aarcosg/traffic-sign-detection
Traffic Sign Detection. Code for the paper entitled "Evaluation of deep neural networks for traffic sign detection systems".
Implements comparative benchmarking of eight detector-backbone combinations (Faster R-CNN, R-FCN, SSD, YOLO V2) fine-tuned on the German Traffic Sign Detection Benchmark via transfer learning from COCO pre-trained weights. Built on TensorFlow's Object Detection API, the framework evaluates trade-offs across mAP, latency, FLOPs, memory footprint, and performance on variable input sizes, with pretrained models and evaluation notebooks provided for reproducibility.
336 stars. No commits in the last 6 months.
Stars
336
Forks
101
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aarcosg/traffic-sign-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
davidbrai/deep-learning-traffic-lights
Code and files of the deep learning model used to win the Nexar Traffic Light Recognition challenge
hoanglehaithanh/Traffic-Sign-Detection
Traffic signs detection and classification in real time
thibo73800/capsnet-traffic-sign-classifier
A Tensorflow implementation of CapsNet(Capsules Net) apply on german traffic sign dataset
alexstaravoitau/traffic-signs
Building a CNN based traffic signs classifier.
surmenok/GTSRB
Convolutional Neural Network for German Traffic Sign Recognition Benchmark