# Deep learning by Yolo Darknet vs HAAR and LBP cascades in people detection

> People detection compared on the same dataset: YOLO Darknet in the OpenCV 4 DNN module against HAAR and LBP cascades, with CPU results for each.

- Canonical URL: https://www.funvisiontutorials.com/blog/deep-learning-yolo-darknet-vs-haar-lbp/
- Author: Vladimir Kucera
- Published: 2019-02-26
- Updated: 2023-09-13
- Topics: Object detection, Deep learning
- Videos: https://www.youtube.com/watch?v=WBsSt57Bm78, https://www.youtube.com/watch?v=yIpw3_YUw6Q, https://www.youtube.com/watch?v=kMxRlvSKPp4, https://www.youtube.com/watch?v=lidhA50duEY

I just performed people detection by the Yolo model in the Opencv 4 DNN module. I analyzed my old dataset, which was used for the same task performed by Haar, LBP as well.

I will let the evaluation on your visual feeling. Let me know if there is an application out there building on HAAR, LBP. I think that even the camera's head focus/tracking systems are no more based on HAARs. Your comments are welcomed on Facebook.

## YOLO DARKNET (CPU performance) people detection in OpenCV 4

300 ms per image- width=316 --height=510 --scale=0.00392

###

Video: https://www.youtube.com/watch?v=WBsSt57Bm78

## LBP based detectMultiscale

Video: https://www.youtube.com/watch?v=yIpw3_YUw6Q

## HAAR based detectMultiscale

Video: https://www.youtube.com/watch?v=kMxRlvSKPp4

## HAAR based detectMultiscale

Video: https://www.youtube.com/watch?v=lidhA50duEY