BladeNeRF: Exploiting camera constraints for NeRF in repetitive texture-less 3D reconstruction

Neural Radiance Fields (NeRFs) have demonstrated remarkable capabilities in photo-realistic 3D reconstruction. NeRFs often take as input posed images where the camera poses come from either off-the-shelf S\textit{f}M or online optimization together with NeRFs. However, we find that both strategies yield suboptimal results in recovering camera...

Improving the Performance of Object Counting Using Training Images in the Frequency Domain

Convolutional Neural Networks (CNNs) have made significant strides in the field of image processing over the last decade. Different approaches have been taken and improvements have been suggested. This paper looks at a newer novelty to neural networks for image counting, which is based on single-pixel center localization instead of the...

Injecting prior frequency information in DETR for wheat head detection

Wheat is among the most important grains worldwide. For the assessment of wheat fields, image detection of spikes atop the plant containing grain is used. Previous work in deep learning for precision agriculture employs the already established object detectors, Faster R-CNN and YOLO, adapted for the given context. However, these models suffer...

Vertex-voting-based polygonal object detection

Although the pixel-wise labelling approaches have been exploited in depth and achieve good results in segmentation tasks, the grouped pixels are not ideal output for many end-users. In this paper, we propose a vertex-voting-based approach that can directly extract the polygon representations of objects. In order to better solve overlapping...

Modelling the influence of physical properties of extracellular polymeric substances in aerobic granule morphology

This thesis examines the influence of physical properties of structural EPS on granule morphology. Two types of structural EPS are found to be important. These types of structural EPS are: surface bound EPS and hydrogel forming EPS matrix. VirtualLeaf is used to model granules which contain only binding surface bound EPS. The TST model is used...

Analysis of Alginate-like Exopolysaccharides for the Application in Enhanced Oil Recovery

Alginate-like exopolysaccharides (ALE) can be extracted from granular sludge, which is produced during aerobic granular sludge waste water treatment as a waste product. Processing the waste is a costly operation. It is believed that ALE consist mostly of alginates. The chemical and mechanical properties of alginates are potential for the...