Bashir Kazimi

Bashir Kazimi
Leibniz Universität Hannover · Geodetic Institute

About

8
Publications
5,181
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
43
Citations
Introduction
Research in deep learning for detection of structures related to historical mining and archaeology using airborne laser scanning data
Additional affiliations
April 2017 - present
Leibniz Universität Hannover
Position
  • Researcher
Description
  • Deep learning for archaeological mining
Education
April 2017 - March 2021
Leibniz Universität Hannover
Field of study
  • Geodesy and Geoinformatics
September 2015 - April 2017
Universitat Politècnica de Catalunya
Field of study
  • Artificial Intelligence
September 2010 - June 2015
Middle East Technical University
Field of study
  • Computer Engineering

Publications

Publications (8)
Article
Full-text available
This paper explores the role deep convolutional neural networks play in automated extraction of linear structures using semantic segmentation techniques in Digital Terrain Models (DTMs). DTM is a regularly gridded raster created from laser scanning point clouds and represents elevations of the bare earth surface with respect to a reference. Recent...
Article
Full-text available
Automated recognition of terrain structures is a major research problem in many application areas. These structures can be investigated in raster products such as Digital Elevation Models (DEMs) generated from Airborne Laser Scanning (ALS) data. Following the success of deep learning and computer vision techniques on color images, researchers have...
Article
Full-text available
We explore the use of semantic segmentation in Digital Terrain Models (DTMS) for detecting manmade landscape structures in archaeological sites. DTM data are stored and processed as large matrices of depth 1 as opposed to depth 3 in RGB images. The matrices usually contain continuous real-valued information upper bound of which is not fixed, such a...
Chapter
We use an object instance segmentation approach in deep learning to detect and outline objects in Digital Terrain Models (DTMs) derived from Airborne Laser Scanning (ALS) data. Object detection methods in computer vision have been extensively applied to RGB images, and gained excellent results. In this work, we use Mask R-CNN, a famous object detec...
Conference Paper
Full-text available
It is important to preserve archaeological monuments as they play a key role in helping us understand human history and their accomplishments for times with no or little written sources. The first step for this purpose is an efficient method for collecting and documenting information about objects of interest for archaeologists. Airborne laser scan...
Conference Paper
Full-text available
In the last couple of years Deep Learning has gained popularity and shown potential in the field of classification. In contrast to 2D image data, Airborne Laser Scanning data is complex due to its irregular 3D structure, which turns the classification into a difficult task. Classifying point clouds can be separated into pointwise semantic classifi...
Presentation
Archaeological monuments need to be preserved and protected. A fundamental prerequisite for such a preservation is an adequate object acquisition and documentation. Some of the objects, however, such as archaeological objects visible in the terrain like ramparts, grave-mounds or traces of historic agriculture – even when covered by forest or bushes...
Conference Paper
Full-text available
In recent years, Neural Machine Translation (NMT) has achieved state-of-the-art performance in translating from a language; source language, to another; target language. However, many of the proposed methods use word embedding techniques to represent a sentence in the source or target language. Character embedding techniques for this task has been...

Network

Cited By

Projects

Projects (3)
Project
In this project, we use Convolutional Neural Networks (CNNs) to analyze the LIDAR data, and identify unknown archaeological objects
Project
The goal of this project is to classify high resolution airborne laser scanning point clouds using Deep Learning approaches. The classified should correctly classify lidar data as well as dense image matching point cloud data.