AI-enabled Evince automates detection and capture of primary and secondary ad elements on multiple live sport streams, to instantaneously store visual proof of delivery.
Skandha Media Services' Evince is an AI-based ad verification tool for live sports streaming platforms and advertising agencies. Skandha, specialising in scalable playout services that use cloud systems, automation, AI and machine learning, developed Evince to automate the detection and capture of primary and secondary ad elements on live sport streams.
Advertising agencies and advertisers can see exactly how an Ad appeared on a specific channel via mobile, digital or CTV, and at what point during a live event. The software can be used to ensure that contractual obligations are met by giving advertisers automated visual proof-of-delivery.
"This approach goes beyond delivering traditional logs for a live sports stream that may be firing hundreds and even thousands of Ads over the full length of a live game or competition," said Yogesh Salian, director of client services at Skandha Media Services. "The advertising agency not only has the ability to check that a particular Ad appeared correctly during an event on a specific stream or platform, but also that it was delivered at a specific time, or in a particular spot, for the expected duration."
Visual Evidence
Ad placement and timing are crucial during live sports events for broadcasters, OTT platforms, content owners and aggregators, rights holders and brands. Evince returns visual evidence that an ad has been served, through the use of AI to detect ad elements displayed in a live sport stream. It captures and carefully records each one as a video or image file with timestamps, using metadata to automate file names relating to the commercial ID and brand.
Video spot ads, including those carrying QR codes, are saved as files in MP4 format. L-Band, Aston band (for example lower thirds) and bug ads are saved as PNG, JPG and MOV files. The files are immediately and securely stored in the cloud so that each ad insertion record can be accessed reliably in real time.
Developing Evince
Skandha developed this new AI-based tool after a customer approached them to find a way to supply visual proof to their advertisers that 100% of ads were being served and displayed correctly during the streaming of a live cricket match.
"Initially we implemented a manual process to monitor and record screenshots and videos of each ad on multiple streams during the match," said Yogesh Salian. "Although the client was impressed with having instant access to the visual files of every single ad, the manpower and resources to accomplish this level of verification was unsustainable. This is when we introduced Machine Learning to automate the process – training cameras to identify and capture ad elements. With Evince we can very efficiently deliver ad verification and proof of delivery, in a way that did not exist before."
"The transparency of Evince builds trust with advertisers by ensuring responsible ad practices that contribute to safeguarding their brand identity," said Yogesh. www.skandha.in
