A simple pedestrian detector using the SVM model

In this recipe, you will learn how to detect pedestrians using a pre-trained SVM model with HOG features. Pedestrian detection is an important component of many Advanced Driver Assistance Solutions (ADAS). Pedestrian detection is also used in video surveillance systems, and many other computer vision applications.

Getting ready

Before you proceed with this recipe, you need to install the OpenCV 3.x Python API package and the matplotlib package.

How to do it...

1. Import the modules:

import cv2
import matplotlib.pyplot as plt

2. Load the test image:

image = cv2.imread('../data/people.jpg')

3. Create the HOG feature computer and detector:

hog = cv2.HOGDescriptor()
hog.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())

4. Detect the people in the image:

locations, weights = hog.detectMultiScale(image)

5. Draw the detected people bounding boxes:

dbg_image = image.copy()
for loc in locations:
    cv2.rectangle(dbg_image, (loc[0], loc[1]), 
                  (loc...