Congratulations to Yuzhuo Ren for passing her defense on April 26, 2017. Her Ph.D. thesis is entitled “Machine Learning Techniques for Outdoor and Indoor Layout Estimation”.

Abstract of thesis:

In my dissertation, I study three research problems: 1) Outdoor geometric labeling, and 2) Indoor layout estimation and 3) 3D object detection.

A novel method that extracts global attributes from outdoor images to facilitate geometric layout labeling is proposed. The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes. The performance of the proposed GAL system is demonstrated and benchmarked with several state-of-the-art algorithms against a popular outdoor scene layout dataset.

Existing solutions to indoor layout estimation largely rely on hand-craft features and vanishing lines. They often fail in highly cluttered indoor scenes. The proposed coarse-to-fine indoor layout estimation (CFILE) method consists of two stages: 1) coarse layout estimation; and 2) fine layout localization. In the first stage, we adopt a fully convolutional neural network (FCN) to obtain a coarse-scale room layout estimate that is close to the ground truth globally. In the second stage, we formulate an optimization framework that enforces several constraints such as layout contour straightness, surface smoothness and geometric constraints for layout detail refinement. The proposed CFILE system offers the state-of-the-art performance on two common benchmark datasets.

Given a RGB-D image, we examine the 3D object detection problem with an objective to produce a bounding box around the object and classify its category. This is a challenging problem due to high intra-class variance, illumination change, background clutter and occlusion. Here, we propose a novel solution that integrates the context information together to provide a robust 3D object detection solution. Extensive experiments are conducted to demonstrate that the proposed Context-3D method achieves the state-of-the-art performance for the 3D object detection problem in two popular benchmark datasets.

We are so glad to have her share her Ph.D. experience with us. Here is her sharing.

Ph.D. experience:

Ph.D. study is a very precious experience in my life. I learnt a lot during my Ph.D. study by working with Professor Kuo, such as how to do rigorous research, how to face and overcome difficulties. MCL is a big family with huge resources. There are many talent students working on various research problems. Excellent students and researchers in MCL stimulate me to learn and grow. I benefit a lot from working on various projects and working with teams. The weekly seminar and the discussion with labmates greatly broaden my knowledge in different research fields.

I would like to thank my advisor Professor C.-C. Jay Kuo who spent a lot of time and effort guiding my research. His endless energy and enthusiasm in research stimulates me for hard working and delivery of high quality research. I would also like to thank all my labmates for their support and encouragement.

Congratulations again to Yuzhuo and we wish her all the best in her future career.