This is a dance pipeline project code.

The correct code is stored in lifang535/dance.

Mainly including VideoToFrame, ObjectDetection, PostureRecognition, PersonRecognition, GenderRecognition, AgeRecognition, ExpressionRecognition and FrameToVideo.

Dance Monitoring Pipeline

The modules are in dance/module:

• VideoToFrame: Extracts frames from video, and sends them to ObjectDetection.
• ObjectDetection: Detects persons, and sends them with boxes to PostureRecognition and PersonRecognition respectively.
• PostureRecognition: Reads the posture in the box of the frame, and sends frame with box and label to FrameToVideo.
• PersonRecognition: Recognizes the face in the box of the frame, and sends frame with box and label to GenderRecognition.
• GenderRecognition: Recognizes the gender in the box of the frame, and sends frame with box and label to AgeRecognition.
• AgeRecognition: Recognizes the age in the box of the frame, and sends frame with box and label to ExpressionRecognition.
• ExpressionRecognition: Recognizes the expression in the box of the frame, and sends frame with box and label to FrameToVideo.
• FrameToVideo: Collects frames with boxes, labels and postures, and combines them into a video.

Model Source

• ObjectDetection: YOLOs Tiny
• PostureRecognition: Openpose
• PersonRecognition: Face Recognition
• GenderRecognition: Gender Recognition
• AgeRecognition: Age Recognition
• ExpressionRecognition: Expression Recognition

Quick Start

Install the required libraries:

$ pip3 install -r requirements.txt

Adjust configuration in dance/module/configs.py.

Execute:

$ cd module
$ python3 pipeline.py

Then, the pipeline will read the videos from dance/input_video, process them, and save the processed videos in dance/output_video.

Docker

Note: This is an image of the traffic monitoring pipeline. Please make sure to clone the dance monitoring pipeline repository first.

Search for the Docker image:

$ docker search traffic_monitoring_pipeline

Pull the image:

$ docker pull lifang535/traffic_monitoring_pipeline_with_git_v3

Create and run the container:

$ docker run --gpus all -it --rm --name temp traffic_monitoring_pipeline_with_git_v3

Pull the repository:

All dependencies have been installed. Execute the following commands:

$ cd /
$ git clone https://github.com/lifang535/dance.git

Execute the pipeline:

Execute:

$ cd dance/module
$ python3 pipeline.py