Batbayar Battseren

Batbayar Battseren
Technische Universität Chemnitz · Department of Computer Science

Master of Engineering

About

16
Publications
5,302
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
23
Citations
Introduction
Batbayar Battseren currently works at Technische Universität Chemnitz. Batbayar does research in Electronic Engineering, Electrical Engineering and Computer Graphics. Their current project is 'Project APOLI'.

Publications

Publications (16)
Chapter
The automotive industry is currently experiencing a major paradigm shift from conventional, human-driven to autonomous vehicles driven by artificial intelligence. Automated vehicles offer a safe, reliable, efficient and cost-effective solution that will dramatically redefine the future of human mobility. Deep learning techniques have proven very su...
Chapter
Deep Learning has gained significant traction in recent years and has driven advancements in automatically recognizing patterns in data that surpass humans. Deep Learning has overcome the limitations of traditional machine learning algorithms as it has achieved astonishing results in a wide range of applications such as pattern recognition, speech...
Conference Paper
Full-text available
In the growing world of artificial intelligence (AI), there are tremendous opportunities in computer vision, as today's robots are already equipped with cameras or one can easily be attached. There are a variety of machines and robots moving autonomously in industries or warehouses, or something as new as self-driving cars on the road. Besides that...
Conference Paper
Full-text available
The aim of depth estimation is to achieve a representation of a scene's spatial structure and retrieve the three-dimensional shape and appearance in imagery representation. For depth predictions, we use an architecture that combines a transformer encoder and a convolutional decoder. We adopt dense vision transformers, an architecture that embraces...
Conference Paper
Full-text available
Autonomous vehicles are developed a lot in recent times, which has improved driving and road safety. Various instruments are used to understand the 3D geometric scene around the vehicle. Depth estimation is an important technique to analyze the environment in autonomous driving. Estimating the distance of the object from 2D images using only the ca...
Conference Paper
Full-text available
With the advance in autonomous vehicles, the need to analyze the images of road objects increased. That motivated many researchers to develop a state-of-art deep learning model to estimate the depth from the captured images. Currently, accurate depth estimation results from images are a fundamental portion of many applications, particularly in self...
Conference Paper
Full-text available
In the past years, the object detection applications have witnessed a rapid increase in usage of deep-learning (DL) based solutions, due to their accurate object detection, and robustness to illumination, scale, clutter, rotation changes, etc. Therefore, DL-based approaches started to be used in real-time applications. In an autonomous aerial inspe...
Preprint
In the growing world of Artificial Intelligence (AI) there are huge opportunities in computer vision as todays robots come equipped with cameras or one can be easily mounted on. There are lots of machines and robots which mobilize autonomously in industries, warehouses or something as new as self-driving cars. Localization of such robots is very im...
Article
Full-text available
The applications of unmanned aerial systems have dramatically increased in the late days, in particular within dull, dirty and dangerous missions, where it has been clearly shown that unmanned systems are better suited than manned aircrafts. The reduction of human involvements leads to an increasing demand for autonomous and operationally adaptive...
Conference Paper
Full-text available
In the domain of Unmanned Aerial Vehicle (UAV), the autonomy is getting more important. In order to reach a higher autonomy level, certain key software components have to be implemented. One of that is a middle layer, which lies between the decision-making higher-level and hardware-controlling lower-level components. This study aims to abstract the...
Conference Paper
Full-text available
This paper describes image processing for the detection of high voltage power lines. Different algorithms were applied for the detection of lines from images taken by unmanned aerial vehicle-based inspection. The purpose of detection is to find out the heading direction, while the unmanned aerial vehicle position and camera view angle are not defin...
Conference Paper
In this paper, we present an image processing algorithm for high voltage power line insulator fault (burn-mark) detection, and its ongoing result. The proposed algorithm consists of two main parts, which are insulator detection and fault detection. First, a geometric shape-based symmetry detector is used for insulator detection. For the burn-mark d...
Article
This paper describes a finite state machine for adaptive mission control of mini aerial vehicles. The purpose of a finite state machine is to support mission control during aerial inspection of high voltage transmission lines and insulators independently from environmental and other conditions. One of the basic application of our mini aerial vehicl...
Conference Paper
Full-text available
Today, numerous researchers and companies use unmanned aerial vehicles (UAVs) for a wide range of different applications. Modern UAVs are equipped with powerful sensors for various measurement and inspection tasks. One of the main technology drivers of UAV-based inspection is the energy sector for renewable power and electricity distribution. This...

Network

Cited By

Projects

Project (1)
Project
APOLI: Automated POwerLine Inspection Autonomous object inspection requires high sophisticated methods for image processing and control. We develop methods for image based inspections of power lines and autonomous flight control algorthms for inspection drones.