Object-Detection-on-Raspberry-Pi3

Main details:

Object detection is a computer vision technique that works to identify and locate objects within an image or video.

Specifically, object detection draws bounding boxes around these detected objects, which allow us to locate where said objects are in (or how they move through) a given scene.

Objects are detected using Single Shot MultiBox Detector (SSD)), a convolutional approach, and this model can detect up to 90 different objects.

The model is trained over COCO dataset using Tensorflow API and converted to Tensorflow Lite to run on power efficient devices (i.e. IoT devices) like Raspberry pi

Tools used:

Raspbian Stretch (Operating System for Raspberry pi 3)

OpenCV library

TensorFlow Lite Framework

Web Cam (i.e. to feed live video data)

Improvements:

Extending for automatic braking system, whenever a red light is detected the brakes are automatically applied

Using new raspberry pi models will give better FPS (i.e. frames per second)

Applications are not limited to Crowd counting, Self-driving cars, Video surveillance, Face detection, Anomaly detection.

Sample Frame from the video: