Fully Annotated Indian Traffic Signs Database for Recognition

Sanyal, Banhi; Mohapatra, Ramesh Kumar; Dash, Ratnakar

doi:10.1007/978-981-15-4032-5_63

Cited by 2 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(b) Figure 1 shows the different types of images including broken images to blur has been included in the IRSDBv1.0 database. 16 As such a high amount of challenge coupled with a low number of images poses a threat to any implemented classifier.…”

Section: Discussionmentioning

confidence: 99%

“…The data that support the findings of this study are available in [GTSRB, IRSDBv1.0] at [https://www.kaggle.com/meowmeowmeowmeowmeow/ gtsrb-german-traffic-sign, https://nitrkl.ac.in/CS/Datasets.aspx], reference number. 16,17 These data were derived from the following resources available in the public domain: [GTSRB at doi = "10.1109/IJCNN.2011.6033395" and IRSDBv1.0 at doi="10.1109/AISP48273.2020.9072976"].…”

Section: Data Availability Statementmentioning

confidence: 99%

“…The choice of databases are discussed as follows: GTSRB • GTSRB is chosen as it has the highest total number of images. It is a standard benchmark for traffic signs. A huge chunk of researchers has worked on it. So it will be easy to compare and give competitive results. IRSDBv1.0 • As discussed, there is no Indian database for researchers to work on. A detailed discussion on the differences between Indian and non‐Indian database are penned down by Sanyal et al 16 As such, IRSDBv1.0 is selected as the only publicly available traffic sign Indian database. …”

Section: Motivationmentioning

confidence: 99%

“…IRSDBv1.0 • As discussed, there is no Indian database for researchers to work on. A detailed discussion on the differences between Indian and non‐Indian database are penned down by Sanyal et al 16 As such, IRSDBv1.0 is selected as the only publicly available traffic sign Indian database. …”

Section: Motivationmentioning

confidence: 99%

“…A detailed discussion on the differences between Indian and non‐Indian database are penned down by Sanyal et al 16 …”

Section: Motivationmentioning

confidence: 99%

See 4 more Smart Citations

Traffic sign recognition on Indian database using wavelet descriptors and convolutional neural network ensemble

Sanyal

Mohapatra

Dash

2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Traffic sign recognition (TSR) has been a rising and lucrative field for researchers during the last decades. The high improvement of ADAS (autonomic driving autonomous system) has led researchers worldwide to concentrate on the development of TSR systems. As such, a novel automated multiclass TSR system is proposed. The architecture uses wavelet descriptors to extract the high information density and the traffic signs' edges and curves. The LL band image is directly fed into the classifier to avoid normalization. Three classifiers, CNN, CNN ensemble, and LSTM, are deployed for recognition. The architecture is implemented on IRSDBv1.0, the first available Indian traffic sign database. The architecture is also implemented on the standard traffic sign database GTSRB to investigate its effectiveness. An efficiency of 71.57% and 96.76% are recorded on IRSDBv1.0, and GTSRB, respectively. A list of comparative results is also provided to prove the competence of the architecture. The reasons behind the difference in the achieved accuracy are also discussed.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Data Availability Statementmentioning

confidence: 99%