2017

The 13th IEEE Embedded Computer Vision Workshop

July 21, 2017,
Honolulu, HI, USA
Held in conjunction with IEEE CVPR 2017.

Main theme: Autonomous Driving

Best paper from Embedded Vision Workshop  2017:

Bichen Wu, Alvin Wan, Forrest Iandola, Peter Jin, Kurt Keutzer. SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

arXiv version

Program

Each oral presentation includes a 15 minute talk followed by 5 minute Q&A session. Poster presentations include 2-minute spotlight followed by the poster presentation during the allocated time. The poster dimensions are 4×8 (maximum).

Location:
Schedule: Full day

Session	Start Time	Paper/Talk Title	Author/Speaker
	0800	Welcome
S1: Oral 1 (0810-1000)	0810	Invited/Keynote Talk: Deep Learning for Autonomous Driving	Branislav Kisacanin, Nvidia
	0900	Fast, Accurate Thin-Structure Obstacle Detection for Autonomous Mobile Robots	Chen Zhou; Jiaolong Yang; Chunshui Zhao; Gang Hua
	0920	Sparse, Quantized, Full Frame CNN for Low Power Embedded Devices	Manu Mathew; Kumar Desappan; Pramod Swami; Soyeb Nagori
	0940	Reconstructing Intensity Images from Binary Spatial Gradient Cameras	Suren Jayasuriya; Orazio Gallo; Jinwei Gu; Timo Aila; Kautz Jan
	1000	Morning Break
S2: Oral 2 (1030-1230)	1030	Invited/Keynote Talk: Computer Vision for Camera Drones	Friedrich Fraundorfer, Graz University of Technology (TU Graz)
	1120	Binarized Neural Network with Separable Filters	Jeng-Hau Lin; Tianwei Xing; Ritchie Zhao; Zhiru Zhang; Mani Srivastava; Zhuowen Tu; Rajesh Gupta
	1140	Joint Mobile-Cloud Video Stabilization	Gbolahan S Adesoye; Oliver Wang
	1200	Embedded Robust Visual Obstacle Detection on Autonomous Lawn Mowers	Mathias Franzius; Mark Dunn; Roman Dirnberger; Nils Einecke
	1230	Lunch
S3: Poster 1 (1330-1540)	1330	Invited/Keynote Talk: Bootstrapping AI from naturalistic driving	Stefan Heck, Nauto (CEO)
	1420	Spotlights Posters and Demos
	1440	Posters
		Improved Cooperative Stereo Matching for Dynamic Vision Sensors with Ground Truth Evaluation	Ewa Piatkowska; Jürgen Kogler; Nabil Belbachir; Margrit Gelautz
		Diagnostic mechanism and robustness of safety relevant automotive deep convolutional networks	Robert Krutsch; Rolf Schlagenhaft
		Hand gesture based Region marking for tele-support using wearables	Archie Gupta; Shreyash Mohatta; Jitender Maurya; Ramakrishna Perla; Ramya Hebbalaguppe; Ehtesham Hassan
		Even More Confident predictions with deep machine-learning	Matteo Poggi; Fabio Tosi; Stefano Mattoccia
		Low-complexity Global Motion Estimation for Aerial Vehicles	Nirmala Ramakrishnan; Alok Prakash; Srikanthan Thambipilla
		LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection for Embedded Systems	Subarna Tripathi; Gokce Dane; Byeongkeun Kang; Vasudev Bhaskaran; Truong Nguyen
		Image-based Visual Perception and Representation for Collision Avoidance	Cevahir Cigla; Roland Brockers; Larry Matthies
		Pruning ConvNets Online for Efficient Specialist Models	Jia Guo; Miodrag Potkonjak
		Real-time Driver Drowsiness Detection for Embedded System Using Model Compression of Deep Neural Networks	Bhargava Reddy Thipireddy; Kim Yehoon; Sojung Yun; Chanwon Seo; Junik Jang
	1540	Afternoon Break
S4: Oral 3 (1600-1700)	1600	SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving	Bichen Wu; Forrest Iandola; Peter Jin; Kurt Keutzer
	1620	Training Sparse Neural Networks	Suraj Srinivas; Akshayvarun Subramanya; Venkatesh Babu R.
	1640	SqueezeMap: Fast Pedestrian Detection on a Low-power Automotive Processor Using Efficient​ Convolutional Neural Networks	Rytis Verbickas; Robert Laganiere; Daniel Laroche; Changyun Zhu; Xiaoyin Xu; Ali Ors
	1700	Closing Remarks and Awards

Sponsors

NVIDIA Corporation kindly sponsors this year’s best paper award!

Call For Papers

Embedded Vision is what makes Computer Vision mainstream today, as it brings together embedded systems with vision functionalities. Due to the emergence of powerful yet low-cost and energy-efficient processors, it has become possible to incorporate vision capabilities into a wide range of embedded systems, including video search and annotation, surveillance, gesture recognition in video games, driver assist systems in automotive safety, and autonomous robots such as drones. The IEEE Embedded Vision Workshop (EVW) brings together researchers working on vision problems that share embedded system characteristics.

CFP: https://drive.google.com/file/d/0B-aYI7rgXZ2vVzZrMXF4emxsVlk/view?usp=sharing

Important Dates

• Paper submission: March 31, 2017
• Notification to the authors: May 12, 2017
• Camera ready paper: May 19, 2017

Paper submission: http://cmt3.research.microsoft.com/EVW2017

Author guidelines: http://cvpr2017.thecvf.com/submission/main_conference/author_guidelines

Demos

EVW will have live demonstrations of embedded vision prototypes and solutions. This year we strongly encourage authors to embed their demo into their talk. We will provide 5 extra minutes in order to have enough time for the demo.

Furthermore we plan a demo session during which authors, engineers, and researchers can showcase their prototypes with real-time implementations of vision systems on embedded computing platforms. Additionally, we invite abstracts, independent of the paper submissions, to present your demonstrations during the workshop.

Special Journal Issue on Embedded Computer Vision

Since 2005 Workshops on Embedded (Computer) Vision (ECVW and EVW) were held in conjunction with CVPR, with the exception of the fifth, which was held in conjunction with ICCV 2009. These events were very successful, and selected workshop papers have been published in several special issues of major journals (EURASIP Journal on Embedded Systems, CVIU and Springer monographs titled Embedded Computer Vision). This year, we also plan to organize a special issue for selected papers.

Organizing Committee

General Chair:

Martin Humenberger, AIT Austrian Institute of Technology
Swarup Medasani, Uurmi Systems

Program Chair:

Ravi Kumar Satzoda, Nauto Inc.
Zoran Nikolic, Nvidia

Sponsorship Chair:

Goksel Dedeoglu, PercepTonic

Steering Committee:

Stefano Mattoccia, University of Bologna, Italy
Jagadeesh Sankaran, Nvidia
Ahmed Nabil Belbachir, Teknova AS (Norway)
Sek Chai, SRI International
Margrit Gelautz, Vienna University of Technology
Branislav Kisacanin, Nvidia
Fridtjof Stein, Daimler AG

Web Chair:

Yu Wang, Ambarella