Road Traffic Sign Recognition

Slides:



Advertisements
Similar presentations
Example: ZIP Code Recognition Classification of handwritten numerals.
Advertisements

Spatial Pyramid Pooling in Deep Convolutional
Neural Network Tool Box Khaled A. Al-Utaibi. Outlines  Neuron Model  Transfer Functions  Network Architecture  Neural Network Models  Feed-forward.
Feedforward semantic segmentation with zoom-out features
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition arXiv: v4 [cs.CV(CVPR)] 23 Apr 2015 Kaiming He, Xiangyu Zhang, Shaoqing.
Assignment 4: Deep Convolutional Neural Networks
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
When deep learning meets object detection: Introduction to two technologies: SSD and YOLO Wenchi Ma.
Big data classification using neural network
Intrusion Detection using Deep Neural Networks
CS 4501: Introduction to Computer Vision Object Localization, Detection, Semantic Segmentation Connelly Barnes Some slides from Fei-Fei Li / Andrej Karpathy.
Convolutional Neural Network
Mini Places Challenge Adrià Recasens, Nov 21.
Lecture 3. Fully Connected NN & Hello World of Deep Learning
Computer Science and Engineering, Seoul National University
DeepCount Mark Lenson.
Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek
Jure Zbontar, Yann LeCun
Understanding and Predicting Image Memorability at a Large Scale
Applications of Deep Learning and how to get started with implementation of deep learning Presentation By : Manaswi Advisor : Dr.Chinmay.
The Need for Speed: Benchmarking DL Workloads
Robust Lung Nodule Classification using 2
Intelligent Information System Lab
Summary Presentation.
Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis
Policy Compression for MDPs
Urban Sound Classification with a Convolution Neural Network
A brief introduction to neural network
Generalization ..
A Convolutional Neural Network Cascade For Face Detection
Handwritten Digits Recognition
Layer-wise Performance Bottleneck Analysis of Deep Neural Networks
Bird-species Recognition Using Convolutional Neural Network
Mitchell Kossoris, Catelyn Scholl, Zhi Zheng
Convolutional Neural Networks
Face Recognition with Deep Learning Method
NormFace:
Classification Neural Networks 1
Counting in Dense Crowds using Deep Learning
RGB-D Image for Scene Recognition by Jiaqi Guo
Construct a Convolutional Neural Network with Python
CS539: Project 3 Zach Pardos.
Basics of Deep Learning No Math Required
Optimization for Fully Connected Neural Network for FPGA application
Faster R-CNN By Anthony Martinez.
Neural Networks Geoff Hulten.
YOLO-LITE: A Real-Time Object Detection Web Implementation
Yi Zhao1, Yanyan Shen*1, Yanmin Zhu1, Junjie Yao2
Visualizing and Understanding Convolutional Networks
Coding neural networks: A gentle Introduction to keras
Convolutional Network by GoogLeNet
ImageNet Classification with Deep Convolutional Neural Networks
Introduction to Neural Networks
Automating stroke lesion segmentation in brain images using a multi-model multi-path convolutional neural network Yunzhe.
Deep Object Co-Segmentation
DRC with Deep Networks Tanmay Lagare, Arpit Jain, Luis Francisco,
Deep screen image crop and enhance
Deep screen image crop and enhance
CRCV REU 2019 Kara Schatz.
Single Parameter Tuning
Deep screen image crop and enhance
Sign Language Recognition With Unsupervised Feature Learning
Self-Supervised Cross-View Action Synthesis
Learning to Navigate for Fine-grained Classification
Introduction Face detection and alignment are essential to many applications such as face recognition, facial expression recognition, age identification,
Deep screen image crop and enhance
An introduction to neural network and machine learning
Overall Introduction for the Lecture
Shengcong Chen, Changxing Ding, Minfeng Liu 2018
Presentation transcript:

Road Traffic Sign Recognition ECE 539 Project Road Traffic Sign Recognition Bo Peng bo.peng@wisc.edu

Background & Motivation Traffic signs ensure the safety when people drive Automatic recognition for autonomous driving (DataCamp)

Data Belgian Traffic Signs Dataset (64 categories ) Training: 4575 images / Testing: 2520 images

Data German Traffic Signs Dataset (43 categories ) Training: 39,209 images / Testing: 12,630 images

Method Data transformation Resize all the images into the same size, e.g., 64 × 64 Normalize the greyscale of the images to [0, 1] Divide training data into training part and validation part Size of validation data: 20% Convolutional neural network + fully connected layers

Results and Discussion Training process Epoch: 1...Train acc: 50.0%...Validation acc: 62.5%...Validation loss: 1.245 Epoch: 2...Train acc: 90.6%...Validation acc: 90.6%...Validation loss: 0.245 Epoch: 3...Train acc: 96.9%...Validation acc: 96.9%...Validation loss: 0.117 Epoch: 4...Train acc: 100.0%...Validation acc: 96.9%...Validation loss: 0.183 Epoch: 5...Train acc: 100.0%...Validation acc: 100.0%...Validation loss: 0.029 Epoch: 6...Train acc: 96.9%...Validation acc: 90.6%...Validation loss: 0.179 Acc = percentage of images being correctly recognized Loss = softmax cross entropy between truth and predictions Epoch 6 is over-fitting

Results and Discussion Belgian Traffic Signs German Traffic Signs Image size Num of epochs Batch size Testing acc 64 7 16 89.7% 32 86.0% 79.8% Image size Num of epochs Batch size Testing acc 32 6 16 89.7% 87.0% 5 88.0%