Dhanushka Liyanage

Dr. Dhanushka Liyanage

Tallinn University of Technology, Tallinn, Harjumaa, Estonia
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2019
Verified
Conference Paper
Closed access
AZAli Zahavi
Ali Zahavi
APAndrei Palshin
Andrei Palshin
Dhanushka LiyanageDhanushka Liyanage
Dhanushka Liyanage
MTMart Tamre
Mart Tamre
This paper discusses the influence of different illumination sources on hyperspectral imaging. In order to find the best illumination source for hyperspectral image acquisition, sun, fluorescent, light-emitting diodes (LED) and incandescent light sources have been used. The hyperspectral images were acquired using two hyperspectral cameras, Resonon Pika II in the range of 400-1000 nm and Resonon Near Infrared camera in the range of 1000-1700 nm. Then, the results have been compared with the literature. This chapter of the paper suggests the incandescent lights as the best illumination source in HSI. The second part of the paper presents light absorption spectra of different materials including Aluminium Oxide Al 2 O 3 , Aluminium Oxide plus Cubic Boron Nitride (cBN), Wood and unknown Metal Disk by using two hyperspectral cameras, Resonon Pika II and Resonon Near Infrared by the presence of incandescent lights as the illumination source. All experiments have been done in Mechatronics and Autonomous Systems Centre of Tallinn University of Technology.

8 April 2025 in Sensors
Verified
Journal Article
Open access
PDF file
DVDaniil Valme
Daniil Valme
Anton RassõlkinAnton Rassõlkin
Anton Rassõlkin
Dhanushka LiyanageDhanushka Liyanage
Dhanushka Liyanage
Hyperspectral imaging (HSI) has evolved from its origins in space missions to become a promising sensing technology for mobile ground robots, offering unique capabilities in material identification and scene understanding. This review examines the integration and applications of HSI systems in ground-based mobile platforms, with emphasis on outdoor implementations. The analysis covers recent developments in two main application domains: autonomous navigation and inspection tasks. In navigation, the review explores HSI applications in Advanced Driver Assistance Systems (ADAS) and off-road scenarios, examining how spectral information enhances environmental perception and decision making. For inspection applications, the investigation covers HSI deployment in search and rescue operations, mining exploration, and infrastructure monitoring. The review addresses key technical aspects including sensor types, acquisition modes, and platform integration challenges, particularly focusing on environmental factors affecting outdoor HSI deployment. Additionally, it analyzes available datasets and annotation approaches, highlighting their significance for developing robust classification algorithms. While recent advances in sensor design and processing capabilities have expanded HSI applications, challenges remain in real-time processing, environmental robustness, and system cost. The review concludes with a discussion of future research directions and opportunities for advancing HSI technology in mobile robotics applications.

1 July 2020
Verified
Conference Paper
Closed access
Dhanushka LiyanageDhanushka Liyanage
Dhanushka Liyanage
RHRobert Hudjakov
Robert Hudjakov
MTMart Tamre
Mart Tamre
Terrain recognition for off-road unmanned ground vehicles driven on unstructured terrains are far complex in contrast to terrain recognition for road vehicles which are driven on structured terrains. Large number of terrain classes mixed-up in unstructured terrains make it difficult to classify using convolution neural networks based on RGB images. Partly it is attributed to lack of sufficiently annotated training data for neural network, and partly it is difficult to label such a large number of object classes which shows visual similarities. Introducing additional details about the scene with hyperspectral or multispectral cameras, the scene classification can be greatly improved for annotation of training data for neural network training. Using spectral signatures of different materials, hyperspectral imaging can detect different materials in the scene. This article discusses a method to annotate RGB images and semantic segmentation for autonomous driving on unstructured terrain applications by using hyperspectral imaging. The RGB images will be generated using same hyperspectral data cube by extracting certain spectral bands in the visible light spectrum. Using semantic segmentation network ResNet18, manually annotated training data will be compared with hyperspectral method assisted annotated data by classifying terrain scenarios.

1 July 2020
Verified
Conference Paper
Closed access
Dhanushka LiyanageDhanushka Liyanage
Dhanushka Liyanage
RHRobert Hudjakov
Robert Hudjakov
MTMart Tamre
Mart Tamre
Hyperspectral images contain hundreds of spectral bands. These bands contain abundant information and more often redundant information. This article presents an unsupervised band selection method to choose most significant spectral image bands from hyperspectral datacube which maximize the relavance and minimize redundancy. The outcome of the research can be used for two purposes. One of them is to fabricate multispectral sensor which is more effective in identifying the subjects of interest. The other purpose is to enhance computational efficiency in classification of the hyperspectral image by processing only the selected spectral bands. Proposed method is based on spectral pooling of hyperspectral data cube. Since spectral pooling methods cause information loss which reduces the discrimination of material classes. This article suggests a novel approach which can minimize the loss while improving material classes discrimination. The proposed technique uses min-max pooling together with reflectance intensity gradient of neighboring pixels of hyperspectral image in spectral data axis. Experiment results of classifying terrain hyperspectral datasets are presented to validate the consistency of image classification which contains several material classes. A comparative analysis has been conducted between max pooling, principle component analysis and the proposed min-max pooling.

1 January 2018 in DAAAM Proceedings
Verified
Book Chapter
Closed access
AZAli Zahavi
Ali Zahavi
FAFadi Al Afrange
Fadi Al Afrange
SHShahriar Najafi Haeri
Shahriar Najafi Haeri
UAUdith Ajeevan
Udith Ajeevan
Dhanushka LiyanageDhanushka Liyanage
Dhanushka Liyanage

1 January 2022
Verified
Book Chapter
Closed access
Dhanushka LiyanageDhanushka Liyanage
Dhanushka Liyanage
MTMart Tamre
Mart Tamre
RHRobert Hudjakov
Robert Hudjakov
Product quality assurance is a vital component in any manufacturing process. With the advancement of machine vision, the product quality inspection has been vastly improved. This couldn't be achieved with human inspection otherwise when it comes to consistency, accuracy, and the speed. The advance sensor technologies and image processing algorithms are ensuring the product and process quality in various industries including pharmaceutical manufacturing, food production, agriculture, and waste sorting. In contrast to the RGB imaging technology, multispectral and hyperspectral imaging technologies carry more information about the objects under inspection. With the help of both spectral and spatial information, it is possible to discriminate the quality indices of various products with higher accuracy than RGB imaging methods. This chapter discusses the state-of-the-art product quality inspection applications using hyperspectral imaging and multispectral imaging using modern machine learning and other statistical algorithms.