As the availability and demand for media content continues to explode, companies that deal with large volumes of media assets are faced with the recurring challenge of having to filter out content to meet distribution guidelines and requirements. Oftentimes, this translates into unreasonable amounts of human labor dedicated to manually identifying and editing out instances of questionable content. Too often this labor utilizes relatively scarce and costly resources like video editors along with their associated high-power equipment, stealing time from true value-added creative tasks.
Estimates show that the average medium to large-sized company in the media and entertainment industry dedicates somewhere between 4–10 hours of editing time per hour of content to the curation process. With ever-increasing volumes of content being produced along with the rapidly growing universe of media outlets, the need for a solution that would help companies streamline the rather mundane process of content curation has never been greater.
DeepScan AI Video Reviewer Tool
DeepScan is an Artificial Intelligence Machine Learning (AI/ML) powered smart review tool that helps companies streamline and automate their content curation processes. It is a web-based solution that can be used by non-editorial staff to search for and mark specific vocabulary and imagery in video assets. DeepScan is an ideal solution for companies that handle large volumes of video content that require scrupulous editing to adhere to distribution requirements.
How The Tool Works
DeepScan is a web-based application that can be run from any web browser, at any location, freeing the curation effort from requiring any geographic or on-premise locality.
Upon sign-in, a user is taken to a straightforward asset management interface that provides an upload utility for their videos and a list of content available for review.
Built-in customization for transcribed word identification is supported, and the tool is extensible to recognize other imagery through custom models or more sophisticated AI/ML such as scene detection, sentiment analysis, etc. (contact TrackIt for customization services).
After a user selects a video, the DeepScan presents an easy-to-use video player interface that allows them to quickly identify and mark items of interest for deletion, retention, or adding comments for editors to then act on. Keyboard shortcuts to jump to marked occurrences on the timeline are available for operator efficiency.
Once a video review is complete, users have the choice to export Marker/Edit Decision Lists that can be used by video editors to make final cuts and edits.
AWS Service Used
The following AWS Services were used to build DeepScan:
- Amazon Rekognition: Used to analyze video from the ingested content for segment detection (to detect technical cues and shots) and content moderation (to detect graphic or questionable content).
- Amazon Transcribe: Used to analyze audio from ingested content. Helps create a transcript file from the audio to identify and filter unwanted words.
- AWS Amplify Video: Used to provide end-users with a playback video on the web-based UI. An HLS playlist is created using Amplify Video.
- AWS Elemental MediaConvert: Used for video transcoding.
- Amazon CloudFront: AWS’s content delivery network (CDN) used to deliver website content and data.
- Amazon Cognito: Used for user authentication.
- Amazon Dynamo DB: Used to store results of AI/ML jobs
- AWS Lambda: Used to host code that processes metadata coming from API requests, Cloudwatch Events, or SNS Topics.
- Amazon CloudWatch: Used to store logs.
- Amazon SQS: Message queuing service used to process job results from Rekognition and Transcribe when a job is started, complete, or has failed. (AWS Lambda is used to process messages. Amazon SNS or Amazon CloudWatch events send their messages to the SQS Queue).
- Amazon SNS: Used to send email notifications to the end-users and send job results from Rekognition/MediaConvert/Transcribe to the SQS Queue.
- Amazon AppSync: Serves as the GraphQL API to handle user requests and internal requests to save, fetch, and delete metadata and also generate specific assets.
- Amazon S3: Used to ingest video content and store generated assets (EDL, transcripts, Marker files, HLS playlist).
Conclusion
Companies that handle sizable volumes of content often find themselves dedicating excessive amounts of resources to filter out questionable content from video assets. Leveraging DeepScan enables companies of all sizes to realize significant time and cost savings by streamlining and automating their content curation processes.
About TrackIt
TrackIt is an international AWS cloud consulting, systems integration, and software development firm headquartered in Marina del Rey, CA.
We have built our reputation on helping media companies architect and implement cost-effective, reliable, and scalable Media & Entertainment workflows in the cloud. These include streaming and on-demand video solutions, media asset management, and archiving, incorporating the latest AI technology to build bespoke media solutions tailored to customer requirements.
Cloud-native software development is at the foundation of what we do. We specialize in Application Modernization, Containerization, Infrastructure as Code and event-driven serverless architectures by leveraging the latest AWS services. Along with our Managed Services offerings which provide 24/7 cloud infrastructure maintenance and support, we are able to provide complete solutions for the media industry.