Related Objects of Interest: stop, roundabout, no entry, no stopping, give way, parking, pedestrian crossing, slippery road, speed limit 30, car
Top Traffic Datasets and Models
The datasets below can be used to train fine-tuned models for traffic detection. You can explore each dataset in your browser using Roboflow and export the dataset into one of many formats.
At the bottom of this page, we have guides on how to train a model using the traffic datasets below.
4320 images 127 classes
by f
86 images 46 classes
Bus stop Cycle track Dip Filling station Guarded level crossing ahead Height limit-3.5m Hotel Keep left Level crossing countdown marker Narrow road Ngã Ba No Left turn No entry No entry for Trucks No entry for bicycles No entry for motor vehicles No entry for pedestrians No parking No passing No vehicles in both directions
by kendrickxy
2312 images 119 classes
roundabout Bump Car breaking Children Crosswinds Curve Cyclist crossing Cyclists Dip Domestic animals End of all previously signed restrictions End of no overtaking End of no overtaking by heavy goods vehicles End of no parking zone End of priority road End of speed limit 30 End of speed limit zone 30 Entering city Exiting city Falling rocks
by Rohith Pai
83 images 75 classes
5574 images 85 classes
7195 images 74 classes
388 images 17 classes
9900 images 56 classes
5117 images 54 classes
by trafficsign
507 images 22 classes
by 4300
4300 images 47 classes
stop Ahead only Beaware of icesnow Bumpy road Children Crossing Dangerous curve left Dangerous curve right Double curve End Speed - Passing limits End no passing veh 3-5 tons End of no passing General caution Go Stright or Left Go Stright or Right Keep Left Keep Right No entry No passing No passing veh over 3-5 tons No vechiels
3240 images 21 classes
* Auto-orientation of pixel data (with EXIF-orientation stripping) * Resize to 640x640 (Stretch) * annotate, and create datasets * collaborate with your team on computer vision projects * collect & organize images * export, train, and deploy computer vision models * understand and search unstructured image data * use active learning to improve your dataset over time 19 20 ============================== For state of the art Computer Vision training notebooks you can use with this dataset, No image augmentation techniques were applied. Roboflow is an end-to-end computer vision platform that helps you The dataset includes 3385 images. The following pre-processing was applied to each image: This dataset was exported via roboflow.com on May 24, 2023 at 4:29 PM GMT To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com Traffic-Signs are annotated in YOLOv8 format. new_classes - v8 2023-05-24 7:26pm
by trafficsign
4660 images 25 classes
by kaushik
8015 images 78 classes
* 50% probability of horizontal flip * 50% probability of vertical flip * Random Gaussian blur of between 0 and 3.25 pixels * Randomly crop between 0 and 33 percent of the image * annotate, and create datasets * collaborate with your team on computer vision projects * collect & organize images * export, train, and deploy computer vision models * understand and search unstructured image data * use active learning to improve your dataset over time 100 120 21 22 23 24 25 26 27 28
by t
5228 images 45 classes