Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Multi-Task Learning SegNet Architecture for Semantic Segmentation

Sorg, Bradley R.
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1542726487025455

Abstract Details

2018, Master of Science in Computer Engineering, University of Dayton, Engineering.
Semantic segmentation has been a complex problem in the field of computer vision and is essential for image analysis tasks. Currently, most state-of-the-art algorithms rely on deep convolutional neural networks (DCNN) to perform this task. DCNNs are able to down-sample the spatial resolution of the input image into low resolution feature mappings which are then up-sampled to produce the segmented images. However, the reduction of this spatial information causes the high frequency details of the image to be lessened resulting in blurry and inaccurate object boundaries. In order to improve this limitation, I propose combining a DCNN used for semantic segmentation with semantic boundary information. This is done using a multi-task approach by incorporating a boundary detection network into the encoder decoder architecture SegNet. I explore two different multi-task learning methods of incorporating this boundary information into the SegNet architecture. These two multi-task approaches are as follows: the incorporation of the global probability of boundary algorithm and the inclusion of an edge class. In doing so, the multi-task learning network is provided more information, thus improving segmentation accuracy, specifically boundary delineation. This approach was tested on the CityScapes dataset as well as the RGB-NIR Scene dataset. Compared to using SegNet alone, I observe increased boundary segmentation accuracies using this approach. I am able to show that the addition of a boundary detection information significantly improves the semantic segmentation results of a DCNN.
Vijayan Asari, Ph.D. (Committee Chair)
Theus Aspiras, Ph.D. (Committee Member)
Eric Balster, Ph.D. (Committee Member)
64 p.
Artificial Intelligence; Computer Engineering; Electrical Engineering
semantic segmentation; SegNet; scene labeling; boundary detection; multi-task learning;

Recommended Citations

Citations

  • Sorg, B. R. (2018). Multi-Task Learning SegNet Architecture for Semantic Segmentation [Master's thesis, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1542726487025455

    APA Style (7th edition)

  • Sorg, Bradley. Multi-Task Learning SegNet Architecture for Semantic Segmentation. 2018. University of Dayton, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1542726487025455.

    MLA Style (8th edition)

  • Sorg, Bradley. "Multi-Task Learning SegNet Architecture for Semantic Segmentation." Master's thesis, University of Dayton, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1542726487025455

    Chicago Manual of Style (17th edition)

dayton1542726487025455
959
© 2018, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.