Hanwha Vision introduces Wisenet 9 ‘System on a Chip’

After nearly four years of extensive research and testing, Wisenet 9’s advanced features help to elevate Hanwha Vision’s cameras into an AI-driven era, while “setting a new standard” for performance, accuracy and security.

“With Wisenet 9, you can count on the superior image quality that delivers the best possible video in the toughest environments, as well as the accuracy of the AI-generated data, whether statistical or event-driven,” stated John Lutz Boorman, head of product and marketing at Hanwha Vision Europe.

AI revolution at the edge

Wisenet 9’s enhanced edge AI capabilities are essential in this innovation era, wherein the volume and complexity of security threats demand real-time and accurate analysis. By elevating edge-device performance, AI empowers systems to quickly analyse vast amounts of video data and discern crucial patterns and anomalies.

A key differentiator driving this transformation is the two Neural Processing Units (NPUs), which have improved inference performance three-fold compared to Wisenet 7, the previous ‘System on a Chip’ generation.

While one NPU handles image processing, the other focuses on object detection and advanced analytics. This dual NPU concept was introduced to ensure video quality and analytics have independent resources, preventing one function from impacting the performance of the other.

Unveiling hidden details

Wisenet 9 uses AI to analyse visual data with greater precision. By leveraging a powerful NPU, the system moves past traditional image processing to extract critical information, unlocking previously unseen details with remarkable clarity in tough environments.

This enhanced visual intelligence is achieved through a suite of sophisticated AI features, including AI-based extreme Wide Dynamic Range, AI-powered noise reduction and image enhancements.

When combined, these technologies deliver exceptional clarity, even under the most challenging conditions. The AI-driven image enhancement, itself powered by an independent NPU, ensures that every detail – no matter how subtle – is captured and analysed.

AI efficiency redefined

AI is powerful, but it can also be resource-intensive. Wisenet 9 flips that script. It’s not just smart, it’s efficient: optimising every aspect of its operation.

By intelligently reducing noise, Wisenet 9 achieves a “remarkable” level of efficiency in data volume reduction, resulting in significantly reduced bandwidth consumption and storage requirements.

This core efficiency is further bolstered by the latest H.265 compression technology. The H.265 codec provides high video quality with optimised bandwidth, ensuring reliable and real-time video processing and transmission. This is critical for uninterrupted 24/7 security. Further, this optimised H.265 support enables consistently high performance in demanding environments, which is essential for system stability, and streamlines data management in cloud environments, efficiently controlling storage and transfer costs.

Wisenet 9’s H.265 codec, aligned with current industry standards and ONVIF Profiles, ensures broad hardware compatibility and seamless integration with existing security infrastructures, while also providing a dependable foundation for long-term system reliability.

Advanced analytics

Beyond this, Wisenet 9 leverages AI for advanced analytics. Its enhanced AI technology provides detailed attribute analysis, including colour, bag, face mask, glasses, age and gender, along with other key analytics like people and vehicle counting, slip and fall detection, crowd detection, heatmap, queue management and more, enabling faster and more informed decision-making.

To further amplify its capabilities, Wisenet 9 incorporates several key technologies that power the next generation of efficiency, including re-identification (RE-ID) for enhanced person tracking and searching and RE-ID technology (a deep learning-based approach to matching visual identities across non-overlapping camera views).

RE-ID extracts feature vectors representing unique visual attributes, enabling video management systems to recognise and track individuals even with changes in appearance or conditions. For example, it can identify a person entering a building with an orange jacket and later recognise the same individual leaving with the jacket unzipped and a hat across different cameras.

As an AI-based feature, dynamic privacy masking efficiently safeguards biometric personal data, ensuring compliance with privacy regulations. Wisenet 9 offers flexible masking options, including both opaque and mosaic masking, allowing end users to tailor privacy protection to their specific needs and preferences.

Widening horizons with expandable AI 

Recognising that security demands are as diverse as the industries they serve, Wisenet 9 has been engineered with “unparalleled” AI capabilities. This empowers end users to tailor their security systems.

*AI Packs: Wisenet 9 is compatible with AI Packs (traffic, retail, factory), designed to deliver actionable insights specific to various sectors*AI Sound Classification: AI-based sound classification enables rapid detection and directional awareness of critical events like gunshots, glass breaks and screaming to enhance situational awareness*Hanwha Vision Open Platform: Wisenet 9 empowers end users to create customised security solutions by providing the flexibility to tailor their systems with custom applications for video analytics, storage and other functionalities.

*Improved end-to-end protection: Wisenet 9 significantly enhances end-to-end protection by building upon the robust security foundation of Wisenet 7. It inherits essential features like Secure Storage, OS and Boot, which protect critical chipset data and prevent unauthorised software execution.

The inclusion of an FIPS 140-3 Level 3 elevates security to an “exceptional” standard. This certification guarantees that the chipset adheres to rigorous security protocols, assuring end users of comprehensive data protection.

*Further information is available online at www.hanwhavision.com