Develop a vehicle and pedestrian counter in the Nvidia Jetson Nano using the GPU
Budget: $250 – $750 USD
We are a video processing company and we use the Jetson Nano for face recognition and people counting.
Currently, we are having problems integrating a traffic counter which detects, tracks, and finally counts cars, motorcycles, bicycles, and pedestrians.
The developer has to have a Jetson nano to be able to develop the solution and provide a tested source code as a deliverable.
The final code has to be able to count cars, pedestrians, motorcycles, and bicycles using a Jetson nano of 4GB of RAM memory and all the following types of inputs:
A USB camera.
An IP camera using RTSP
a local video saved in the Jetson nano
One possible solution is to use deepstream as described in the following link:
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Python_Sample_Apps.html#sample-application-source-details
Currently, we are having problems integrating a traffic counter which detects, tracks, and finally counts cars, motorcycles, bicycles, and pedestrians.
The developer has to have a Jetson nano to be able to develop the solution and provide a tested source code as a deliverable.
The final code has to be able to count cars, pedestrians, motorcycles, and bicycles using a Jetson nano of 4GB of RAM memory and all the following types of inputs:
A USB camera.
An IP camera using RTSP
a local video saved in the Jetson nano
One possible solution is to use deepstream as described in the following link:
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Python_Sample_Apps.html#sample-application-source-details