Abstract:
ReID is difficult due to person images’ large pose variations and misalignment errors. Existing works use pose estimation, part segmentation, etc. to improve pedestrian representations. Boosting ReID accuracy requires computational overheads and makes deep models complex and hard to tune. We propose a Part-Guided Representation (PGR) with Pose Invariant Feature (PIF) and Local Descriptive Feature (LDF) for a more efficient solution. PGR is “Part-Guided” because local part cues train and supervise it. PIF approximates a pose-invariant representation inferred by pose estimation and normalization. LDF approximates body region segmentation to focus on discriminative body parts. Thus, extra pose extraction is only used during PGR training to supervise learning, but not during feature extraction. PGR outperforms recent works on five popular datasets.
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
