智慧城市-智慧城管系列-2.1-人流统计-PaddleDetection

1 离线人流统计测试：

https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/deploy/pipeline/docs/tutorials/pphuman_mot.md

1.1 图片检测

安装

pip install -r requirements.txt 

python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml \
                                                   --image_file=test_image.jpg \
                                                   --device=gpu

1.2 视频追踪

MOT:
  model_dir: https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip
  tracker_config: deploy/pipeline/config/tracker_config.yml
  batch_size: 1
  skip_frame_num: 2
  enable: True

python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml -o MOT.enable=True  MOT.skip_frame_num=-1 \
--video_file=test_video.mp4 \
--device=gpu

1.3 人流统计

python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml -o MOT.enable=True \
                                                   --video_file=test_video.mp4 \
                                                   --device=gpu \
                                                   --draw_center_traj \
                                                   --do_break_in_counting \
                                                   --region_type=custom \
                                                   --region_polygon 605 258 1170 316 1140 490 574 410

1.3.1 人流统计,自定义统计区域

python deploy/pipeline/tools/get_video_info.py --video_file=test_video.mp4 --region_polygon 550 310 1171 331 1177 353 550 339

2 在线人流统计测试：

目前是支持rstp单路视频流的输入：https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/deploy/pipeline/docs/tutorials/PPHuman_QUICK_STARTED.md