English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper addresses the growing interest in deploying deep learning modelsdirectly in-sensor. We present "Q-Segment", a quantized real-time segmentationalgorithm, and conduct a comprehensive evaluation on a low-power edge visionplatform with an in-sensors processor, the Sony IMX500. One of the main goalsof the model is to achieve end-to-end image segmentation for vessel-basedmedical diagnosis. Deployed on the IMX500 platform, Q-Segment achievesultra-low inference time in-sensor only 0.23 ms and power consumption of only72mW. We compare the proposed network with state-of-the-art models, both floatand quantized, demonstrating that the proposed solution outperforms existingnetworks on various platforms in computing efficiency, e.g., by a factor of 75xcompared to ERFNet. The network employs an encoder-decoder structure with skipconnections, and results in a binary accuracy of 97.25% and an Area Under theReceiver Operating Characteristic Curve (AUC) of 96.97% on the CHASE dataset.We also present a comparison of the IMX500 processing core with the SonySpresense, a low-power multi-core ARM Cortex-M microcontroller, and asingle-core ARM Cortex-M4 showing that it can achieve in-sensor processing withend-to-end low latency (17 ms) and power concumption (254mW). This researchcontributes valuable insights into edge-based image segmentation, laying thefoundation for efficient algorithms tailored to low-power environments.

Q-Segment: Segmenting Images In-Sensor for Vessel-Based Medical Diagnosis