A Modern Computer Vision Library

View the Project on GitHub liuliu/ccv



ccv_tld_new(ccv_dense_matrix_t *a, ccv_rect_t box, ccv_tld_param_t params)

Create a new TLD tracking instance from a given first frame image and the tracking rectangle.

return: A ccv_tld_t object holds temporal information about tracking.


Short-term lucas-kanade tracking parameters

Image pyramid generation parameters (for scale-invariant object detection)

Samples generation parameters

Ferns classifier parameters

Nearest neighbor classifier parameters

Deformation parameters to apply perspective transforms on patches for robustness

Speed up parameters


ccv_comp_t ccv_tld_track_object(ccv_tld_t *tld, ccv_dense_matrix_t *a, ccv_dense_matrix_t *b, ccv_tld_info_t *info)

ccv doesn’t have retain / release semantics. Thus, a TLD instance cannot retain the most recent frame it tracks for future reference, you have to pass that in by yourself.

return: The newly predicted bounding box for the tracking object.


‹  back 

comments powered by Disqus