Essays about: "Mask R-CNN"
Showing result 11 - 15 of 29 essays containing the words Mask R-CNN.
-
11. 3D Instance Segmentation of Cluttered Scenes : A Comparative Study of 3D Data Representations
University essay from Linköpings universitet/DatorseendeAbstract : This thesis provides a comparison between instance segmentation methods using point clouds and depth images. Specifically, their performance on cluttered scenes of irregular objects in an industrial environment is investigated. Recent work by Wang et al. READ MORE
-
12. Application of Deep-learning Method to Surface Anomaly Detection
University essay from Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)Abstract : In traditional industrial manufacturing, due to the limitations of science and technology, manual inspection methods are still used to detect product surface defects. This method is slow and inefficient due to manual limitations and backward technology. READ MORE
-
13. Improving Automatic Image Annotation Using Metadata
University essay from Linköpings universitet/DatorseendeAbstract : Detecting and outlining products in images is beneficial for many use cases in e-commerce, such as automatically identifying and locating products within images and proposing matches for the detections. This study investigated how the utilisation of metadata associated with images of products could help boost the performance of an existing approach with the ultimate goal of reducing manual labour needed to annotate images. READ MORE
-
14. Using Mask R-CNN for Instance Segmentation of Eyeglass Lenses
University essay from KTH/Matematisk statistikAbstract : This thesis investigates the performance of Mask R-CNN when utilizing transfer learning on a small dataset. The aim was to instance segment eyeglass lenses as accurately as possible from self-portrait images. Five different models were trained, where the key difference was the types of eyeglasses the models were trained on. READ MORE
-
15. Weed Detection in UAV Images of Cereal Crops with Instance Segmentation
University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknikAbstract : Modern weeding is predominantly carried out by spraying whole fields with toxic pesticides, a process that accomplishes the main goal of eliminating weeds, but at a cost of the local environment. Weed management systems based on AI solutions enable more targeted actions, such as site-specific spraying, which is essential in reducing the need for chemicals. READ MORE