Camera Pose Estimation using CNN

Simple item page
dc.contributor.authorWattanacheep, Bhattarabhorn
dc.contributor.authorChitsobhuk, Orachat
dc.date.accessioned2026-08-06T10:29:24Z
dc.date.available2026-08-06T10:29:24Z
dc.date.issued2020-08-23
dc.description.abstractEstimating camera pose is a significant process, which assures the success of the 3D modeling performance. This research presents a camera pose estimation using convolutional neural network (CNN) to transfer learning from pre-trained deep learning VGG19 model in order to extract features from a single image using several datasets captured in indoor and outdoor environments with diverse perspectives and photographic styles. Due to the large dimensions of the extracted features, Latent Semantic Analysis (LSA) are introduced prior to the CNN input. Then, the CNN is trained to predict the camera views and translations. The prediction performance is measured in terms of average mean square errors and compared to the reference techniques. As a result, the regression estimation of the proposed CNN model outperforms the others with average 0.24 degrees rotation error and 0.26 m. translation errors.
dc.identifier.citationACM International Conference Proceeding Series, 84-88, 2020
dc.identifier.doi10.1145/3425577.3425593
dc.identifier.other2-s2.0-85100462354
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/11172
dc.sourceACM International Conference Proceeding Series
dc.subject3D Reconstruction
dc.subjectDeep Learning
dc.subjectImage Processing
dc.subjectRobotics
dc.titleCamera Pose Estimation using CNN
dc.typeConference Paper

Files

Collections

Research