Real-time traffic light detection from videos with inertial sensor fusion

Khan, Nishat Anjum; Ansari, Rashid

doi:10.1145/3284566.3284573

Cited by 3 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Videos and inertial sensor fusion can be leveraged in systems providing real-time traffic light detection systems for BVI pedestrian navigation [ 49 ]. The inertial sensors are used to estimate the orientation, by fusing gyroscope, accelerometer and magnetic field sensor data, and motion of the camera, which is used to correct for the distortion in the image caused by the camera’s tilt and to calculate the position of the traffic light in the image.…”

Section: Resultsmentioning

confidence: 99%

“…Finally, only 14% of these solutions can be used in real-life scenarios with some degree of success, 29% of them are practical but have a combination of either high cost or require from the user to carry many sensors, 24% are limited practicality for specific scenarios while 32% are purely experimental. N/A N/A N/A N/A [49] ✖ ✖ ✖ ✖ ✖ [50] N/A N/A N/A N/A [51] N/A N/A 5 m 95% [52] 0 m < R < 9 m 98% [53] ✖ 0.1 m < R < 3.5 m 90-95% [54] N/A N/A N/A N/A [55] N/A N/A 0.2 m < R < 10 m N/A [56] ✖ R > 2 m N/A [57] ✖ N/A N/A [58] 2 cm < R < 4.5 m N/A [59] ✖ N/A 67-98% [60] 2 cm < R < 12 m N/A [61][62][63]…”

Section: Literature Reviewmentioning

confidence: 99%

“…N/A N/A N/A [49] rs 2023, 23, x FOR PEER REVIEW 9 of 29 and camera sensors is expected given the proliferation of smartphone devices as the preferred platform for developing solutions for the BVI individuals. Finally, only 14% of these solutions can be used in real-life scenarios with some degree of success, 29% of them are practical but have a combination of either high cost or require from the user to carry many sensors, 24% are limited practicality for specific scenarios while 32% are purely experimental.…”

Section: N/amentioning

confidence: 99%

See 2 more Smart Citations

Multi-Sensor Data Fusion Solutions for Blind and Visually Impaired: Research and Commercial Navigation Applications for Indoor and Outdoor Spaces

Theodorou

Tsiligkos

Μηλιώνης

2023

Sensors

View full text Add to dashboard Cite

Several assistive technology solutions, targeting the group of Blind and Visually Impaired (BVI), have been proposed in the literature utilizing multi-sensor data fusion techniques. Furthermore, several commercial systems are currently being used in real-life scenarios by BVI individuals. However, given the rate by which new publications are made, the available review studies become quickly outdated. Moreover, there is no comparative study regarding the multi-sensor data fusion techniques between those found in the research literature and those being used in the commercial applications that many BVI individuals trust to complete their everyday activities. The objective of this study is to classify the available multi-sensor data fusion solutions found in the research literature and the commercial applications, conduct a comparative study between the most popular commercial applications (Blindsquare, Lazarillo, Ariadne GPS, Nav by ViaOpta, Seeing Assistant Move) regarding the supported features as well as compare the two most popular ones (Blindsquare and Lazarillo) with the BlindRouteVision application, developed by the authors, from the standpoint of Usability and User Experience (UX) through field testing. The literature review of sensor-fusion solutions highlights the trends of utilizing computer vision and deep learning techniques, the comparison of the commercial applications reveals their features, strengths, and weaknesses while Usability and UX demonstrate that BVI individuals are willing to sacrifice a wealth of features for more reliable navigation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: N/amentioning

confidence: 99%

See 1 more Smart Citation

Multi-Sensor Data Fusion Solutions for Blind and Visually Impaired: Research and Commercial Navigation Applications for Indoor and Outdoor Spaces

Theodorou

Tsiligkos

Μηλιώνης

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Khan and Ansari [6] employed inertial sensor fusion to perform real-time traffic light detection from videos. They built a fusion system by utilizing a smartphone to capture the frames of images and a computer to do the traffic light detection.…”

Section: Related Workmentioning

confidence: 99%

Traffic Light Recognition Assistance for Colour Vision Deficiency Using Deep Learning

Lee¹,

Ng²,

Yap³

et al. 2022

Proceedings of the International Conference on Computer, Information Technology and Intelligent Computing (CITIC 2022)

View full text Add to dashboard Cite

This research intends to train a model to recognize traffic light signals in real-time to allow a person with Colour Vision Deficiency to identify the current signal of traffic lights with a mobile device's camera. First, LISA Traffic Light Dataset is downloaded obtained from Kaggle. Then, two data pre-processing steps are carried out, namely label map generation and TFRecords conversion. A total of six models,

show abstract

Real-Time Image Detection of Traffic Light in Complex Intersection Traffic Environment

Shifu

Zheng

et al. 2021

2021 IEEE International Conference on Data Science and Computer Application (ICDSCA)

View full text Add to dashboard Cite

Real-time traffic light detection from videos with inertial sensor fusion

Cited by 3 publications

References 30 publications

Multi-Sensor Data Fusion Solutions for Blind and Visually Impaired: Research and Commercial Navigation Applications for Indoor and Outdoor Spaces

Multi-Sensor Data Fusion Solutions for Blind and Visually Impaired: Research and Commercial Navigation Applications for Indoor and Outdoor Spaces

Traffic Light Recognition Assistance for Colour Vision Deficiency Using Deep Learning

Real-Time Image Detection of Traffic Light in Complex Intersection Traffic Environment

Contact Info

Product

Resources

About