Pedestrian reidentification - Why only face sent for reidentification?

[adammpolak]

@daniilpastukhov

For this repo: https://github.com/luxonis/depthai-experiments/tree/master/gen2-pedestrian-reidentification

Why do you only grab the face frame for reidentification? It seems like from the openvino info you could use the whole body? https://docs.openvino.ai/latest/omz_models_model_person_reidentification_retail_0288.html

[adammpolak]

Nevermind it turns out that does not happen and the readme is incorrect.

The entire person detection is sent for cropping and identification