学位/职称

博士

办公室电话

+1-609-468-4570

Email

Changpeng805@pingan.com.cn

教育背景

卡内基梅隆大学机器人学院博士学位，清华大学自动化系学士学位

研究方向

机器视觉：（当前研究方向）实时多模态人体行为动作检测及分类算法，实时微表情检测算法，实时人体姿态检测算法，实时物体识别算法；（以前研究方向）实时机器视觉导引机械臂抓取算法，实时路口交通监控系统，基于立体视觉的车辆防撞系统，越野机器人视觉导航系统，基于单目相机的鲁棒三维重建算法；

AI医疗：基于多视图的乳腺钼靶图像深度学习诊断系统

任职经历

Tech Lead Manager 2019 – present， PingAn Silicon Valley Research Lab, Palo Alto, CA

Tech Lead 2017-2019，JD.COM Silicon Research Center Mountain View, CA

Founder and Chief Scientist 01/2008-2017 Princeton Vision

Member of Technical Staff 09/2002-11/2007， Sarnoff Corporation (Now part of SRI International) Princeton, NJ

主持、参与项目

平安：

-        智慧医疗：AI 乳腺钼靶诊断系统

-        智慧教育：AI教师助手

京东：

-        亚一无人仓视觉导引机械臂抓取项目

普利斯顿视觉

-        国家智能交通实验室视觉智能交通灯项目（安徽科力）

-        美国DARPA SBIR/STTR 智能防撞系统 （卡内基梅隆）

Sarnoff （SRI International）

-        基于立体视觉的车辆防撞系统

-        越野机器人视觉导航系统

个人获奖

-        Best Paper Award in IEEE International Conference on Transportation Information and Safety, Banff, Canada  2017

-        DARPA SBIR/STTR Phase I and Phase II, Monte Carlo Sampling based Collision Detection for Autonomous Driving Systems, 2008-2012

-        Recipient of Sarnoff Innovation Award for “Developed real-time stereo-vision based imminent collision detection prototype system and successful demonstration in client’s testing facility”.

-        Recipient of Sarnoff Innovation Award for “Participation in DARPA PerceptOR for coordinated UGV and UAV exploration”.

代表性论著

1.     P. Chang and C. Mertz, Monte Carlo Sampling Based Imminent Collision

Detection Algorithm, IEEE International Conference on Transportation

Information and Safety, 2017 (Best Paper Award)

2.  P. Chang, Monte Carlo Sampling Based Collision Detection Algorithm

Development and False Positive and False Negative Rate Analysis: A

Bayesian Approach, Final report to DARPA, 2012

3. H. Tang, P. Chang, E. Molina and Z. Zhu, Uncertainty preserving patch-based online modeling for 3D model acquisition and integration from passive motion imagery, Evolutionary and Bio-inspired Computation: Theory and Applications VI, SPIE Defense, Security and Sensing 2012

4.  S. Wu, S. Decker, P. Chang, T. Camus and J. Eledath, Collision Sensing by

Stereo Vision and Radar Sensor Fusion, IEEE Trans. On Intelligent Transportation System, Vol. 10, Issue 4, Dec 2009

5.  S. Wu, S. Decker, Peng Chang, T. Camus and J. Eledath, Collision sensing by stereo vision and RADAR fusion, IEEE Intelligent Vehicle Symposium, 2008

6.  P. Chang, D. Hirvonen, T. Camus and B. Southall, Stereo-vision based object detection and classification for automotive applications and evaluations, IEEE Workshop on Machine Vision for Intelligent Vehicles, i n conjunction with CVPR, 2005

7.  P. Chang, T. Camus and R. Mandelbaum, Stereo-based vision system for

automotive imminent collision, IEEE Intelligent Vehicle Symposium, 2004

8.  P. Chang and M. Hebert, Robust tracking and structure from motion through sampling based uncertainty representation, proceedings of ICRA ' 02, May 2002

9.  P. Chang, M. Han and Y. Gong, Highlight detection and classification of

baseball game video with Hidden Markov Models, Proceedings of the

International Conference on Image Processing (ICIP '02), 2002

10. P. Chang and M. Hebert, Omni-directional structure from motion, Proceedings of the 2000 IEEE Workshop on Omnidirectional Vision, June, 2000

11. M. Hebert, R. MacLachlan and Peng Chang, Experiments with Driving Modes for Urban Robots, Proceedings of SPIE, 1999

12. P. Chang and J. Krumm, Object Recognition with Color Co-occurrence

Histogram, Proceedings of CVPR '99, 1999

13 P. Chang and M. Hebert, Omni-directional Visual Servoing for Human-Robot interaction, Proceedings of the 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '98), October, 1998