DeepSORT | end pedestrian multi-target tracking

I am trying to run this github repo found at this link: https://github.com/HowieMa/DeepSORT_YOLOv5_Pytorch After installing the requirements via pip install -r requirements.txt. I am running this in a python 3.8 virtual environment, on a dji manifold 2g which runs on an Nvidia jetson tx2.

The following is the terminal output.

I am using YoloV4 and Deepsort to detect and track people in a frame.

My goal is to get speed of a moving person in meaningful units without calibration as I would like to be able to move the camera with this model to different rooms without having to calibrate it each time. I understand this to be a very difficult problem. I am currently getting speed as pixels per second. But that is inaccurate as items closer to frame are "moving" faster.

My question is if I can use the bounding box of the person detection as a measurement of the size of a person in pixels and if I can average the size of a human being (say 68 inches height by 15 inches width) and have the necessary "calibration" metrics to determine in inches/s the object moved from Point A to Point B in the frame as a reflection of the size of the person from Region A to Region B?

In short, is there a way to get velocity from the size of an object to determine how fast it is moving in a frame?

Any suggestions would be helpful! Thanks!

This is how I am calculating speed now.

I'm currently doing some research to detect and locate a text-cursor (you know, the blinking rectangle shape that indicates the character position when you type on your computer) from a screen-record video. To do that, I've trained YOLOv4 model with custom object dataset (I took a reference from here) and planning to also implement DeepSORT to track the moving cursor.

Here's the example of training data I used to train YOLOv4:

Here's what I want to achieve:

Do you think using YOLOv4 + DeepSORT is considered overkill for this task? I'm asking because as of now, only 70%-80% of the video frame that contains the text-cursor can be successfully detected by the model. If it is overkill after all, do you know any other method that can be implemented for this task?

Anyway, I'm planning to detect the text-cursor not only from Visual Studio Code window, but also from Browser (e.g., Google Chrome) and Text Processor (e.g., Microsoft Word) as well. Something like this:

I'm considering the Sliding Window method as an alternative, but from what I've read, the method might consume much resources and perform slower. I'm also considering Template Matching from OpenCV (like this), but I don't think it will perform better and faster than the YOLOv4.

The constraint is about the performance speed (i.e, how many frames can be processed given amount of time) and the detection accuracy (i.e, I want to avoid letter 'l' or '1' detected as the text-cursor, since those characters are similar in some font). But higher accuracy with slower FPS is acceptable I think.

I'm currently using Python, Tensorflow, and OpenCV for this. Thank you very much!

Okay... So I'm trying to run this repo on my jetson nano 2gb...

I followed this official documentation for installation for tensorflow on jetson nano, while I followed https://www.tensorflow.org/install, this official documentation to run tensorflow on windows..

So after setting the dependencies on windows...the started to run smoothly with no problem.

But after setting the dependencies on jetson nano... the code showed this error..

This is my application architecture:

In my code there is a pedestrian.py file which uses a while loop to read frames from rtsp link and after doing pedestrian detection process (available in this link), it caches the frame in Redis.

(please note that in the loop each time the output frame is replaced with the previous output from loop. it means that there exists only one frame in redis in any moment.)

Then in flask application, I read processed frame from redis and send it for the clients.

This is the code for my pedestrian detection: