Object Detection in Self-driving Cars Using Brainy Pi

Brainy pi

– An Enterprise grade device for AI on Edge and IoT

– With support to convert your prototypes to a fully customised Hardware and Software Enterprise solution.

LINK TO BRAINYPI PAGE

What's Object detection?

Object detection is a computer vision task that has become an integral part of many consumer applications today such as surveillance and security systems, mobile text recognition, and diagnosing diseases from MRI/CT scans. Object detection is also one of the critical components to support self driving cars. They rely on the perception of their surroundings to ensure safe and robust driving performance. This perception system uses object detection algorithms to accurately determine objects such as pedestrians, vehicles, traffic signs, and barriers in the vehicle's vicinity. This project uses Tensorflow Object Detection API. This API can be used to detect with bounding boxes, objects in image or video using some of the pretrained models. Using this pretrained model we can train image for a custom object detection.

 Stages to train a model:

1. Data Collection.

2. Data cleaning and preproceesing.

3. Annotating dataset.

4. Creating label_map.pbtxt.

5. Splitting the dataset.

6.Model Architecture.

7.Training the model.

8.Testing the model.

9.Inference.

Log into Brainy-pi using the SSH

ssh -X pi@auth.iotiot.in -p 65530

pip install tensorflow

git clone "link to your repository"

Run the inference file

python3 inference.py