Anomalous Event Detection and Localization Using Stacked Autoencoder

Bansod, Suprit D.; Nandedkar, Abhijeet V.

doi:10.1007/978-981-15-4018-9_11

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several existing autoencoder-based methods that have been applied to video-based anomaly detection, www.ijacsa.thesai.org showcasing the effectiveness of this approach. Some notable examples include Variational Autoencoders (VAE) [39], Stacked Autoencoders (SAE) [40], and Convolutional Autoencoders (CAE) [38,41].…”

Section: Autoencodersmentioning

confidence: 99%

Investigating of Deep Learning-based Approaches for Anomaly Detection in IoT Surveillance Systems

HUANG,

CAI,

SUN

2023

IJACSA

View full text Add to dashboard Cite

Anomaly detection plays a crucial role in ensuring the security and integrity of Internet of Things (IoT) surveillance systems. Nowadays, deep learning methods have gained significant popularity in anomaly detection because of their ability to learn and extract intricate features from complex data automatically. However, despite the advancements in deep learning-based anomaly detection, several limitations and research gaps exist. These include the need for improving the interpretability of deep learning models, addressing the challenges of limited training data, handling concept drift in evolving IoT environments, and achieving real-time performance. It is crucial to conduct a comprehensive review of existing deep learning methods to address these limitations as well as identify the most accurate and effective approaches for anomaly detection in IoT surveillance systems. This review paper presents an extensive analysis of existing deep learning methods by collecting results and performance evaluations from various studies. The collected results enable the identification and comparison of the most accurate deep-learning methods for anomaly detection. Finally, the findings of this review will contribute to the development of more efficient and reliable anomaly detection techniques for enhancing the security and effectiveness of IoT surveillance systems.

show abstract

Section: Autoencodersmentioning

confidence: 99%

Investigating of Deep Learning-based Approaches for Anomaly Detection in IoT Surveillance Systems

HUANG,

CAI,

SUN

2023

IJACSA

View full text Add to dashboard Cite

show abstract

Anomalous event detection and localization in dense crowd scenes

Alhothali

Balabid²,

Alharthi³

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

Hybrid Classifiers for Spatio-Temporal Abnormal Behavior Detection, Tracking, and Recognition in Massive Hajj Crowds

et al. 2023

View full text Add to dashboard Cite

Individual abnormal behaviors vary depending on crowd sizes, contexts, and scenes. Challenges such as partial occlusions, blurring, a large number of abnormal behaviors, and camera viewing occur in large-scale crowds when detecting, tracking, and recognizing individuals with abnormalities. In this paper, our contribution is two-fold. First, we introduce an annotated and labeled large-scale crowd abnormal behavior Hajj dataset, HAJJv2. Second, we propose two methods of hybrid convolutional neural networks (CNNs) and random forests (RFs) to detect and recognize spatio-temporal abnormal behaviors in small and large-scale crowd videos. In small-scale crowd videos, a ResNet-50 pre-trained CNN model is fine-tuned to verify whether every frame is normal or abnormal in the spatial domain. If anomalous behaviors are observed, a motion-based individual detection method based on the magnitudes and orientations of Horn–Schunck optical flow is proposed to locate and track individuals with abnormal behaviors. A Kalman filter is employed in large-scale crowd videos to predict and track the detected individuals in the subsequent frames. Then, means and variances as statistical features are computed and fed to the RF classifier to classify individuals with abnormal behaviors in the temporal domain. In large-scale crowds, we fine-tune the ResNet-50 model using a YOLOv2 object detection technique to detect individuals with abnormal behaviors in the spatial domain. The proposed method achieves 99.76% and 93.71% of average area under the curves (AUCs) on two public benchmark small-scale crowd datasets, UMN and UCSD, respectively, while the large-scale crowd method achieves 76.08% average AUC using the HAJJv2 dataset. Our method outperforms state-of-the-art methods using the small-scale crowd datasets with a margin of 1.66%, 6.06%, and 2.85% on UMN, UCSD Ped1, and UCSD Ped2, respectively. It also produces an acceptable result in large-scale crowds.

show abstract

Anomalous Event Detection and Localization Using Stacked Autoencoder

Cited by 3 publications

References 19 publications

Investigating of Deep Learning-based Approaches for Anomaly Detection in IoT Surveillance Systems

Investigating of Deep Learning-based Approaches for Anomaly Detection in IoT Surveillance Systems

Anomalous event detection and localization in dense crowd scenes

Hybrid Classifiers for Spatio-Temporal Abnormal Behavior Detection, Tracking, and Recognition in Massive Hajj Crowds

Contact Info

Product

Resources

About