Jacob J. Lin 林之謙

I am an Assistant Professor at National Taiwan University in the Department of Civil Engineering. Earlier, I received my PhD in CEE and MS in CS from UIUC advised by Mani Golparvar-Fard. We started an AI construction company Reconstruct with Derek Hoiem and Joe Degol.

My research focuses on creating new computer vision algorithms that use visual data and BIM for construction project controls; leveraging synergies between lean construction, BIM and Reality modeling for construction production management; and building predictive schedule analytics for construction risk management.

Email  /  CV  /  Biography  /  Linkedin  /  Google Scholar

profile photo
Research
Automated Progress Monitoring Using Multiview Geometry and Material Classification
Jacob J. Lin, Amir Ibrahim, Mani Golparvar-Fard, Derek Hoiem, Jae Yong Lee

A new end-to-end system is developed that reasons about geometry and appearance using CNN model. The system reports the state of work in progress per BIM element and schedule task.

paper 1 / paper 2 (under review)
Automated Bridge Inspection with Aerial Robots: Visual Data Capture, 3D Mapping, Defect Detection, Analysis and Reporting
Jacob J. Lin, Amir Ibrahim, Mani Golparvar-Fard

We present an end-to-end robotic bridge inspection system consisting of five tightly coupled methods to (1) create automatic data collection missions; (2) assure visual quality of such missions; (3) reconstruct 3D models of elevated structures; (4) detect and localize surface distresses in 3D; and (5) generate reports complying with highway agencies' requirements.

paper 1 (under review)
A Visual and Virtual Production Management System
Jacob J. Lin, Mani Golparvar-Fard

A visual and virtual project control system is presented that improves understanding of how construction progress can be captured, communicated, and analyzed in the form of a production system.

paper 1 / paper 2 / paper 3*
*ASCE DSA Best Paper Award
Predictive Schedule Analytics for Proactive Project Controls
Jacob J. Lin, Mani Golparvar-Fard

The system predicts the reliability of the look-ahead plans, supports root-cause assessment on plan failure, facilitates information flows and decentralizes decision-making.

paper 1
Construction Site Logistics Simulation
Jacob J. Lin, Chi-En Yang, Wei-Han Hung, Shih-Chung Kang

A game engine-based simulation system is developed to automatically evaluate construction site logistics plan.

paper 1 / paper 2
Affiliations
               
NTU
2005-2012, 2020-
UW
2012-2013
UIUC
2014-2020
Reconstruct
2015-
Teaching
CIE1005 Engineering Graphics and Design
Fall 2020

template credits: this and this.