CEE PhD student Yuqing Gao won Best Poster Award (2nd prize) in the student poster competition at the Tsinghua-Berkeley Shenzhen Institution (TBSI) Retreat 2018 for his two posters: Structural ImageNet and PEER Hub ImageNet Challenge 2018 and Synthetic Data Aggregation: Leaf-Bootstrapping Generative Adversarial Networks for Image-based Structural Scene and Damage Identification.
In addition, Gao led the group in the Incubation of Innovation in Interdisciplinary Research Applications competitio, and this group received the Best Creativity Award.
Gao's adviser is Khalid Mosalam.
The Pacific Earthquake Engineering Research (PEER) Center organized the first image-based structural damage recognition competition, the PEER Hub ImageNet (PHI) Challenge.
PEER provided a large image dataset relevant to the field of structural engineering, and designed several detection tasks to contribute to the establishment of automated vision-based structural health monitoring.
The goal of the PHI challenge is to evaluate algorithms for structural image classification using a large-scale dataset based on regular conditions and past reconnaissance efforts after extreme events. The state-of-the-art algorithms are expected to have both accuracy and generalization towards a complex structural image dataset.