For complex ML systems involving many sensors (e.g. cameras, depth sensors, accelerometers), interconnected algorithms and a sophisticated control flow, system performance monitoring is a challenging problem. To architect these...
At the end of 2022, we introduced the open hardware Jetson Orin Baseboard as the successor to the original Jetson Nano Baseboard. The baseboard, like the original, has become the starting point for many customer projects involving...
Neural networks are a powerful tool for processing noisy and unstructured sensor data like camera frames, accelerometer or biometric readings, which makes them perfect for preprocessing or decision making on edge devices, where...
Antmicro’s open source Raviewer tool allows developers working with camera systems, especially in embedded applications, to inspect data collected by sensors in a raw, preprocessed format – to verify correctness of the data...
Antmicro’s projects often revolve around video acquisition and processing, with the camera system sometimes placed at a longer distance from the embedded processing platform. In such scenarios we cannot directly use MIPI CSI...
Given the rising demand for AI processing on the edge along with rapid advances in AI model compression through pruning and quantization to 8-bit, 4-bit (and even lower) integers, the configurability, low power and latency...
OLDER