Deepstream Pose Estimation is not able to predict joints when 3 or more person are in frame


I was trying Deepstream Pose Estimation which uses tfpose model. (GitHub - NVIDIA-AI-IOT/deepstream_pose_estimation: This is a sample DeepStream application to demonstrate a human pose estimation pipeline.).

I am getting a very good results for single and dual person in a frame but as soon as the 3rd person comes in the frame, it mess up the 2nd person skeleton. The issue seems to be while assigning the joints to the individuals. Its not able to determine which joint belongs to which person. In the images attached below, you can see that for 2 person it works well but as soon as the 3rd person comes into the picture, the joints of the 2nd person scatter across other persons in the frame.

Q1. Is there a way to get the joins properly on the individual in case of more than 2 people?


TensorRT Version:
GPU Type: GTX 1650
Nvidia Driver Version: 460.73.01
CUDA Version: 10.2
CUDNN Version: -
Operating System + Version: Ubuntu 18.04
Python Version (if applicable): 3.6.9
TensorFlow Version (if applicable): -
PyTorch Version (if applicable): -
Baremetal or Container (if container which image + tag): Deepstream 5.0/5.1 container

Relevant Files

Reference Results:

Steps To Reproduce

Follow the steps from here to reproduce the result.

1 Like

Hi @aniket.manoj,

We recommend you to post your query on Deepstream forum to get better help.

Thank you,

I have shared the same in the Deepstream Forum. thanks!