View source for GRABTAXI HOLDINGS PTE. LTD. (20240257352). SEGMENTING METHOD FOR EXTRACTING A ROAD NETWORK FOR USE IN VEHICLE ROUTING, METHOD OF TRAINING THE MAP SEGMENTER, AND METHOD OF CONTROLLING A VEHICLE simplified abstract

=SEGMENTING METHOD FOR EXTRACTING A ROAD NETWORK FOR USE IN VEHICLE ROUTING, METHOD OF TRAINING THE MAP SEGMENTER, AND METHOD OF CONTROLLING A VEHICLE=


==Organization Name==

[[:Category:GRABTAXI HOLDINGS PTE. LTD.|GRABTAXI HOLDINGS PTE. LTD.]]


[[Category:GRABTAXI HOLDINGS PTE. LTD.]]

==Inventor(s)==

[[:Category:Wenmiao Hu of Singapore (SG)|Wenmiao Hu of Singapore (SG)]][[Category:Wenmiao Hu of Singapore (SG)]]

[[:Category:Yifang Yin of Singapore (SG)|Yifang Yin of Singapore (SG)]][[Category:Yifang Yin of Singapore (SG)]]

[[:Category:An Tran of Singapore (SG)|An Tran of Singapore (SG)]][[Category:An Tran of Singapore (SG)]]

[[:Category:Hannes Martin Kruppa of Singapore (SG)|Hannes Martin Kruppa of Singapore (SG)]][[Category:Hannes Martin Kruppa of Singapore (SG)]]

[[:Category:Roger Zimmermann of Singapore (SG)|Roger Zimmermann of Singapore (SG)]][[Category:Roger Zimmermann of Singapore (SG)]]

==SEGMENTING METHOD FOR EXTRACTING A ROAD NETWORK FOR USE IN VEHICLE ROUTING, METHOD OF TRAINING THE MAP SEGMENTER, AND METHOD OF CONTROLLING A VEHICLE - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240257352 titled 'SEGMENTING METHOD FOR EXTRACTING A ROAD NETWORK FOR USE IN VEHICLE ROUTING, METHOD OF TRAINING THE MAP SEGMENTER, AND METHOD OF CONTROLLING A VEHICLE

'''Simplified Explanation:'''
This patent application describes a computer-implemented training method for a map segmenter using a deep neural network. The method involves providing a training dataset with map images and segmentation masks, generating synthetic map images using a generative adversarial network, and training the map segmenter with the dataset. A segmenting method for extracting a road network and a computer program product are also disclosed.

* The patent application introduces a novel method for training a map segmenter using a deep neural network.
* It involves providing a training dataset with map images and segmentation masks acquired from image acquisition apparatuses.
* Synthetic map images are generated using a generative adversarial network, enhancing the training dataset.
* The trained map segmenter can be used for extracting a road network for vehicle routing applications.
* The innovation aims to improve the accuracy and efficiency of map segmentation tasks.

'''Potential Applications:'''
1. Autonomous vehicle navigation systems
2. Urban planning and infrastructure development
3. Geographic information systems (GIS) for mapping applications

'''Problems Solved:'''
1. Enhancing the accuracy of map segmentation tasks
2. Improving the efficiency of road network extraction
3. Streamlining vehicle routing algorithms

'''Benefits:'''
1. Increased precision in identifying road networks
2. Faster and more reliable vehicle routing
3. Enhanced performance of geographic mapping software

'''Commercial Applications:'''
Optimizing Logistics Operations with Advanced Map Segmentation Technology

'''Prior Art:'''
Prior research in the field of computer vision and deep learning algorithms for map segmentation tasks.

'''Frequently Updated Research:'''
Ongoing advancements in deep learning models for map segmentation and road network extraction.

'''Questions about Map Segmentation Technology:'''
1. How does this technology improve the accuracy of road network extraction compared to traditional methods?
2. What are the potential limitations of using synthetic map images in training the map segmenter?


==Original Abstract Submitted==

computer-implemented training method of training a map segmenter including a deep neural network, including: providing a training dataset including training image data including training pairs of map images of a geographical area acquired by one or more image acquisition apparatuses and corresponding segmentation masks, wherein the training image data may be stored a computer memory; generating synthetic map images by a computer-implemented generation method including creating synthetic map images by applying a generative adversarial network onto segmentation masks, wherein the segmentation masks may include the corresponding segmentation masks and additional segmentation masks; storing the synthetic map images and the corresponding additional segmentation masks as additional training data pairs in the training dataset in the computer memory; and training the map segmenter with the training dataset. computer-implemented segmenting method for extracting a road network for use in vehicle routing with the trained segmenter, and a computer program product are also disclosed.



[[Category:G06T7/10]]
[[Category:G01C21/00]]
[[Category:G06T11/60]]
[[Category:G06V10/764]]
[[Category:G06V20/10]]
[[Category:G06V20/56]]
[[Category:CPC_G06T7/10]]