METHOD AND SYSTEM FOR ZERO-SHOT CROSS-DOMAIN VIDEO ANOMALIA DETECTION - Patent application

Abstract

An embodiment of the present invention discloses a method and system for performing video anomaly detection by training a neural network. The method includes collecting a video of one or more digital images from a source domain. The method includes obtaining a set of images of a foreground object present in the video. The method further includes training a first neural network to predict frames of the one or more digital images in the video. The first neural network is trained using a future frame prediction module to predict frames of the one or more digital images. The method includes training a second neural network to classify the predicted frames as normal and classify the synthesized pseudo-anomalous frames as anomalous. The method includes performing video anomaly detection based on training the first neural network and the second neural network.

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates to video anomaly detection, and more particularly to a method and system for zero-shot cross-domain video anomaly detection. [Background technology]

[0002] Unsupervised video anomaly detection (VAD) is widely used in security and surveillance applications compared to supervised or weakly supervised VAD. This is primarily because unsupervised VAD methods do not require training videos containing unusual and laborious annotated events. Therefore, unsupervised VAD methods use only normal events in the training videos to mark inexplicable activities as anomalous during testing by a trained model. Recently, unsupervised VAD methods in cross-domain settings have been introduced. The goal is to perform VAD in a different target domain given video data containing only normal events from the source domain. However, these cross-domain VAD (xVAD) methods are few-shot scene adaptation-based methods that require access to VAD normal data from both the source and target domains. This assumption becomes a serious problem when there is no access to the data (videos of normal activities) required for model training and adaptation. For example, third-party companies may not be allowed to collect or access video data in public places due to security and privacy concerns. For this reason, current xVAD methods are ineffective because they rely heavily on access to at least a small number of target domain training datasets. Existing solutions to the video anomaly detection (VAD) problem require access to normal training videos taken from both the source and target domains. As an example of a VAD problem, the source and target domains may be a train station and airport scenario. At training time, only normal videos (not including anomalous videos) taken at the station and airport are available. At test time, the task is to identify anomalies in test videos taken at the airport (target domain), where the test videos include both normal and anomalous videos. Summary of the Invention

[0003] [Technical Issues] Therefore, to address the above-mentioned problems, there is a need for an improved xVAD system and method that can overcome the above-mentioned drawbacks. [Problem Solution]

[0004] The present disclosure provides methods and systems for performing video anomaly detection.

[0005] Some embodiments are based on the recognition that there is a need for zero-shot cross-domain video anomaly detection without target domain data.

[0006] To that end, some embodiments are based on the realization of a zero-shot cross-domain video anomaly detection (zVAD) system. The zVAD system collects a video of one or more digital images from a source domain. The zVAD system also acquires a set of images of foreground objects present in the video. The source domain video corresponds to at least one of non-task-related or task-related video, video related to normal events, publicly available video, and video combining multiple images.

[0007] Some embodiments are based on the recognition that the zVAD system of the present disclosure is configured to train a first neural network to predict frames of one or more digital images in a video. The first neural network is trained using a future frame prediction module that predicts frames of the one or more digital images. The future frame prediction module includes a generator and a classifier. The generator includes an encoder, a memory module, and a decoder. The future frame prediction module is associated with an object-aware anomaly synthesis module that is configured to generate pseudo-anomalous frames and learn features from normal frames for the pseudo-anomalous frames.

[0008] Some embodiments are based on the recognition that the zVAD system of the present disclosure is configured to train a second neural network. The second neural network is trained to classify predicted frames of digital images of the one or more digital images as normal and to classify predicted frames of digital images of the one or more digital images having corrupted portions with images from the image set of foreground objects as anomalous. The second neural network is trained using a normality classifier module. The normality classifier module generates a plurality of loss functions utilized to train the second neural network. The plurality of loss functions include at least one of a normality loss, a relative normality loss, an attention positivity loss, and a relative attention positivity loss. The normality classifier module utilizes the predicted frames received from the future frame prediction module and one or more pseudo-anomalous frames generated by the object recognition anomaly synthesis module to predict the probability of normality or anomaly in the video.

[0009] Accordingly, some embodiments disclose a method for performing video anomaly detection by training a neural network. The method includes collecting a video of one or more digital images from a source domain. The method includes obtaining a set of images of a foreground object present in the video. The foreground object corresponds to at least one of a group of people and an individual. The method further includes training a first neural network to predict frames of the one or more digital images in the video. The first neural network is trained using a future frame prediction module that predicts frames of digital images of the one or more digital images. The method further includes training a second neural network to classify predicted frames of digital images of the one or more digital images as normal and to classify predicted frames of digital images of the one or more digital images having a corrupted portion with an image from the set of images of the foreground object as anomalous. The second neural network is trained using a normality classifier module. The method further includes performing video anomaly detection based on training the first neural network and the second neural network.

[0010] The present disclosure is further described in the following detailed description by way of non-limiting examples of exemplary embodiments of the present disclosure with reference to the noted drawings in which like reference numerals represent like parts throughout the several views of the drawings. The drawings shown are not necessarily to scale, with emphasis generally being placed upon illustrating the principles of embodiments of the present disclosure. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a schematic block diagram illustrating a training system for video anomaly detection, according to some embodiments of the present disclosure. [Figure 2A] FIG. 1 is a block diagram illustrating a training system for training a first neural network, according to some embodiments of the present disclosure. [Figure 2B]FIG. 10 is a block diagram for training a second neural network according to some embodiments of the present disclosure. [Figure 2C] FIG. 1 is a block diagram illustrating a normality classifier module according to some embodiments of the present disclosure. [Figure 3] 1A-1C illustrate representations of one or more pseudo-anomalous frames according to some embodiments of the present disclosure. [Figure 4] 2 illustrates an exemplary representation of the operation of the training system shown in FIG. 1 according to some embodiments of the present disclosure. [Figure 5] FIG. 1 is a block diagram for jointly training a first neural network and a second neural network to perform video anomaly detection according to some embodiments of the present disclosure. [Figure 6] 5 is a flowchart illustrating a method for performing video anomaly detection using the training system disclosed in FIG. 4, according to various embodiments of the present disclosure. [Figure 7] FIG. 1 illustrates a use case for detecting anomalies using a training system, according to some example embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] [Description of the embodiment] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be practiced without these specific details. In other instances, devices and methods are shown only in block diagram form to avoid obscuring the disclosure. Various changes can be made in the function and arrangement of elements without departing from the spirit and scope of the disclosed subject matter as set forth in the appended claims.

[0013] As used in this specification and claims, terms such as "for example," "for example," and "such as," as well as the verbs "comprise," "have," and "include," and each of their other verb forms, when used in conjunction with a list of one or more components or other items, are to be construed as open-ended, meaning that such list should not be viewed as excluding other additional components or items. The term "based on" means based at least in part on. Furthermore, it is to be understood that the words and terms used herein are for descriptive purposes and should not be considered limiting. Any headings used herein are for convenience only and have no legal or limiting effect.

[0014] Specific details are provided in the following description to provide a thorough understanding of the embodiments. However, those skilled in the art will understand that the embodiments may be practiced without these specific details. For example, systems, processes, and other elements of the disclosed subject matter may be shown as components in block diagram form to avoid obscuring the embodiments in unnecessary detail. In other instances, well-known processes, structures, and techniques may be shown without unnecessary detail to avoid obscuring the embodiments. Furthermore, like reference numbers and names in the various drawings indicate like elements. (System Overview)

[0015] FIG. 1 is a schematic block diagram 100 illustrating a training system 104 for video anomaly detection, according to some embodiments of the present disclosure.

[0016] The training system 104 includes a memory 106, a first neural network 108, a second neural network 110, and a processor 112. The memory 106 includes at least one of RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage, or other storage medium usable to store desired information and accessible by the training system 104. The memory 106 may include non-transitory computer storage media in the form of volatile and / or non-volatile memory. The memory 106 may be removable, non-removable, or a combination thereof. Exemplary memory devices include solid-state memory, hard drives, optical disk drives, etc. The memory 106 stores instructions executed by the processor 112. Execution of the instructions by the processor 112 causes the training system 104 to perform a series of operations described below.

[0017] The training system 104 collects source domain data, such as a video of one or more digital images, from a source domain 102 to perform video anomaly detection in a target domain. In one example, the source domain 102 is any location, such as an airport, a shopping mall parking lot, or a train station. The video in the source domain 102 corresponds to at least one of task-unrelated or task-related video, video related to normal events, publicly available video, and video combining multiple images. The source domain data includes only normal events and does not include abnormal events. For example, a car driving on a road may be considered a normal event, but a car entering a pedestrian area may be considered an abnormal event; a person running on a sports court may be considered a normal event, but a person running out of a bank may be considered an abnormal event.

[0018] In general, the target domain corresponds to anywhere where video anomaly detection is performed. As an example, the task corresponds to video anomaly detection. Furthermore, the training system 104 obtains a set of images of foreground objects present in the collected video from the source domain 102. The foreground objects correspond to at least one of a group of people and an individual. The source domain 102 may be different from the target domain. The source domain data is utilized as training data for training the first neural network 108 and the second neural network 110 for performing video anomaly detection.

[0019] Further, the first neural network 108 is trained to predict frames of one or more digital images in the video. Further, the second neural network 110 is trained to classify predicted frames of digital images of the one or more digital images as normal or anomalous. For example, a predicted frame of a digital image of the one or more digital images having a corrupted portion in an image from the image set of a foreground object is classified as anomalous. Further, video anomaly detection is performed based on the training of the first neural network 108 and the second neural network 110. Anomalies in the video may correspond to, but are not limited to, a fire, a fight, a collision of two or more objects, etc. The training of the first neural network 108 and the second neural network 110 is further described in Figures 2A, 2B, and 2C.

[0020] 2A illustrates an environment 200A for training a first neural network 108, according to some embodiments of the present disclosure. The zVAD system 104 is associated with a future frame prediction module 202. The first neural network 108 is trained using the future frame prediction module 202 to predict one or more frames of one or more digital images.

[0021]

number

[0022]

number

[0023]

number

[0024] Furthermore, the HMDB is a large collection of realistic videos from various sources, including movies and web videos. The dataset consists of 6,849 video clips from 51 action categories (e.g., "jumping," "kissing," "laughing," etc.), with each category containing at least 101 clips. Finally, the HMDB dataset is utilized to learn human activities for performing VAD tasks.

[0025]

number

[0026]

number

[0027]

number

[0028]

number

[0029]

number

[0030]

number

[0031]

number

[0032]

number

[0033]

number

[0034]

number

[0035]

number

[0036]

number

[0037]

number

[0038]

number

[0039] 6 is a flowchart illustrating a method 600 for performing video anomaly detection according to various embodiments of the present disclosure. The method 600 is performed by the training system 104. The method 600 begins at step 602. Following step 602, the method 600 includes collecting a video of one or more digital images from the source domain 102 at step 604. The video from the source domain 102 corresponds to at least one of non-task-related or task-related video, video related to normal events, publicly available video, and video combining multiple images.

[0040] The method includes, in step 606, obtaining a set of images of a foreground object present in the video. The foreground object corresponds to at least one of a group of people and an individual. The method includes, in step 608, training a first neural network 108 to predict frames of one or more digital images in the video. The first neural network 108 is trained using a future frame prediction module 202 that predicts frames of the one or more digital images. The future frame prediction module 202 includes a generator 206 and a classifier 212. The first neural network 108 is trained using one or a combination of a reconstruction loss and an identification loss. The reconstruction loss is calculated to train the generator 206. The identification loss is calculated to train the classifier 212. The generator 206 includes an encoder 206A, a memory module 206B, and a decoder 206C. The future frame prediction module 202 is associated with an object recognition anomaly synthesis module 216. The object recognition anomaly synthesis module 216 generates pseudo-anomalous frames and learns features from normal frames for the anomalous frames.

