Near-Infrared Road-Marking Detection Based on a Modified Faster Regional Convolutional Neural Network
| Autor: | Shengjun Liu, Xiaobiao Dai, Shitu Abubakar, Hao Sha, Junping Hu, Gen Yang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Feature fusion
Article Subject Computer science business.industry Near-infrared spectroscopy Random rotation 020206 networking & telecommunications Modified method 02 engineering and technology Translation (geometry) Convolutional neural network Poor vision Control and Systems Engineering lcsh:Technology (General) 0202 electrical engineering electronic engineering information engineering lcsh:T1-995 Detection performance 020201 artificial intelligence & image processing Computer vision Artificial intelligence Electrical and Electronic Engineering business Instrumentation |
| Zdroj: | Journal of Sensors, Vol 2019 (2019) |
| ISSN: | 1687-725X |
| DOI: | 10.1155/2019/7174602 |
| Popis: | Pedestrians, motorist, and cyclist remain the victims of poor vision and negligence of human drivers, especially in the night. Millions of people die or sustain physical injury yearly as a result of traffic accidents. Detection and recognition of road markings play a vital role in many applications such as traffic surveillance and autonomous driving. In this study, we have trained a nighttime road-marking detection model using NIR camera images. We have modified the VGG-16 base network of the state-of-the-art faster R-CNN algorithm by using a multilayer feature fusion technique. We have demonstrated another promising feature fusion technique of concatenating all the convolutional layers within a stage to extract image features. The modification boosts the overall detection performance of the model by utilizing the advantages of the shallow layers and the deep layers of the VGG-16 network. The training samples were augmented using random rotation and translation to enhance the heterogeneity of the detection algorithm. We have achieved a mean average precision (mAP) of 89.48% and 92.83% for the baseline faster R-CNN and our modified method, respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text