Data Set For NXP AIM
Last updated
Was this helpful?
Last updated
Was this helpful?
In NXP AIM 2024, we will be working on following traffic signs:
Go Straight Traffic Sign
Turn Left Traffic Sign
Turn Right Traffic Sign
Stop Traffic sign
Teams have to divide the dataset into train/validation/test sub-sets on their own.
Teams can add more images to the data set as per their needs by refering to images of finalised traffic sign design in below file
The below file conatins all the images that can be used in training of your model are present here.
The below file conatins all the images along with information about their labels and clases that can be used in training of ypur model are present here.
Teams need to devide the images into train,val and test categories themselves and then create suiatble folders and edit this yaml file
The below links contain file containing images with multiple signs classes in a single image along with information about their labels and clases that can be used in training of ypur model are present here.
Labbled data set for Pytorch - Pytorch_Dataset_Multi_Class_Images.
Labbled data set for OBB (Tensorflow) - OBB_Dataset_Multi_Class_Images.
Teams need to devide the images into train,val and test categories themselves and then create suiatble folders and edit this yaml file
The below links conatins all the images that can be used in training of your model to detect the Traffic Light to be used in AIM Grand finale.
Unlabbled data set for red/green light - Traffic_Light_Imahes.
The link contains 1700+ red lights and 700+ green light images. We recommend all participants only to train model for red traffic light and consider it an extension of stop sign.
The below links conatins all the images that can be used in training of your model to detect the Traffic Light as well as traffic lights to be used in AIM Grand finale.
Final labbled data set - Final Dataset.
This is updated dataset for traffic signs as well as traffic lights. In this data set there are more images, as well as the bounding boxes are improved to achieve better results