[0041] At step 610, the method includes training a second neural network 110 to classify predicted frames of digital images of the one or more digital images as normal and to classify predicted frames of digital images of the one or more digital images having corrupted portions with images from the image set of foreground objects as anomalous. The second neural network is trained using a normality classifier module 214. The normality classifier module 214 generates a plurality of loss functions utilized to train the second neural network 110. The plurality of loss functions include a normality loss, a relative normality loss, an attention positive loss, and a relative attention positive loss. The normality classifier module 214 utilizes predicted frames received from the future frame prediction module 202 and one or more pseudo-anomalous frames generated by the object recognition anomaly synthesis module 216 to predict the probability of normality or anomaly in the video. The normality classifier module 214 is trained jointly using the predicted normal video frames and the pseudo-anomalous video frames to detect anomalies in the video.

[0042] The method includes, at step 612, performing video anomaly detection based on training the first neural network 108 and the second neural network 110. The method ends at step 614.

[0043] 7 illustrates a use case for detecting anomalies using the training system 104, according to some example embodiments of the present disclosure. The zVAD system 104 can be integrated into a video surveillance system for detecting anomalies in various locations. The use case includes a parking lot scene 700. The scene 700 includes a video surveillance camera 702, Person A, and Person B. Person A and Person B are seen fighting in the parking lot scene 700. A video of Person A and Person B fighting is captured in real time by the video surveillance camera 702. This video is then detected as an anomaly based on the trained neural network of the training system 104. The training system 104 then sends a video anomaly detection notification to a server, and appropriate action is taken immediately.

[0044] Many modifications and other embodiments of the inventions described herein will suggest themselves to one skilled in the art to which these inventions pertain having the benefit of the teachings presented in the foregoing description and the associated drawings. It is to be understood that the invention is not limited to the particular embodiments disclosed, and that modifications and other embodiments are intended to be included within the scope of the appended claims. Moreover, while the foregoing description and the associated drawings describe example embodiments in the context of example combinations of elements and / or functions, it should be understood that different combinations of elements and / or functions may be provided by alternative embodiments without departing from the scope of the appended claims. In this regard, combinations of elements and / or functions other than those expressly described above are contemplated, for example, as may be set forth in some of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

Claims

【Request 1】 【Number 1】

2. The method of claim 1 , further comprising obtaining a set of images of at least one of a group of people and an individual that is a foreground object in the video.

3. the first neural network is trained using one or a combination of a reconstruction loss and a discriminative loss; the reconstruction loss is computed to train the generator; The method of claim 1 , wherein the discrimination loss is calculated to train the discriminator. 【Request 4】 【Number 2】

5. the first neural network is trained using one or a combination of a reconstruction loss and a discriminative loss; the reconstruction loss is computed to train the generator; The training system of claim 4 , wherein the discrimination loss is calculated to train the classifier.

6. the normality classifier module is associated with an object recognition anomaly synthesis module; The training system of claim 4 , wherein the object recognition anomaly synthesis module generates pseudo-anomalous frames and learns features from normal frames for the anomalous frames.

7. 7. The training system of claim 6, wherein the normality classifier module utilizes the predicted frames received from the future frame prediction module and the pseudo-anomalous frames generated by the object recognition anomaly synthesis module to predict the probability of normality or anomaly in the video.

8. 5. The training system of claim 4, wherein the videos in the source domain correspond to at least one of non-task-related or task-related videos, videos related to regular events, publicly available videos, and videos combining multiple images.

Images