Verkada has announced a strategic collaboration with NVIDIA to advance the development and deployment of AI in physical security within the built environment.
As part of this partnership, NVIDIA has also become an investor in Verkada, joining Alphabet’s CapitalG, which invested in Verkada in the previous year. This partnership aims to leverage AI to transform data from schools, hospitals, retailers, and manufacturers into actionable insights, ultimately enhancing safety and security in these environments.
Enhancing Training Datasets
“Verkada has been building and deploying Physical AI before the term existed. With our footprint of more than 2.4 million devices across 170 countries and 30,000 organizations, we’ve proven that the built environment is one of the largest beneficiaries of AI,” stated Verkada co-founder and CEO Filip Kaliszan. “Working with NVIDIA supercharges what we've spent nearly a decade building: AI that keeps students safe in schools, protects workers on factory floors, helps retailers prevent theft, and enables organizations to operate more efficiently.”
The partnership with NVIDIA is expected to enhance Verkada's video analytics capabilities
The partnership with NVIDIA is expected to enhance Verkada's video analytics capabilities. By strengthening models and data processes, Verkada aims to improve its AI video search functions, multimodal embeddings, and vector retrieval methods for its next-generation semantic search. Additionally, the company is developing synthetic data generation techniques to enrich training datasets, thereby boosting accuracy.
Accelerating AI Model Training
With access to NVIDIA Cosmos world foundation models and the NVIDIA Physical AI Data Factory, Verkada has accelerated its AI model training and inference across a growing global infrastructure using NVIDIA's accelerated computing power. This collaborative effort has already yielded a 68% improvement in mean average precision (mAP) for AI-powered search capabilities regarding spatial-temporal understanding, enhancing the speed, accuracy, and robustness of its search functions.
The venture is also focusing on developing a multi-model search agent architecture and exploring reasoning models to tackle complex, unstructured real-world scenarios. These include detecting health and safety issues in manufacturing environments and identifying shrinkage trends in retail. The collaboration signifies Verkada's commitment to integrating context-aware AI to fortify and secure built environments.
