Difference between revisions of "Design and Implementation of a Convolutional Neural Network Accelerator ASIC"
From iis-projects
(→Short Description) |
(→Short Description) |
||
Line 2: | Line 2: | ||
==Short Description== | ==Short Description== | ||
− | + | Imaging sensor networks, UAVs, smartphones, and other embedded computer vision systems require power-efficient, low-cost and high-speed implementations of synthetic vision systems capable of recognizing and classifying objects in a scene. Many popular algorithms in this area require the evaluations of multiple layers of filter banks. Almost all state-of-the-art synthetic vision systems are based on features extracted using multi-layer convolutional networks (ConvNets). When evaluating ConvNets, most of the time is spent performing the convolutions (80% to 90%). The focus of this work is on speeding up this step by creating an accelerator to perform this step faster and more power-efficient. | |
+ | |||
<!-- | <!-- | ||
More and more video surveillance data is being collect for real-time surveillance and storage. Privacy is a real issue, posing a legal obstacle when public places are being monitored: real-time surveillance is not allowed in such cases, and stored data can (even for internal use) only be accessed with a court order. | More and more video surveillance data is being collect for real-time surveillance and storage. Privacy is a real issue, posing a legal obstacle when public places are being monitored: real-time surveillance is not allowed in such cases, and stored data can (even for internal use) only be accessed with a court order. | ||
Line 10: | Line 11: | ||
This project is supposed to overcome this by using deep learning techniques to detect pedestrians/persons and using temporal/motion information to improve the delineation of moving objects. This way the pedestrians can be overpainted, blurred, or overlaid with motion-based information, protecting their privacy while enabling better information to security personnel. | This project is supposed to overcome this by using deep learning techniques to detect pedestrians/persons and using temporal/motion information to improve the delineation of moving objects. This way the pedestrians can be overpainted, blurred, or overlaid with motion-based information, protecting their privacy while enabling better information to security personnel. | ||
---> | ---> | ||
− | |||
===Status: In Progress === | ===Status: In Progress === | ||
: David Gschwend, Christoph Mayer, Samuel Willi | : David Gschwend, Christoph Mayer, Samuel Willi |
Revision as of 20:45, 6 December 2014
Contents
Short Description
Imaging sensor networks, UAVs, smartphones, and other embedded computer vision systems require power-efficient, low-cost and high-speed implementations of synthetic vision systems capable of recognizing and classifying objects in a scene. Many popular algorithms in this area require the evaluations of multiple layers of filter banks. Almost all state-of-the-art synthetic vision systems are based on features extracted using multi-layer convolutional networks (ConvNets). When evaluating ConvNets, most of the time is spent performing the convolutions (80% to 90%). The focus of this work is on speeding up this step by creating an accelerator to perform this step faster and more power-efficient.
Status: In Progress
- David Gschwend, Christoph Mayer, Samuel Willi
- Supervision: Lukas Cavigelli, Beat Muheim
- Date: Fall Semester 2014 (sem14h17, sem14h18, sem14h19)
Prerequisites
- Knowledge of Matlab
- Interest in video processing and VLSI design
- VLSI 1 and enrolment in VLSI 2 is required
- At least one student has to test the chip as part of the VLSI 3 lecture, if the ASIC should be manufactured.
Character
- 10% Theory / Literature Research
- 60% VLSI Architecture, Implementation & Verification
- 30% VLSI back-end Design
Professor
Detailed Task Description
Goals
- Explore various architectures to perform the 2D convolutions used in convolutional networks, considering the constraints of an ASIC design project.
- Get to know the ASIC design flow from specification through architecture exploration to implementation, functional verification, back-end design and silicon testing.
Literature
Practical Details
Results
Links
- The EDA wiki with lots of information on the ETHZ ASIC design flow (internal only) [[1]]