Events Calendar

PHD Defense - Weiwei Duan

Dissertation Title:
Efficient and Accurate Object Extraction from Scanned Maps by Leveraging External Data and Learning Representative Context

Venue: Zoom meeting link: https://usc.zoom.us/j/2332986718

Time: 1 pm - 2:30 pm (PT), August 4th

Abstract:
Scanned historical maps contain valuable information about environmental changes and human development over time. For instance, comparing historical waterline locations can reveal patterns of climate change. Extracting geographic objects in map images involves two main steps: 1. obtaining a substantial amount of labeled data to train extraction models, and 2. training extraction models to extract desired geographic objects. However, the extraction process has two difficulties. One difficulty is generating a large amount of labeled data with minimal human effort, as manual labeling is expensive and time-consuming. The other difficulty is ensuring that the extraction model learns representative and sufficient knowledge for the accurate extraction of geographic objects. The success of subsequent analyses, like calculating the shortest paths after extracting railroads, heavily depends on the accuracy of the extractions.

To generate labeled data with minimal human efforts, this thesis presents semi- and fully automatic approaches to generate labeled desired geographic objects by leveraging external data. The semi-automatic approach requires one or a few manually labeled desired objects to collect all desired objects from candidates provided by the external data. In contrast, existing methods require more than a few manually labeled desired objects to achieve the same goal. On the other hand, the proposed automatic approach aims to label the desired objects in close proximity to external data. Using the location and shape information fully from the external data, the proposed automatic approach can accurately label the desired objects on the maps. On the contrary, existing methods that do not utilize shape information may lead to false labels. The novel approaches introduced in this thesis significantly reduce the need for manual labeling while ensuring accurate results.

Extracting accurate geographic objects is the other difficulty due to the ambiguous appearances of objects and the overlapping objects in maps. The extraction model presented in this thesis captures cartographic symbols to differentiate desired objects from other objects with similar appearances. When the desired objects overlap with other objects on maps, the extracted results could be broken. The proposed extraction model captures sufficient spatial context to reduce broken extraction. For example, the proposed extractor learns the long and continuous structure of linear objects to reduce the gaps in the extracted lines. On the contrary, existing extractors lack the ability to learn sufficient spatial context, resulting in the broken extraction of linear objects. In summary, the proposed extractor learns representative cartographic symbols and sufficient spatial context to accurately extract desired objects.

The results of the experiment demonstrate the superiority of both the labeling and extraction approaches compared to the existing methods. Accurately labeled data generated by the proposed methods significantly improve the quality of training data for extraction models. The extraction results from the proposed extractor have much less false extraction and better continuity than state-of-the-art baselines. The combination of precise labeling and accurate extraction allows us to extract geographic objects in scanned historical maps. Therefore, we can analyze and interpret historical map data effectively.

Committee: Craig A. Knoblock Chair), Yao-Yi Chinag, Ram Nevatia, and John Wilson

Location: https://usc.zoom.us/j/2332986718

Audiences: Everyone Is Invited

Contact: Asiroh Cham

Event Link: https://usc.zoom.us/j/2332986718