This paper highlights the topic of object recognition and its algorithms, used in detection of different objects. By using the concept of object recognition, emergency vehicles like ambulances, fire trucks and ambulances can be identified on the way so that a clear path can be made for them. This can be used in autonomous vehicles as an algorithm to identify emergency vehicles. This paper is an extension of a previous paper (Goel et al. in Intelligent communication, control and devices. Springer, Singapore [1]), highlighting present techniques related to object detection. In this paper, the focus is to develop a machine learning model that is built on YOLO algorithm and is able to recognize emergency vehicles. Model proposed is Extended-YOLO (Ex-YOLO), an extension of YOLO. It is basically an ML pipeline with two phases, one is the YOLO algorithm that creates bounding boxes across objects and the other would be the classifier that would detect emergency vehicles. The output from the YOLO algorithm is cropped out and then preprocessed. Image tensors are then passed to Phase II classifiers that are pretrained and classified the images to further categories. Classifiers present in Phase II of the pipeline work independently.
CITATION STYLE
Baghel, A., Srivastava, A., Tyagi, A., Goel, S., & Nagrath, P. (2020). Analysis of Ex-YOLO Algorithm with Other Real-Time Algorithms for Emergency Vehicle Detection. In Lecture Notes in Networks and Systems (Vol. 121, pp. 607–618). Springer. https://doi.org/10.1007/978-981-15-3369-3_45
Mendeley helps you to discover research relevant for your work.