Blind Spot Detection System in Vehicles Using Fusion of Radar Detections and Camera Verification
| Autor: | Shayan Shirahmad Gale Bagi, Behzad Moshiri, Hossein Gharaee Garakani, Mohammad Khoshnevisan |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
Aerospace Engineering 010501 environmental sciences 01 natural sciences k-nearest neighbors algorithm law.invention law 0502 economics and business Computer vision Radar MATLAB 0105 earth and related environmental sciences computer.programming_language 050210 logistics & transportation business.industry General Neuroscience Applied Mathematics Blind spot 05 social sciences Probabilistic logic Sensor fusion Object detection Computer Science Applications Control and Systems Engineering Automotive Engineering Artificial intelligence business Joint (audio engineering) computer Software Information Systems |
| Zdroj: | International Journal of Intelligent Transportation Systems Research. 19:389-404 |
| ISSN: | 1868-8659 1348-8503 |
| Popis: | Sensors are the quintessential part of Blind Spot Detection (BSD) systems, which have a profound effect on the performance of the system. Every sensor has its unique deficiencies that can deteriorate the performance of the system under grievous circumstances. Hence, making vital tasks in BSD such as object detection arduous. Indeed, previous studies have demonstrated that data fusion techniques can diminish the adverse effects of sensors and improve detection accuracy in the BSD system. One of the main advantages of data fusion is to improve detection accuracy and reduce the processing time by multiple sensors cooperation. We propose a BSD model that objects are detected in consecutive time intervals in the BSD system. Then, association techniques are employed for multi-sensor fusion since all sensors data are not ordinarily ready for fusion simultaneously. It should be noted that the orthodox approach in data association techniques in BSD often includes a global nearest neighbor, joint probabilistic data association, and multiple hypothesis tests. We simulate and compare these techniques by tracking multiple targets and multi-sensor fusion using virtual data in MATLAB. Furthermore, we illustrate that our multi-sensor fusion detection accuracy in the BSD system is augmented compared to a single sensor BSD system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink