SECO has introduced a new set of Edge AI applications that enhance capabilities in safety monitoring, low-power machine vision, geospatial analysis, and intelligent video understanding. The release strengthens SECO’s growing ecosystem of production-ready AI solutions designed for deployment across industrial and embedded environments.
The new additions include Land-Cover Change Detection, an advanced computer vision application that analyses satellite or aerial imagery to automatically identify and map land-cover changes such as deforestation or urbanisation. This capability is essential for environmental monitoring, sustainable urban planning, and ecological impact assessments.
SECO is also expanding into speech-driven workflows with Wave2Vec – Speech-to-Text, a high-accuracy transcription application based on the Wave2Vec model and optimised to convert audio into text. It supports use cases such as automated documentation in industrial and healthcare settings, as well as voice-controlled operations in complex environments.
For energy-sensitive devices, Object Detection – Low Power on Edge offers an energy-efficient object detection capability designed for Edge platforms with power constraints. It enables real-time recognition of objects, people, or events where battery life, portability, and thermal efficiency are critical.
On the safety front, Human Fall Detection provides an AI vision application focused on detecting human falls in real time using advanced models. It is particularly useful for elderly care or high-risk industrial environments, enabling automated alerts for immediate response.
SECO is also extending its video analytics capabilities with Video Action Recognition, a deep learning application that analyses video sequences to recognise and classify complex human actions. It supports workflow analysis, operational safety, and staff training across sectors ranging from manufacturing to retail.
Rounding out the update, Face ID – Training Experience delivers a customizable training environment dedicated to training and fine-tuning Face Recognition (Face ID) models. It enables the creation, optimisation, and validation of identity-verification solutions directly on target hardware, ensuring accuracy and alignment with deployment requirements.
Each application is validated for deployment across platforms powered by Intel, Qualcomm, NXP, AMD, Rockchip, and MediaTek, and is supported by SECO’s enterprise-grade Long-Term Support to guarantee stability, security, and smooth integration within SECO’s hardware ecosystem.
“With these additions, we continue to make advanced AI capabilities accessible on a wide range of edge devices,” says Fausto Di Segni, Head of IoT and AI at SECO. “Each new model responds to concrete needs we see in the field — from energy efficiency to real-time safety — and helps customers accelerate deployment.”
The new AI applications can now be found on the SECO Application Hub, with full documentation available on the SECO Developer Centre and the opportunity to try the Clea Framework at no cost.