Abstract:
Background clutter often affects RGBT tracking methods that localize a target object with a bounding box. This article introduces noise-robust cross-modal ranking to reduce background effects in RGBT target bounding boxes. We address noise interference in cross-modal fusion and seed labels from two angles. First, soft cross-modality consistency allows sparse inconsistency in fusing different modalities, taking into account collaboration and heterogeneity for better fusion. Second, optimal seed learning handles ranking seed label noise caused by irregular object shape and occlusion. We rank each feature and use cross-feature consistency to deploy complementarity and maintain structural information within each modality. The proposed model is solved using a unified optimization framework with fast convergence. The proposed approach outperforms state-of-the-art tracking methods on GTOT and RGBT234 benchmark data sets in extensive experiments.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
