Skip to content

O2andsAnoxia/2019-DAC-System-Design-Contest

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 

Repository files navigation

2019 DAC System Design Contest

Overview

The 2019 System Design Contest features embedded system implementation of neural network based object detection for drones. Contestants will receive training dataset provided by our industry sponsor DJI, and a hidden dataset will be used to evaluate the performance of the designs in terms of accuracy and power. Contestants will compete in two different categories: FPGA and GPU, and grand cash awards will be given to the top three teams in each category. In addition, our industry sponsor Xilinx and Nvidia will provide a limited number of teams successfully registered with a free design kit (on a first-come-first-served basis). The award ceremony will be held at 2018 IEEE/ACM Design Automation Conference. The contest detail can be found at DAC webpage. The contest supporting source code can be found here.

The 2018 System Design Contest winners designs can be found here.

ORGANIZING COMMITTEE

Jingtong Hu, Chair University of Pittsburgh

Jeff Goeders, Co-Chair Brigham Young University

Phillip Brisk, Co-Chair University of California, Riverside

Yanzhi Wang, Co-Chair Northeastern University

Guojie Luo, Co-Chair Peking University

Christopher Rowen, DAC Representative Cognite Ventures

Cong Zhao, Industry Liaison DJI

Naveen Purushotham, Industry Liaison Xilinx

Bei Yu, Publicity Chinese University of Hong Kong

SPONSOR

DJI; XILINX; NVIDIA

DATASET

The contest dataset is provided from DJI, captured by unmanned aerial vehicles(UAV). This dataset contains12 classes of images and 95 sub-categories. For each sub-category, 70% of the images are provided for training and30% are reserved for evaluation. in this dataset, most of the images have a object size 1-2% of the captured images (640x360), which is a main character of UAV-view images(ILSVRC with average object ratio 17%, PASCAL VOC with average object ratio 20%,).

The 70% dataset is open source and can be download here. A sample dataset can be download here.

FPGA WINNERS


First Place (Xilinx Ultra96)

iSmart3 - University of Illinois Urbana-Champaign
Cong Hao


Second Place

XJTU_Tripler - Xi'an Jiaotong University
Boran Zhao


Third Place

SystemsETHZ - ETH Zurich
Kaan Kara


The detailed ranking can be found here

GPU WINNERS (NVIDIA TX-2)


First Place

iSmart3-SkyNet - University of Illinois Urbana-Champaign
Xiaofan Zhang


Second Place

Thinker - Tsinghua University
Feng Xiong


Third Place

DeepZS - Zhejiang University & ShanghaiTech University
Zhuo Chen


The detailed ranking can be found here

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published