To help police search for objects or persons of interests more efficiently, Motorola Solutions has teamed up with artificial intelligence company Neurala to develop smart cameras for public safety users.

The partnership will see Neurala integrate its AI capabilities with Motorola's software and cameras, including its Si500 body-worn camera, to create intelligent cameras that can learn “at the edge” and automatically search for persons or objects of interest. This, the companies said, will significantly reduce the time and effort required to find a missing child or suspicious object in environments that are often crowded or chaotic.

20170728_EETA_Motorola-AI-camera_01 (cr) Figure 1: Motorola Si500 (Source: Motorola Solutions)

Neurala’s patent-pending lifelong deep neural network (L-DNN) technology provides an alternative to lengthy training for the AI engine. Known as incremental learning, this feature also reduces the risk of “catastrophic forgetting,” which occurs when a neural network forgets its previous training. Incremental learning also enables enhanced accuracy and latency for real-time public safety applications of AI.

20170728_EETA_Motorola-AI-camera_02 (cr) Figure 2: Neurala will integrate its AI capabilities with Motorola's cameras to create cameras capable of eal-time edge learning for public safety officers. (Source: Motorola Solutions)

Neurala will initially work with Motorola Solutions to build a prototype that allows for real-time learning for a person of interest search. Motorola Solutions Venture Capital, the company’s strategic investment group, was a lead investor in Neurala’s Series A funding announced in January.