Skip to content

Latest commit

 

History

History
35 lines (33 loc) · 1.73 KB

README.md

File metadata and controls

35 lines (33 loc) · 1.73 KB
Raw

Object-Detection-MobileNet

license

Demonstration of Object Detection using MobileNets and OpenCV.

Description

This project was made for detecting 20 different types of object such as "background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor" in a live video using the webcam or a pre-recorded video.

Preview

Alt Text

Better Quality Video

IMAGE ALT TEXT

Requirements

  • numpy
  • imutils
  • OpenCV

You can install all the required libraries by running the following command
pip install requirements.txt

Functionalities

  1. Using pre-trained MobileNet architecture for detection of the objects present.
  2. Combining MobileNet and Single Shot Detector(SSD) framework.
  3. Model used is Caffe version of original TensorFlow implementation by Howard et al.

Procedure

For detecting objects in an image.

./image_object_detection.py -i #path to the input image -p #path to Caffe deploy prototxt file -m #path to the Caffe pre-trained model

For detecting objects in a video.

./video_object_detection.py -p #path to Caffe deploy prototxt file -m #path to the Caffe pre-trained model

Credits

Adrian Rosebrock creator of PyimageSearch