Positive unlabeled learning‐based anomaly detection in videos

Mu, Huiyu; Sun, Ruizhi; Yuan, Gang; Shi, Guoqing

doi:10.1002/int.22437

Cited by 10 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, from Table 5, it is hard to notice the best performative method as an individual method could not achieve an absolute better performance. For example, Mu et al [109], Cho et al [131], Xia et al [104], Zahid et al [87], and Roy et al [91] achieved the best AUC scores of 0.952, 0.992, 0.922, 0.940, and 0.997 from UCSD-Ped1 [31], UCSD-Ped2 [31], CUHK-Avenue [32], ShanghaiTech-Campus [18], and UMN [36], respectively. Unambiguously, considering experimental results in Table 5, it is very hard to find that one algorithm is better than its alternatives.…”

Section: Experimental Results Comparisonmentioning

confidence: 99%

“…Yet, other hypotheses on the differences of this G 2 group are not statistically significant as their distance differences are less than 26.242. For example, the hypothesis on the difference of Mu et al [109] vs. AE-Unet (Ours) is not statistically significant as their distance difference lacks by a numerical value of more than |26.242 + 11.8333 − 37.5| = 0.5753. However, the performance of the method of AEcaUnet (Ours) is remarkably different from AEcUnet (Ours), Zhang et al [13], Dong et al [81], Esquivel et al [117], Park et al [118], ParkLCL [132], Zhang et al [106], Tang et al [96], Zahid et al [87], Song et al [101], Shao et al [123], and AE-Unet (Ours).…”

Section: Average Ranking Of Gmentioning

confidence: 87%

See 1 more Smart Citation

Deep Crowd Anomaly Detection by Fusing Reconstruction and Prediction Networks

2023

View full text Add to dashboard Cite

Abnormal event detection is one of the most challenging tasks in computer vision. Many existing deep anomaly detection models are based on reconstruction errors, where the training phase is performed using only videos of normal events and the model is then capable to estimate frame-level scores for an unknown input. It is assumed that the reconstruction error gap between frames of normal and abnormal scores is high for abnormal events during the testing phase. Yet, this assumption may not always hold due to superior capacity and generalization of deep neural networks. In this paper, we design a generalized framework (rpNet) for proposing a series of deep models by fusing several options of a reconstruction network (rNet) and a prediction network (pNet) to detect anomaly in videos efficiently. In the rNet, either a convolutional autoencoder (ConvAE) or a skip connected ConvAE (AEc) can be used, whereas in the pNet, either a traditional U-Net, a non-local block U-Net, or an attention block U-Net (aUnet) can be applied. The fusion of both rNet and pNet increases the error gap. Our deep models have distinct degree of feature extraction capabilities. One of our models (AEcaUnet) consists of an AEc with our proposed aUnet has capability to confirm better error gap and to extract high quality of features needed for video anomaly detection. Experimental results on UCSD-Ped1, UCSD-Ped2, CUHK-Avenue, ShanghaiTech-Campus, and UMN datasets with rigorous statistical analysis show the effectiveness of our models.

show abstract

Section: Experimental Results Comparisonmentioning

confidence: 99%

Section: Average Ranking Of Gmentioning

confidence: 87%

Deep Crowd Anomaly Detection by Fusing Reconstruction and Prediction Networks

2023

View full text Add to dashboard Cite

show abstract

“…Deep-learning concepts have also been widely applied to tasks related to computer vision and have yielded excellent performance. Te majority of these deep-learning methods are based on supervised learning (i.e., with labels); however, supervised or semisupervised learning is also used in anomaly detection, requiring low training datasets [4][5][6]. Anomaly detection can be broadly divided into two categories, based on the deeplearning framework used: (i) frame generation and (ii) probability estimation.…”

Section: Introductionmentioning

confidence: 99%

AD-Graph: Weakly Supervised Anomaly Detection Graph Neural Network

Ullah,

Hussain,

Min Ullah

et al. 2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

The main challenge faced by video-based real-world anomaly detection systems is the accurate learning of unusual events that are irregular, complicated, diverse, and heterogeneous in nature. Several techniques utilizing deep learning have been created to detect anomalies, yet their effectiveness on real-world data is often limited due to the insufficient incorporation of motion patterns. To address these problems and enhance the traditional functionality of anomaly detection systems for surveillance video data, we propose a weakly supervised graph neural-network-assisted video anomaly detection framework called AD-Graph. To identify temporal information from a series of frames, we extract 3D visual and motion features and represent these in a language-based knowledge graph format. Next, a robust clustering strategy is applied to group together meaningful neighbourhoods of the graph with similar vertices. Furthermore, spectral filters are applied to these graphs, and spectral graph theory is used to generate graph signals and detect anomalous events. Extensive experimental results over two challenging datasets, UCF-Crime and ShanghaiTech, show improvements of 0.35% and 0.78% against a state-of-the-art model.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In current intelligent video surveillance systems, researchers mainly focus on three categories: object tracking, anomalous event detection, and person reidentification (P-Reid). 1 The main purpose of P-Reid is to match and retrieve all images of a person having similar patterns, captured through visual sensors. Recently, this area has attracted numerous researchers in the field of information retrieval, due to its potential applications to surveillance for industrial security.…”

Section: Introductionmentioning

confidence: 99%

Learning to rank: An intelligent system for person reidentification

Khan

Haq

Khan

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Person reidentification (P‐Reid) is an emerging research domain in the field of information retrieval that has gained exponential growth due to its wide range of applications in pedestrian tracking and crime prevention. The primary goal of P‐Reid is to recognize a person based on previous appearance in multiview surveillance videos. The mainstream approaches apply fully supervised learning techniques that have poor scalability when deployed in complex real‐world scenes, due to the overfitting problem, caused by the lack of sufficient annotated data. Further, optimization of these models for unlabeled data in real‐time surveillance is a challenging task. To tackle these issues, an intelligent framework (LR‐Net) is proposed, consisting of three tiers including fine‐tuning (FT), siamese network (SN), and fusion strategy (FS). In the first tier, a deep learning model is fine‐tuned for P‐Reid that can handle both labeled and unlabeled data. Next, with the assistance of transfer learning, an SN is proposed that has a strong discriminative capability in terms of similarity between a pair of images. Finally, a learning‐to‐rank strategy is applied to optimize the learning capability of the SN, in which a triplet network extracts spatial‐temporal patterns from unlabeled samples. In addition, a bayesian fusion model (BFM) is introduced to integrate the spatiotemporal and visual features, which yields 4.4%, 9.3%, and 0.8% improvement in the matching score over Market‐1501, DukeMCMT‐reID, and CUHK03 data sets, respectively. The conducted experiments and ablation study on the benchmark data sets empirically validate the proposed system, which obtains a high Rank‐1 score as compared with the state‐of‐the‐art (SOTA) methods.

show abstract

Positive unlabeled learning‐based anomaly detection in videos

Cited by 10 publications

References 34 publications

Deep Crowd Anomaly Detection by Fusing Reconstruction and Prediction Networks

Deep Crowd Anomaly Detection by Fusing Reconstruction and Prediction Networks

AD-Graph: Weakly Supervised Anomaly Detection Graph Neural Network

Learning to rank: An intelligent system for person reidentification

Contact Info

Product

Resources

About