Abstract:
Remote sensing imagery faces large-scale change, uncertain direction, and high density when detecting and localizing multiclass objects. Remote sensing images benefit from context information. This letter proposes a context-driven detection network (CDD-Net) to improve remote sensing image multiclass object detection. A local context feature network (LCFN) is suggested to capture local neighboring objects and features. A hybrid attention pyramid network (HAPN) is created to prioritize valuable features. HAPN adds a squeeze and excitation block (SEB) and three asymmetric convolution blocks (ACBs) to the feature pyramid network (FPN). The CDD-Net performed well in DOTA-v1.5 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
