* update empty features check (#6985)

* rtsp push stream in pipeline (#7000)

* add push stream

* update push stream docs

* update class name

* update PP-Vehicle docs and en docs (#7042)

* update PP-Vehicle docs and en docs

* add reid model in v2.5 modelzoo

* update more

* update ppvehicle en doc, test=document_fix

* refine vehicle doc, test=document_fix

* multi_thread & multi_rtsp input (#6834)

* multi_thread & multi_rtsp input; test=document_fix

* update rtsp docs; test=document_fix

* update savename,add threadid to name;test=document_fix

* update pphuman&ppvehicle configs relative path

* update pphuman model of keypoint\attribute\action recognition

* update jetson docs

* mv yolov3 pedestrian to pphuman

* update ppvehicle&human det

* update links

* add vehicle plate & attribute

* add pphuman json & ppvehicle json

* add en doc for vehicle attr

* fix some grammer problems

* fix grammer

* fix command line error in doc

* update ppvehicle modelzoo; test=document_fix

* update pipeline pictures

* update

* fix platerec jetson trtfp16; test=document_fix

* replace all --model_dir in pipeline docs; test=document_fix

* skip frames for faster mot

* fix skip frame mot

* fix skip frame mot

* fix skip frame mot

* set skip frame default -1, test=document_fix

* illegal parking for ppvehicle quick start

* add docs for illegal parking

* delete useless number

* modify docs format

* add English version of doc for illegal parking

* modify md5sum for mot_ppyoloe_l_36e_ppvehicle

* delete old ocr models

* add pp-vehicle deploy doc, test=document_fix

* fix readme typo, test=document_fix

* add ppvehicle_plate

* replace cn codes

* update docs

* update mot model

* 1. add -o command for pipeline;
2. remove basemode config;
3. add example configs for pphuman.

* copyright to Copyright

* 1. update docs for quick start;
2. delete merge_model_dir;
3. move cfg codes to cfg_utils.py

* Update QUICK_STARTED.md

* Update PPVehicle_QUICK_STARTED.md

* Update pphuman_action.md

* Update pphuman_action_en.md

* Update pphuman_attribute.md

* Update pphuman_attribute_en.md

* Update cfg_utils.py

* check rtsp stream

* add rtsp in doc s

* visual change to false

* update rtsp command

* ppvehicle tutorials template

* rename pphuman docs

* update quickstart

* fix pphuman det mot doc, test=document_fix

* fix doc, test=document_fix

* fix doc, test=document_fix

* update ppdet docs & remove static code, test=document_fix

* add pphuman doc, test=document_fix

* update action doc, test=document_fix

* update activity, test=document_fix

* optimize pphuman action document

* add en doc

* add break in counting for pphuman

* fix break in doc and codes

* fix mot break in region, test=document_fix

* fix region_polygon and region_type, test=document_fix

* add tools for get_video_info, test=document_fix

* update attr docs

* update more

* update docs

* given inference model path, download model automatically

* encapsulate auto download model as a function

* given note that default model dir is download link

* change attr model download path to https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.zip

* attribute docs update

* fix mtmct

* update docs

* add pphuman mot doc, test=document_fix

* add mot data tutorials, test=document_fix

* Update action.md

delete the step of change model name of fight recognition

* Update video_action_infer.py

get model path from model_dir without model name

* optimize action vis

* add docs, still in working

* add action doc

* add action en doc