Streamline Evidence Analysis:
AI-Powered Video Summarisation for Law Enforcement
Rigr AI’s Video Summarisation Tool (VST Enterprise Edition) integrates the latest technological advancements in audio and video processing, offering a more efficient and effective approach to investigating video content. VST is designed with integration flexibility at its core, offering a powerful API that enables seamless integration with diverse systems and workflows, ensuring compatibility with existing platforms and processes for efficient and scalable deployment.
Our VST Enterprise Edition offers a comprehensive suite of advanced features, harnessing the power of AI to streamline the processing of evidence files and provide concise summaries. The Enterprise Edition does not require a GPU or a high-end machine, but it definitely benefits from a powerful server. Our light-weight version VST Pocket Edition focuses on transcription, optimised to run air-gapped on basic work computers, ensuring secure and efficient operation.
VST Enterprise Edition
Video Thumbnails
To facilitate easier navigation through a video, the app divides the content into thumbnails, each linking directly to its corresponding location in the video. Thumbnails enable to quickly identify the most valuable moments in a video by offering an instant preview of the content.
Transcription
VST detects spoken languages, transcribes audio in any language, diarises the content, and offers translation capabilities into English or the preferred language of your analyst. With user-assigned speaker names, our tool makes transcripts easy to read and reference.
Face Detection
Facilitating efficient face detection in videos, VST identifies moments when a face appears and also extracts key images with precision. This capability, together with face clustering, significantly accelerates face extraction and Victim ID workflows, allowing analysts to quickly and accurately identify individuals in video footage.
OCR
Optical Character Recognition can extract and transcribe textual content from livestreams. This method is also used to identify on-screen text, such as logos, which may prove to be crucial information for investigations.
Location Estimation
Rigr AI's location estimation model can accurately determine the location where a video was recorded, providing critical support to investigators by ensuring cases are referred to the appropriate jurisdiction.
Age Estimation
By leveraging our Age Estimation model, we can estimate the ages of subjects in videos, expediting forensic identification processes. Age Estimation model can be used to automatically highlight sensitive content that may involve minors.
Reports
VST includes an export feature that allows all data extracted from the video to be compiled into a PDF report. This covers transcriptions, face clusters, on-screen text, and more, providing a clear summary of the video analysis for easy reference and reporting.
Register your interest
VST Enterprise Edition is being developed in collaboration with Law Enforcement agencies. You can register your interest in the Enterprise Edition by filling out the form and have your say in the product roadmap early on, staying up to date with developments. Your input will help shape a tool that meets the specific needs of its users.
In the meantime, try out VST Pocket Edition, a free transcription-focused desktop application available for download on iOS and Windows.