watts

{"title":"Wildland Fire Detection and Monitoring using a Drone-collected RGB/IR Image Dataset","authors":"Xiwen Chen, Bryce Hopkins, Hongya Wang, Leo O’Neill, F. Afghah, A. Razi, P. Fulé, J. Coen, E. Rowell, Adam Watts","doi":"10.1109/AIPR57179.2022.10092208","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092208","url":null,"abstract":"Drone-based Unmanned Aerial Systems (UAS) provide an efficient means for early detection and monitoring of remote wildland fires due to their rapid deployment, low flight altitudes, high 3D maneuverability, and ever-expanding sensor capabilities. Recent sensor advancements have made side-by-side RGB/IR sensing feasible for UASs. The aggregation of optical and thermal images enables robust environmental observation, as the thermal feed provides information that would otherwise be obscured in a purely RGB setup, effectively \"seeing through\" thick smoke and tree occlusion. In this work, we present Fire detection and modeling: Aerial Multi-spectral image dataset (FLAME 2) [1], the first ever labeled collection of UAS-collected side-by-side RGB/IR aerial imagery of prescribed burns. Using FLAME 2, we then present two image-processing methodologies with Multi-modal Learning on our new dataset: (1) Deep Learning (DL)-based benchmarks for detecting fire and smoke frames with Transfer Learning and Feature Fusion. (2) an exemplary image-processing system cascaded in the DL-based classifier to perform fire localization. We show these two techniques achieve reasonable gains than either single-domain video inputs or training models from scratch in the fire detection task.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122182994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Weaknesses of Adversarial Camouflage in Overhead Imagery 对抗性伪装在架空图像中的弱点

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) Pub Date : 2022-07-06 DOI: 10.1109/AIPR57179.2022.10092201

A. V. Etten

{"title":"The Weaknesses of Adversarial Camouflage in Overhead Imagery","authors":"A. V. Etten","doi":"10.1109/AIPR57179.2022.10092201","DOIUrl":"https://doi.org/10.1109/AIPR57179.2022.10092201","url":null,"abstract":"Machine learning is increasingly critical for analysis of the ever-growing corpora of overhead imagery. Advanced computer vision object detection techniques have demonstrated great success in identifying objects of interest such as ships, automobiles, and aircraft from satellite and drone imagery. Yet relying on computer vision opens up significant vulnerabilities, namely, the susceptibility of object detection algorithms to adversarial attacks. In this paper we explore the efficacy and drawbacks of adversarial camouflage in an overhead imagery context. While a number of recent papers have demonstrated the ability to reliably fool deep learning classifiers and object detectors with adversarial patches, most of this work has been performed on relatively uniform datasets and only a single class of objects. In this work we utilize the VisDrone dataset, which has a large range of perspectives and object sizes. We explore four different object classes: bus, car, truck, van. We build a library of 24 adversarial patches to disguise these objects, and introduce a patch translucency variable to our patches. The translucency (or alpha value) of the patches is highly correlated to their efficacy. Further, we show that while adversarial patches may fool object detectors, the presence of such patches is often easily uncovered, with patches on average 24% more detectable than the objects the patches were meant to hide. This raises the question of whether such patches truly constitute camouflage. Source code is available at https://github.com/IQTLabs/camolo.","PeriodicalId":301162,"journal":{"name":"2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115927418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4