Abstract
Abstract. A successful image matching is essential to provide an automatic photogrammetric process accurately. Feature detection, extraction and matching algorithms have performed on the high resolution images perfectly. However, images of cameras, which are equipped with low-resolution thermal sensors are problematic with the current algorithms. In this paper, some digital image processing techniques were applied to the low-resolution images taken with Optris PI 450 382 x 288 pixel optical resolution lightweight thermal camera to increase extraction and matching performance. Image enhancement methods that adjust low quality digital thermal images, were used to produce more suitable images for detection and extraction. Three main digital image process techniques: histogram equalization, high pass and low pass filters were considered to increase the signal-to-noise ratio, sharpen image, remove noise, respectively. Later on, the pre-processed images were evaluated using current image detection and feature extraction methods Maximally Stable Extremal Regions (MSER) and Speeded Up Robust Features (SURF) algorithms. Obtained results showed that some enhancement methods increased number of extracted features and decreased blunder errors during image matching. Consequently, the effects of different pre-process techniques were compared in the paper.
Highlights
Thermal cameras offer the benefits of ease of use, relatively low-cost surveys to map 3-D structures and create digital elevation models (DEMs) using photogrammetric method (Erenoglu et al 2017, Fonstad et al 2013, Vilardo et al 2015)
Image matching performances were compared after features extraction was executed
To understand the influences of the parameter values on feature detection, Maximally Stable Extremal Regions (MSER) and Speeded Up Robust Features (SURF) algorithms were applied to the images with different parameter values
Summary
Thermal cameras offer the benefits of ease of use, relatively low-cost surveys to map 3-D structures and create digital elevation models (DEMs) using photogrammetric method (Erenoglu et al 2017, Fonstad et al 2013, Vilardo et al 2015). Due to low spatial and radiometric resolutions, most of the matched features on the thermal images are detected as outliers. Each enhancement methods produce a new diverse image, depending on the parameters used in the process algorithm. The Gaussian filter which defines the blur level with a chosen standard deviation and the mask size, influence feature detection, extraction and matching results. The image filtering methods using different parameters were analysed to acquire better matching accuracy. The paper explains that some analyses before the feature detection might contribute matching results in spite of low spatial and radiometric image resolutions.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
