Sökning: "feature descriptors"
Visar resultat 1 - 5 av 23 uppsatser innehållade orden feature descriptors.
1. Representation learning for single cell morphological phenotyping
Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysikSammanfattning : Preclinical research for developing new drugs is a long and expensive procedure. Experiments relying on image acquisition and analysis tend to be low throughput and use reporter systems that may influence the studied cells. LÄS MER
2. RGB-D Deep Learning keypoints and descriptors extraction Network for feature-based Visual Odometry systems
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Feature extractors in Visual Odometry pipelines rarely exploit depth signals, even though depth sensors and RGB-D cameras are commonly used in later stages of Visual Odometry systems. Nonetheless, depth sensors from RGB-D cameras function even with no external light and can provide feature extractors with additional structural information otherwise invisible in RGB images. LÄS MER
3. FPGA Implementation of the ORB Algorithm
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : Image feature extraction has become a key technology in the field of autonomous Artificial Intelligence. The algorithm Oriented FAST and Rotated BRIEF (ORB), uses established technologies in image processing to allow a computer to ”see” and navigate its surroundings. LÄS MER
4. Local Feature Correspondence on Side-Scan Sonar Seafloor Images
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In underwater environments, the perception and navigation systems are heavily dependent on the acoustic wave based sonar technology. Side-scan sonar (SSS) provides high-resolution, photo-realistic images of the seafloor at a relatively cheap price. LÄS MER
5. Adaptive Losses for Camera Pose Supervision
Master-uppsats, Linköpings universitet/DatorseendeSammanfattning : This master thesis studies the learning of dense feature descriptors where camera poses are the only supervisory signal. The use of camera poses as a supervisory signal has only been published once before, and this thesis expands on this previous work by utilizing a couple of different techniques meant increase the robustness of the method, which is particularly important when not having access to ground-truth correspondences. LÄS MER