Unsupervised Anomaly Detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS) Using a Deep Residual Autoencoder

Samuel, Dinesh Jackson; Cuzzolin, Fabio

doi:10.1109/lra.2021.3097244

Cited by 14 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An Inception V1 was used for feature extraction with Gated Recurrent Unit (GRU) as RNN blocks, followed by two fully connected classifiers. An autoencoder technique was used as a learnable network to measure the ‘normal’ distribution of the data and detect abnormal events deviating from this distribution as reconstruction error 63 . The training was conducted using the Cholec80 dataset and phantom video data showing recall and precision equal to 78.4%, 91.5%, respectively, on Cholec80 and 95.6%, 88.1% on the phantom dataset.…”

Section: Methodsmentioning

confidence: 99%

Where do we stand in AI for endoscopic image analysis? Deciphering gaps and future directions

Ali

2022

npj Digit. Med.

View full text Add to dashboard Cite

Recent developments in deep learning have enabled data-driven algorithms that can reach human-level performance and beyond. The development and deployment of medical image analysis methods have several challenges, including data heterogeneity due to population diversity and different device manufacturers. In addition, more input from experts is required for a reliable method development process. While the exponential growth in clinical imaging data has enabled deep learning to flourish, data heterogeneity, multi-modality, and rare or inconspicuous disease cases still need to be explored. Endoscopy being highly operator-dependent with grim clinical outcomes in some disease cases, reliable and accurate automated system guidance can improve patient care. Most designed methods must be more generalisable to the unseen target data, patient population variability, and variable disease appearances. The paper reviews recent works on endoscopic image analysis with artificial intelligence (AI) and emphasises the current unmatched needs in this field. Finally, it outlines the future directions for clinically relevant complex AI solutions to improve patient outcomes.

show abstract

Section: Methodsmentioning

confidence: 99%

Where do we stand in AI for endoscopic image analysis? Deciphering gaps and future directions

Ali

2022

npj Digit. Med.

View full text Add to dashboard Cite

show abstract

“…With the interest of DL methods by researchers in the literature, they started to be applied for VAD. DL-based methods enabled high performance to be obtained for the detection of abnormalities from video streams under harsh environmental conditions [5], [6], [7], [8], [9]. A ConvLSTM network architecture designed as an encoder-decoder model was developed by authors of [10] for anomaly detection via prediction of subsequent frames and reconstruction.…”

Section: A Vad Work In the Literaturementioning

confidence: 99%

Enhancement of Video Anomaly Detection Performance Using Transfer Learning and Fine-Tuning

Dilek,

Dener

2024

IEEE Access

View full text Add to dashboard Cite

The use of surveillance cameras is a common solution for the need to manage the urban traffic that arises with the effect of the increment in the population in the cities and to provide security. As the number of surveillance cameras rises, video streams that create big data are recorded. Analysis of video streams collected from those traffic surveillance cameras, automatic detection of unusual, suspicious events, as well as a range of harmful activities, become crucial because it is impossible to observe, analyze, and comprehend the contents of these movies using human labor. Recent studies have shown that deep learning (DL)-based artificial intelligence (AI) techniques, particularly machine learning (ML) techniques, are used in video anomaly detection (VAD) studies. In this study, an efficient frame-level VAD method is proposed based on transfer learning (TL) and fine-tuning (FT) approach and anomalies were detected using 20 popular convolutional neural networks (CNN) based DL models where variants of VGG, Xception, MobileNet, Inception, EfficientNet, ResNet, DenseNet, NASNet and ConvNeXt base models were trained using TL and FT approach. The proposed approach was tested using CUHK Avenue, UCSD Ped1 and UCSD Ped2 datasets and the performance of the models were measured using Area Under Curve (AUC), accuracy, precision, recall, and F1-score metrics. The highest AUC scores measured were 100%, 100% and 98.41% for the UCSD Ped1, UCSD Ped2 and CUHK Avenue datasets respectively. Compared to existing techniques in the literature, experimental results show that the suggested method offers state-of-the-art (SOTA) VAD performance.

show abstract

“…A brief survey of the contemporary methods developed between 2015 and 2018 for anomaly detection in videos is presented in [ 268 ], which classifies these methods according to their network structures and the datasets used. In anomaly detection using video surveillance cameras, DL-based methods have achieved high performance under harsh environmental conditions [ 272 , 273 , 274 , 275 , 276 ]. DNNs with hierarchical feature representation learning are much more powerful than the handcrafted feature extraction techniques used in traditional architectures [ 95 ].…”

Section: Computer Vision Applications In Intelligent Transportation S...mentioning

confidence: 99%

Computer Vision Applications in Intelligent Transportation Systems: A Survey

Dilek

Dener

2023

Sensors

View full text Add to dashboard Cite

As technology continues to develop, computer vision (CV) applications are becoming increasingly widespread in the intelligent transportation systems (ITS) context. These applications are developed to improve the efficiency of transportation systems, increase their level of intelligence, and enhance traffic safety. Advances in CV play an important role in solving problems in the fields of traffic monitoring and control, incident detection and management, road usage pricing, and road condition monitoring, among many others, by providing more effective methods. This survey examines CV applications in the literature, the machine learning and deep learning methods used in ITS applications, the applicability of computer vision applications in ITS contexts, the advantages these technologies offer and the difficulties they present, and future research areas and trends, with the goal of increasing the effectiveness, efficiency, and safety level of ITS. The present review, which brings together research from various sources, aims to show how computer vision techniques can help transportation systems to become smarter by presenting a holistic picture of the literature on different CV applications in the ITS context.

show abstract

Unsupervised Anomaly Detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS) Using a Deep Residual Autoencoder

Cited by 14 publications

References 22 publications

Where do we stand in AI for endoscopic image analysis? Deciphering gaps and future directions

Where do we stand in AI for endoscopic image analysis? Deciphering gaps and future directions

Enhancement of Video Anomaly Detection Performance Using Transfer Learning and Fine-Tuning

Computer Vision Applications in Intelligent Transportation Systems: A Survey

Contact Info

Product

Resources

About