Главная
Study mode:
on
1
tiny ML. Talks
2
Vision doesn't always need high-resolution images
3
We can exploit this if image sensing is energy-proportional
4
Image sensor power breakdown
5
Idle power limits energy- proportionality
6
Driver-based power optimization: (1) Aggressive power management
7
Driver-based power optimization (2) Pixel clock frequency optimization
8
Energy-proportionality
9
However, resolution reconfiguration incurs latency penalty
10
Hardware is not the culprit
11
In the operating system, resolution reconfiguration undergoes a sequential procedure inside the media framework which requires the application to invoke several expensive system calls
12
Aspirations for a reconfigurable media framework
13
We introduce the Banner media framework
14
Parallel reconfiguration
15
Format-oblivious memory management
16
Banner media framework for seamless resolution reconfiguration
17
Ongoing efforts in multi-resolution visual computing systems
18
TinyML for all developers Dataset
19
Next tiny ML Talks
Description:
Explore system support for efficient multi-resolution visual computing on mobile devices in this tinyML Talks webcast. Delve into challenges and opportunities for mobile operating systems and vision sensing pipeline architectures to flexibly support dynamic multi-resolution workloads. Learn about energy-saving techniques, including sacrificing image resolution when high detail is unnecessary for computer vision and augmented reality tasks. Discover the Banner media framework for seamless resolution reconfiguration and ongoing efforts in multi-resolution visual computing systems. Gain insights into driver-based power optimization, energy-proportionality, and format-oblivious memory management. Understand the importance of rapid reconfigurability at low latencies and expressiveness to meet computational needs with minimal developer burden in mobile systems.

System Support for Efficient Multi-Resolution Visual Computing on Mobile Systems

tinyML
Add to list