Object Detection Using Mobilenet Single Shot Detector

Made by nilutpolkashyap

About the project

The Google Coral Camera attached to the NavQ board is able to detect objects like cat, dog, car, etc.

Project info

Difficulty: Moderate

Platforms: NXP, Python

Estimated time: 4 days

License: MIT license (MIT)

Items used in this project

Hardware components

NXP 8MMNavQ Kit Starter Kit

x 1

Hand tools and fabrication machines

Python 3.0

x 1

Story

By using SSD, we only need to take one single shot to detect multiple objects within the image, while regional proposal network (RPN) based approaches such as R-CNN series that need two shots, one for generating region proposals, one for detecting the object of each proposal. Thus, SSD is much faster compared with two-shot RPN-based approaches.

I used the dnn module (Deep Neural Networks) of OpenCV for loading the caffe and prototxt files.

I found the MobileNetSSD_deploy.prototxt.txt and MobileNetSSD_deploy.caffemodel pre-trained weight files from the https://awesomeopensource.com/project/chuanqi305/MobileNet-SSD

Schematics, diagrams and documents

gallery_JF7p5puVws.jpg

Code

mobilenet_ssd_object_detection

Credits

nilutpolkashyap

A multidisciplinary engineering graduate with expertise in designing and building intelligent robotics systems. Profound knowledge in ROS, SLAM, Path Planning, Motion Planning and Computer Vision. Have a systematic approach towards research with experience in technical documentation aiming to carry out high impact research work.