Real-time pedestrian crossing lights detection algorithm for the visually impaired

Cheng, Ruiqi; Wang, Kaiwei; Yang, Kailun; Long, Ningbo; Bai, Jian; Liu, Dong

doi:10.1007/s11042-017-5472-5

Cited by 34 publications

(26 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Without even re-training our network, we tested our network on the China portion of the PTLR Dataset, which uses input images of size 1280 × 720 [7]. The only processing we did was to change all network predictions of class Table 7.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…"countdown green" and "countdown blank" to be a prediction of "none", because the images in the China section of the PTLR Dataset were only from three different classes: red, green, and none. After testing our network on the dataset, we compared our results to the results from [21] and [7]. As shown in Table 7, our network outperforms both methods in F1 Score.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…There have been many attempts to alleviating such privation. One such attempt has been the acoustic pedestrian traffic lights [17,4,7]. These specific traffic lights uses audible tones, verbal messages, and/or vibrating surfaces to communicate essential information such as the color of the pedestrian traffic light, and thus, whether it is safe to cross or not [4].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Street Crossing Aid Using Light-Weight CNNs for the Visually Impaired

Lee

Kim

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

In this paper, we address an issue that the visually impaired commonly face while crossing intersections and propose a solution that takes form as a mobile application. The application utilizes a deep learning convolutional neural network model, LytNetV2, to output necessary information that the visually impaired may lack when without human companions or guide-dogs. A prototype of the application runs on iOS devices of versions 11 or above. It is designed for comprehensiveness, concision, accuracy, and computational efficiency through delivering the two most important pieces of information, pedestrian traffic light color and direction, required to cross the road in real-time. Furthermore, it is specifically aimed to support those facing financial burden as the solution takes the form of a free mobile application. Through the modification and utilization of key principles in MobileNetV3 such as depthwise seperable convolutions and squeeze-excite layers, the deep neural network model achieves a classification accuracy of 96% and average angle error of 6.15 • , while running at a frame rate of 16.34 frames per second. Additionally, the model is trained as an image classifier, allowing for a faster and more accurate model. The network is able to outperform other methods such as object detection and non-deep learning algorithms in both accuracy and thoroughness. The information is delivered through both auditory signals and vibrations, and it has been tested on seven visually impaired and has received above satisfactory responses.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Street Crossing Aid Using Light-Weight CNNs for the Visually Impaired

Lee

Kim

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

show abstract

“…In (B), the model correctly predicted the class despite the symbol being underexposed by the camera. To prove the effectiveness of LYTNet, we retrained it using only red, green, and none class pictures from our own dataset and tested it on the PTLR dataset [5]. Due to the small size of the PTLR training dataset, we were unable to perform further training or fine-tuning using the dataset without significant overfitting.…”

Section: Methodsmentioning

confidence: 99%

LYTNet: A Convolutional Neural Network for Real-Time Pedestrian Traffic Lights and Zebra Crossing Recognition for the Visually Impaired

Lee

Kim

2019

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Currently, the visually impaired rely on either a sighted human, guide dog, or white cane to safely navigate. However, the training of guide dogs is extremely expensive, and canes cannot provide essential information regarding the color of traffic lights and direction of crosswalks. In this paper, we propose a deep learning based solution that provides information regarding the traffic light mode and the position of the zebra crossing. Previous solutions that utilize machine learning only provide one piece of information and are mostly binary: only detecting red or green lights. The proposed convolutional neural network, LYTNet, is designed for comprehensiveness, accuracy, and computational efficiency. LYTNet delivers both of the two most important pieces of information for the visually impaired to cross the road. We provide five classes of pedestrian traffic lights rather than the commonly seen three or four, and a direction vector representing the midline of the zebra crossing that is converted from the 2D image plane to real-world positions. We created our own dataset of pedestrian traffic lights containing over 5000 photos taken at hundreds of intersections in Shanghai. The experiments carried out achieve a classification accuracy of 94%, average angle error of 6.35 • , with a frame rate of 20 frames per second when testing the network on an iPhone 7 with additional post-processing steps.

show abstract

“…Histogram of Oriented Gradients (HOG), as outlined in the study by Dalal and Triggs [1], is a feature descriptor that is commonly used for object detection. Its applications include: people detection in images and videos [1], pedestrian detection [2], palmprint recognition [3], sketch based image retrieval [4], scene text recognition [5], traffic sign detection [6], traffic light detection [7], and vehicle detection [8].…”

Section: Introductionmentioning

confidence: 99%

Dihedral Group D4—A New Feature Extraction Algorithm

Sharma

2020

Symmetry

View full text Add to dashboard Cite

In this paper, we propose a new feature descriptor for images that is based on the dihedral group D 4 , the symmetry group of the square. The group action of the D 4 elements on a square image region is used to create a vector space that forms the basis for the feature vector. For the evaluation, we employed the Error-Correcting Output Coding (ECOC) algorithm and tested our model with four diverse datasets. The results from the four databases used in this paper indicate that the feature vectors obtained from our proposed D 4 algorithm are comparable in performance to that of Histograms of Oriented Gradients (HOG) model. Furthermore, as the D 4 model encapsulates a complete set of orientations pertaining to the D 4 group, it enables its generalization to a wide range of image classification applications.

show abstract

Real-time pedestrian crossing lights detection algorithm for the visually impaired

Cited by 34 publications

References 20 publications

Street Crossing Aid Using Light-Weight CNNs for the Visually Impaired

Street Crossing Aid Using Light-Weight CNNs for the Visually Impaired

LYTNet: A Convolutional Neural Network for Real-Time Pedestrian Traffic Lights and Zebra Crossing Recognition for the Visually Impaired

Dihedral Group D4—A New Feature Extraction Algorithm

Contact Info

Product

Resources

About