Topics

#distacne #distance-calculation #distance-estimation-opencv #distance-estimation-python #distance-measure-opencv #opencv #python #yolov4-distance-estimation #yolov4-tiny

Language breakdown

Python 100.0%

▸ Files click to expand

README

Yolov4-Detector-and-Distance-Estimator

Find the distance from the object to the camera using the YoloV4 object detector, here we will be using a single camera :camera:, detailed explanation of distance estimation is available in another repository Face detection and Distance Estimation using single camera

https://user-images.githubusercontent.com/66181793/124917186-f5066b00-e00c-11eb-93cf-24d84e9c2e7a.mp4

Video Tutorial Explains the concept and implementation

Here we are targeting the person and cell phone classes only, for demo purposes.

you can follow all the steps mentioned in the video to create other objects as well.

implementation detail available on Darknet_

TO DO

[x] Finding the distance of multiple objects at the same time.

Installation you need opencv-contrib-python

opencv contrib

windows

pip install opencv-contrib-python==4.5.3.56

Linux or Mac

pip3 install opencv-contrib-python==4.5.3.56

then just clone this repository and you are good to go.

I have used tiny weights, check out more on darknet GitHub for more

Add more Classes(Objects) for Distance Estimation

You will make changes on these particular lines DistanceEstimation.py

if classid ==0: # person class id      datalist.append([classnames[classid[0]], box[2], (box[0], box[1]-2)]) elif classid ==67: # cell phone     datalist.append([classnames[classid[0]], box[2], (box[0], box[1]-2)])      Adding more classes for distance estimation 

elif classid ==2: # car     datalist.append([classnames[classid[0]], box[2], (box[0], box[1]-2)])
elif classid ==15: # cat     datalist.append([classnames[classid[0]], box[2], (box[0], box[1]-2)]) 
In that way you can include as many classes as you want 

# returning list containing the object data.  return data_list

Reading images and getting focal length

You have to make changes on these lines 📝 DistanceEstimation.py there are two situations, if the object(classes) in the single image then, here you can see my reference image it has to two object, person and cell phone

# reading reference images  ref_person = cv.imread('ReferenceImages/image14.png') ref_mobile = cv.imread('ReferenceImages/image4.png') calling the object detector function to get the width or height of the object
 getting pixel width for person
 persondata = objectdetector(ref_person) personwidthinrf = persondata[0][1]
Getting pixel width for cell phone
mobiledata = objectdetector(ref_mobile)
mobilewidthinrf = mobiledata[1][1]
getting pixel width for cat
catdata = objectdetector(ref_person)
catwidthinrf = persondata[2][1]
Getting pixel width for car
cardata = objectdetector(ref_person)
carwidthinrf = persondata[3][1]

if there is single class(object) in reference image then you approach it that way 👍

# reading the reference image from dir 
refperson = cv.imread('ReferenceImages/personref_img.png')
refcar = cv.imread('ReferenceImages/carref_img.png.png')
refcat = cv.imread('ReferenceImages/catref_img.png')
refmobile = cv.imread('ReferenceImages/refcell_phone.png')
Checking object detection on the reference image 
getting pixel width for person
persondata = objectdetector(ref_person)
personwidthinrf = persondata[0][1]
Getting pixel width for cell phone
mobiledata = objectdetector(ref_mobile)
mobilewidthinrf = mobiledata[0][1]
getting pixel width for cat
catdata = objectdetector(ref_cat)
catwidthinrf = persondata[0][1]
Getting pixel width for car
cardata = objectdetector(ref_car)
carwidthinrf = persondata[0][1]
Then you find the Focal length for each

📫 Let's Connect

💼 Freelance Platforms

💬 Questions or Need Help?

If you have any questions or need help with the project, feel free to DM me on Instagram!

🔗 More in this category