Video-based descriptors for object recognition
作者:
Highlights:
•
摘要
We describe a visual recognition system operating on a hand-held device, based on a video-based feature descriptor, and characterize its invariance and discriminative properties. Feature selection and tracking are performed in real-time, and used to train a template-based classifier during a capture phase prompted by the user. During normal operation, the system recognizes objects in the field of view based on their ranking. Severe resource constraints have prompted a re-evaluation of existing algorithms improving their performance (accuracy and robustness) as well as computational efficiency. We motivate the design choices in the implementation with a characterization of the stability properties of local invariant detectors, and of the conditions under which a template-based descriptor is optimal. The analysis also highlights the role of time as “weak supervisor” during training, which we exploit in our implementation.
论文关键词:Feature tracking,Video-based descriptors,Object recognition,Multi-view recognition,Mobile devices,Visual recognition,Active vision
论文评审过程:Received 20 February 2011, Accepted 12 August 2011, Available online 22 August 2011.
论文官网地址:https://doi.org/10.1016/j.imavis.2011.08.003