Paravision extends CV tools with person detection and advanced analytics
Paravision has introduced a Software Development Kit (SDK) with Person Detection and Advanced Attribute Analytics capabilities to compliment or run independently of its facial recognition.
The new computer vision toolset uses video streams or still images, and operates on standard compute platforms, operating systems, and programming languages, to detect the presence and location of people without necessarily identifying who they are with biometrics, according to a company statement. The system can also associate certain attributes with individuals detected.
The capabilities can be used alongside Paravision’s facial recognition technology as long as the video streams and photos have high enough image quality.
The Person Detection capability works on a wide range of deployment distances, from far away with lower-resolution to higher resolution close up views and in different operational environments.
Paravision says the development of the Person Detection system is intended to complement its facial recognition technology with the ability to establish and track occupancy, attributes, or actions of people in a given field of view or physical space, or operate in a fully independent manner, as the use case and operational policy of the entity deploying it warrants.
The Person Detection and Advanced Attribute Analysis toolkit launch also represents a step beyond biometrics for Paravision.
“AI and computer vision technology is evolving at a tremendous pace, and as a Silicon Valley company we feel we have an opportunity to take advantage of amazing new developments across the board, from computer vision frameworks to advanced processor designs to new camera technologies,” Paravision CPO Joey Pritikin told Biometric Update in an interview on the Converge launch announcement.
The analytics offering brings AI computer vision to a wide range of computing environments, including cloud or data center deployments, and near-edge or on-device implementations. The company notes its partnerships with Intel, Nvidia, Ambarella, and the OpenVINO, TensorRT and CVflow computer vision frameworks. The capabilities are provided through an SDK or Docker container to support flexible application development and rapid deployment.
The company raised $23 million in June and announced its plans to expand its facial recognition and computer vision. Then in July, Paravision announced the appointment of biometrics industry expert Benji Hutchinson as the company’s new president and chief operating officer.