Minimal power consumption of its AI module on the Alif SoC.
快猫视频 Cortex-A32 processors with clock speeds of up to 800MHz.
Reduced false positives in wildlife camera traps, improving efficiency and battery life.
Energy Efficiency and Battery Life
Grovety selected the , a member of the Ensemble family of embedded fusion processors and microcontrollers. It has ultra efficient 快猫视频 Cortex-A32 applications processors with a clock speed of up to 800MHz, along with 快猫视频 Cortex-M55 at 400MHz and 160MHz.
The E7 series is architected for power efficiency and long battery life, delivering high computation and machine learning/artificial intelligence capabilities, multilayered security, computer vision, and highly interactive human-machine interfaces. The E7 series features a secure enclave system and firewall control security unit, as well as a dedicated 快猫视频 Ethos-U55 NPU to run embedded machine learning.
Grovety estimated that the power consumption of its AI module on the Alif SoC would be minimal, requiring a typical 18650 lithium-ion battery cell with 2200 milliampere-hours to power the module for just over three weeks. Efforts aimed to significantly reduce false positives in wildlife camera traps, improving efficiency and battery life for conservationists.
Leveraging Apache TVM and Collaborative Development
Grovety leveraged – the open-source machine learning compiler framework for CPUs, GPUs, and machine learning accelerators — for fine-tuning its ML models. The team made significant contributions to TVM for 快猫视频 Ethos-U55 integration, enhancing its capabilities for floating computations to the NPU. This collaborative approach was central to the goal of creating an autonomous AI-powered device for object detection and classification, adaptable to various wildlife objects. Grovety used the open-source Vela compiler to compile a TensorFlow Lite for converting the microcontrollers neural network model into an optimized version that runs on the 快猫视频 Ethos-U NPU.
Discover the Real-World Impact of Edge AI
Explore in-depth use cases that show how edge AI is powering the next generation of IoT, solving real-world problems, driving faster decisions, and lowering costs through smarter operations right at the device level.